pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2025-10-17 13:48:37 +09:00
Code Issues Projects Releases Wiki Activity

Merge branch 'master' into extractor/arte/improvement-switch-to-config-api-v2

Browse Source
This commit is contained in:
dirkf
2023-02-14 18:24:27 +00:00
committed by GitHub
parent 0c149f04d4 dd9aa74bee
commit 82833b44d7
115 changed files with 9712 additions and 1927 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
youtube_dl/extractor/adn.py
View File

@@ -31,30 +31,34 @@ from ..utils import (
class ADNIE(InfoExtractor):
IE_DESC = 'Anime Digital Network'
_VALID_URL = r'https?://(?:www\.)?animedigitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
_TEST = {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'md5': '0319c99885ff5547565cacb4f3f9348d',
IE_DESC = 'Animation Digital Network'
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
_TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir',
'md5': '1c9ef066ceb302c86f80c2b371615261',
'info_dict': {
'id': '7778',
'id': '9841',
'ext': 'mp4',
'title': 'Blue Exorcist - Kyôto Saga - Episode 1',
'description': 'md5:2f7b5aa76edbc1a7a92cedcda8a528d5',
'series': 'Blue Exorcist - Kyôto Saga',
'duration': 1467,
'release_date': '20170106',
'title': 'Fruits Basket - Episode 1',
'description': 'md5:14be2f72c3c96809b0ca424b0097d336',
'series': 'Fruits Basket',
'duration': 1437,
'release_date': '20190405',
'comment_count': int,
'average_rating': float,
'season_number': 2,
'episode': 'Début des hostilités',
'season_number': 1,
'episode': 'À ce soir !',
'episode_number': 1,
}
}
},
'skip': 'Only available in region (FR, ...)',
}, {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'only_matching': True,
}]
_NETRC_MACHINE = 'animedigitalnetwork'
_BASE_URL = 'http://animedigitalnetwork.fr'
_API_BASE_URL = 'https://gw.api.animedigitalnetwork.fr/'
_NETRC_MACHINE = 'animationdigitalnetwork'
_BASE = 'animationdigitalnetwork.fr'
_API_BASE_URL = 'https://gw.api.' + _BASE + '/'
_PLAYER_BASE_URL = _API_BASE_URL + 'player/'
_HEADERS = {}
_LOGIN_ERR_MESSAGE = 'Unable to log in'
@@ -82,14 +86,14 @@ class ADNIE(InfoExtractor):
if subtitle_location:
enc_subtitles = self._download_webpage(
subtitle_location, video_id, 'Downloading subtitles data',
fatal=False, headers={'Origin': 'https://animedigitalnetwork.fr'})
fatal=False, headers={'Origin': 'https://' + self._BASE})
if not enc_subtitles:
return None
# http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
# http://animationdigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
bytes_to_intlist(binascii.unhexlify(self._K + 'ab9f52f5baae7c72')),
bytes_to_intlist(binascii.unhexlify(self._K + '7fac1178830cfe0c')),
bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
))
subtitles_json = self._parse_json(
@@ -138,9 +142,9 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
if not username:
return
try:
url = self._API_BASE_URL + 'authentication/login'
access_token = (self._download_json(
self._API_BASE_URL + 'authentication/login', None,
'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False,
url, None, 'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False,
data=urlencode_postdata({
'password': password,
'rememberMe': False,
@@ -153,7 +157,8 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
message = None
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
resp = self._parse_json(
e.cause.read().decode(), None, fatal=False) or {}
self._webpage_read_content(e.cause, url, username),
username, fatal=False) or {}
message = resp.get('message') or resp.get('code')
self.report_warning(message or self._LOGIN_ERR_MESSAGE)
@@ -211,7 +216,9 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
# This usually goes away with a different random pkcs1pad, so retry
continue
error = self._parse_json(e.cause.read(), video_id)
error = self._parse_json(
self._webpage_read_content(e.cause, links_url, video_id),
video_id, fatal=False) or {}
message = error.get('message')
if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
self.raise_geo_restricted(msg=message)

4
youtube_dl/extractor/aenetworks.py
View File

@@ -20,8 +20,8 @@ class AENetworksBaseIE(ThePlatformIE):
(?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
fyi\.tv
)/'''
_THEPLATFORM_KEY = 'crazyjava'
_THEPLATFORM_SECRET = 's3cr3t'
_THEPLATFORM_KEY = '43jXaGRQud'
_THEPLATFORM_SECRET = 'S10BPXHMlb'
_DOMAIN_MAP = {
'history.com': ('HISTORY', 'history'),
'aetv.com': ('AETV', 'aetv'),

2
youtube_dl/extractor/aliexpress.py
View File

@@ -18,7 +18,7 @@ class AliExpressLiveIE(InfoExtractor):
'id': '2800002704436634',
'ext': 'mp4',
'title': 'CASIMA7.22',
'thumbnail': r're:http://.*\.jpg',
'thumbnail': r're:https?://.*\.jpg',
'uploader': 'CASIMA Official Store',
'timestamp': 1500717600,
'upload_date': '20170722',

89
youtube_dl/extractor/alsace20tv.py Normal file
View File

@@ -0,0 +1,89 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
dict_get,
get_element_by_class,
int_or_none,
unified_strdate,
url_or_none,
)
class Alsace20TVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?alsace20\.tv/(?:[\w-]+/)+[\w-]+-(?P<id>[\w]+)'
_TESTS = [{
'url': 'https://www.alsace20.tv/VOD/Actu/JT/Votre-JT-jeudi-3-fevrier-lyNHCXpYJh.html',
# 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
'info_dict': {
'id': 'lyNHCXpYJh',
'ext': 'mp4',
'description': 'md5:fc0bc4a0692d3d2dba4524053de4c7b7',
'title': 'Votre JT du jeudi 3 février',
'upload_date': '20220203',
'thumbnail': r're:https?://.+\.jpg',
'duration': 1073,
'view_count': int,
},
'params': {
'format': 'bestvideo',
},
}]
def _extract_video(self, video_id, url=None):
info = self._download_json(
'https://www.alsace20.tv/visionneuse/visio_v9_js.php?key=%s&habillage=0&mode=html' % (video_id, ),
video_id) or {}
title = info['titre']
formats = []
for res, fmt_url in (info.get('files') or {}).items():
formats.extend(
self._extract_smil_formats(fmt_url, video_id, fatal=False)
if '/smil:_' in fmt_url
else self._extract_mpd_formats(fmt_url, video_id, mpd_id=res, fatal=False))
self._sort_formats(formats)
webpage = (url and self._download_webpage(url, video_id, fatal=False)) or ''
thumbnail = url_or_none(dict_get(info, ('image', 'preview', )) or self._og_search_thumbnail(webpage))
upload_date = self._search_regex(r'/(\d{6})_', thumbnail, 'upload_date', default=None)
upload_date = unified_strdate('20%s-%s-%s' % (upload_date[:2], upload_date[2:4], upload_date[4:])) if upload_date else None
return {
'id': video_id,
'title': title,
'formats': formats,
'description': clean_html(get_element_by_class('wysiwyg', webpage)),
'upload_date': upload_date,
'thumbnail': thumbnail,
'duration': int_or_none(self._og_search_property('video:duration', webpage) if webpage else None),
'view_count': int_or_none(info.get('nb_vues')),
}
def _real_extract(self, url):
video_id = self._match_id(url)
return self._extract_video(video_id, url)
class Alsace20TVEmbedIE(Alsace20TVIE):
_VALID_URL = r'https?://(?:www\.)?alsace20\.tv/emb/(?P<id>[\w]+)'
_TESTS = [{
'url': 'https://www.alsace20.tv/emb/lyNHCXpYJh',
# 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
'info_dict': {
'id': 'lyNHCXpYJh',
'ext': 'mp4',
'title': 'Votre JT du jeudi 3 février',
'upload_date': '20220203',
'thumbnail': r're:https?://.+\.jpg',
'view_count': int,
},
'params': {
'format': 'bestvideo',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
return self._extract_video(video_id)

115
youtube_dl/extractor/americastestkitchen.py
View File

@@ -15,7 +15,7 @@ from ..utils import (
class AmericasTestKitchenIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?P<resource_type>episode|videos)/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?:cooks(?:country|illustrated)/)?(?P<resource_type>episode|videos)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
'md5': 'b861c3e365ac38ad319cfd509c30577f',
@@ -23,15 +23,20 @@ class AmericasTestKitchenIE(InfoExtractor):
'id': '5b400b9ee338f922cb06450c',
'title': 'Japanese Suppers',
'ext': 'mp4',
'display_id': 'weeknight-japanese-suppers',
'description': 'md5:64e606bfee910627efc4b5f050de92b3',
'thumbnail': r're:^https?://',
'timestamp': 1523318400,
'upload_date': '20180410',
'release_date': '20180410',
'timestamp': 1523304000,
'upload_date': '20180409',
'release_date': '20180409',
'series': "America's Test Kitchen",
'season': 'Season 18',
'season_number': 18,
'episode': 'Japanese Suppers',
'episode_number': 15,
'duration': 1376,
'thumbnail': r're:^https?://',
'average_rating': 0,
'view_count': int,
},
'params': {
'skip_download': True,
@@ -44,15 +49,20 @@ class AmericasTestKitchenIE(InfoExtractor):
'id': '5fbe8c61bda2010001c6763b',
'title': 'Simple Chicken Dinner',
'ext': 'mp4',
'display_id': 'atktv_2103_simple-chicken-dinner_full-episode_web-mp4',
'description': 'md5:eb68737cc2fd4c26ca7db30139d109e7',
'thumbnail': r're:^https?://',
'timestamp': 1610755200,
'upload_date': '20210116',
'release_date': '20210116',
'timestamp': 1610737200,
'upload_date': '20210115',
'release_date': '20210115',
'series': "America's Test Kitchen",
'season': 'Season 21',
'season_number': 21,
'episode': 'Simple Chicken Dinner',
'episode_number': 3,
'duration': 1397,
'thumbnail': r're:^https?://',
'view_count': int,
'average_rating': 0,
},
'params': {
'skip_download': True,
@@ -60,6 +70,12 @@ class AmericasTestKitchenIE(InfoExtractor):
}, {
'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
'only_matching': True,
}, {
'url': 'https://www.americastestkitchen.com/cookscountry/episode/564-when-only-chocolate-will-do',
'only_matching': True,
}, {
'url': 'https://www.americastestkitchen.com/cooksillustrated/videos/4478-beef-wellington',
'only_matching': True,
}, {
'url': 'https://www.cookscountry.com/episode/564-when-only-chocolate-will-do',
'only_matching': True,
@@ -94,7 +110,7 @@ class AmericasTestKitchenIE(InfoExtractor):
class AmericasTestKitchenSeasonIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|cookscountry)\.com/episodes/browse/season_(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|(?P<cooks>cooks(?:country|illustrated)))\.com(?:(?:/(?P<show2>cooks(?:country|illustrated)))?(?:/?$|(?<!ated)(?<!ated\.com)/episodes/browse/season_(?P<season>\d+)))'
_TESTS = [{
# ATK Season
'url': 'https://www.americastestkitchen.com/episodes/browse/season_1',
@@ -105,48 +121,93 @@ class AmericasTestKitchenSeasonIE(InfoExtractor):
'playlist_count': 13,
}, {
# Cooks Country Season
'url': 'https://www.cookscountry.com/episodes/browse/season_12',
'url': 'https://www.americastestkitchen.com/cookscountry/episodes/browse/season_12',
'info_dict': {
'id': 'season_12',
'title': 'Season 12',
},
'playlist_count': 13,
}, {
# America's Test Kitchen Series
'url': 'https://www.americastestkitchen.com/',
'info_dict': {
'id': 'americastestkitchen',
'title': 'America\'s Test Kitchen',
},
'playlist_count': 558,
}, {
# Cooks Country Series
'url': 'https://www.americastestkitchen.com/cookscountry',
'info_dict': {
'id': 'cookscountry',
'title': 'Cook\'s Country',
},
'playlist_count': 199,
}, {
'url': 'https://www.americastestkitchen.com/cookscountry/',
'only_matching': True,
}, {
'url': 'https://www.cookscountry.com/episodes/browse/season_12',
'only_matching': True,
}, {
'url': 'https://www.cookscountry.com',
'only_matching': True,
}, {
'url': 'https://www.americastestkitchen.com/cooksillustrated/',
'only_matching': True,
}, {
'url': 'https://www.cooksillustrated.com',
'only_matching': True,
}]
def _real_extract(self, url):
show_name, season_number = re.match(self._VALID_URL, url).groups()
season_number = int(season_number)
match = re.match(self._VALID_URL, url).groupdict()
show = match.get('show2')
show_path = ('/' + show) if show else ''
show = show or match['show']
season_number = int_or_none(match.get('season'))
slug = 'atk' if show_name == 'americastestkitchen' else 'cco'
slug, title = {
'americastestkitchen': ('atk', 'America\'s Test Kitchen'),
'cookscountry': ('cco', 'Cook\'s Country'),
'cooksillustrated': ('cio', 'Cook\'s Illustrated'),
}[show]
season = 'Season %d' % season_number
facet_filters = [
'search_document_klass:episode',
'search_show_slug:' + slug,
]
if season_number:
playlist_id = 'season_%d' % season_number
playlist_title = 'Season %d' % season_number
facet_filters.append('search_season_list:' + playlist_title)
else:
playlist_id = show
playlist_title = title
season_search = self._download_json(
'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_%s_season_desc_production' % slug,
season, headers={
'Origin': 'https://www.%s.com' % show_name,
playlist_id, headers={
'Origin': 'https://www.americastestkitchen.com',
'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805',
'X-Algolia-Application-Id': 'Y1FNZXUI30',
}, query={
'facetFilters': json.dumps([
'search_season_list:' + season,
'search_document_klass:episode',
'search_show_slug:' + slug,
]),
'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title' % slug,
'facetFilters': json.dumps(facet_filters),
'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title,search_atk_episode_season' % slug,
'attributesToHighlight': '',
'hitsPerPage': 1000,
})
def entries():
for episode in (season_search.get('hits') or []):
search_url = episode.get('search_url')
search_url = episode.get('search_url') # always formatted like '/episode/123-title-of-episode'
if not search_url:
continue
yield {
'_type': 'url',
'url': 'https://www.%s.com%s' % (show_name, search_url),
'id': try_get(episode, lambda e: e['objectID'].split('_')[-1]),
'url': 'https://www.americastestkitchen.com%s%s' % (show_path, search_url),
'id': try_get(episode, lambda e: e['objectID'].rsplit('_', 1)[-1]),
'title': episode.get('title'),
'description': episode.get('description'),
'timestamp': unified_timestamp(episode.get('search_document_date')),
@@ -156,4 +217,4 @@ class AmericasTestKitchenSeasonIE(InfoExtractor):
}
return self.playlist_result(
entries(), 'season_%d' % season_number, season)
entries(), playlist_id, playlist_title)

55
youtube_dl/extractor/applepodcasts.py
View File

@@ -3,8 +3,11 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
clean_podcast_url,
get_element_by_class,
int_or_none,
parse_codecs,
parse_iso8601,
try_get,
)
@@ -14,16 +17,17 @@ class ApplePodcastsIE(InfoExtractor):
_VALID_URL = r'https?://podcasts\.apple\.com/(?:[^/]+/)?podcast(?:/[^/]+){1,2}.*?\bi=(?P<id>\d+)'
_TESTS = [{
'url': 'https://podcasts.apple.com/us/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
'md5': 'df02e6acb11c10e844946a39e7222b08',
'md5': '41dc31cd650143e530d9423b6b5a344f',
'info_dict': {
'id': '1000482637777',
'ext': 'mp3',
'title': '207 - Whitney Webb Returns',
'description': 'md5:13a73bade02d2e43737751e3987e1399',
'description': 'md5:75ef4316031df7b41ced4e7b987f79c6',
'upload_date': '20200705',
'timestamp': 1593921600,
'duration': 6425,
'timestamp': 1593932400,
'duration': 6454,
'series': 'The Tim Dillon Show',
'thumbnail': 're:.+[.](png|jpe?g|webp)',
}
}, {
'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
@@ -39,19 +43,40 @@ class ApplePodcastsIE(InfoExtractor):
def _real_extract(self, url):
episode_id = self._match_id(url)
webpage = self._download_webpage(url, episode_id)
ember_data = self._parse_json(self._search_regex(
r'id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
webpage, 'ember data'), episode_id)
ember_data = ember_data.get(episode_id) or ember_data
episode = ember_data['data']['attributes']
episode_data = {}
ember_data = {}
# new page type 2021-11
amp_data = self._parse_json(self._search_regex(
r'(?s)id="shoebox-media-api-cache-amp-podcasts"[^>]*>\s*({.+?})\s*<',
webpage, 'AMP data', default='{}'), episode_id, fatal=False) or {}
amp_data = try_get(amp_data,
lambda a: self._parse_json(
next(a[x] for x in iter(a) if episode_id in x),
episode_id),
dict) or {}
amp_data = amp_data.get('d') or []
episode_data = try_get(
amp_data,
lambda a: next(x for x in a
if x['type'] == 'podcast-episodes' and x['id'] == episode_id),
dict)
if not episode_data:
# try pre 2021-11 page type: TODO: consider deleting if no longer used
ember_data = self._parse_json(self._search_regex(
r'(?s)id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
webpage, 'ember data'), episode_id) or {}
ember_data = ember_data.get(episode_id) or ember_data
episode_data = try_get(ember_data, lambda x: x['data'], dict)
episode = episode_data['attributes']
description = episode.get('description') or {}
series = None
for inc in (ember_data.get('included') or []):
for inc in (amp_data or ember_data.get('included') or []):
if inc.get('type') == 'media/podcast':
series = try_get(inc, lambda x: x['attributes']['name'])
series = series or clean_html(get_element_by_class('podcast-header__identity', webpage))
return {
info = [{
'id': episode_id,
'title': episode['name'],
'url': clean_podcast_url(episode['assetUrl']),
@@ -59,4 +84,10 @@ class ApplePodcastsIE(InfoExtractor):
'timestamp': parse_iso8601(episode.get('releaseDateTime')),
'duration': int_or_none(episode.get('durationInMilliseconds'), 1000),
'series': series,
}
'thumbnail': self._og_search_thumbnail(webpage),
}]
self._sort_formats(info)
info = info[0]
codecs = parse_codecs(info.get('ext', 'mp3'))
info.update(codecs)
return info

15
youtube_dl/extractor/ard.py
View File

@@ -332,9 +332,24 @@ class ARDIE(InfoExtractor):
formats.append(f)
self._sort_formats(formats)
_SUB_FORMATS = (
('./dataTimedText', 'ttml'),
('./dataTimedTextNoOffset', 'ttml'),
('./dataTimedTextVtt', 'vtt'),
)
subtitles = {}
for subsel, subext in _SUB_FORMATS:
for node in video_node.findall(subsel):
subtitles.setdefault('de', []).append({
'url': node.attrib['url'],
'ext': subext,
})
return {
'id': xpath_text(video_node, './videoId', default=display_id),
'formats': formats,
'subtitles': subtitles,
'display_id': display_id,
'title': video_node.find('./title').text,
'duration': parse_duration(video_node.find('./duration').text),

2
youtube_dl/extractor/arte.py
View File

@@ -342,4 +342,4 @@ class ArteTVCategoryIE(ArteTVBaseIE):
return merge_dicts(
self.playlist_from_matches(items, playlist_id=playlist_id, playlist_title=title),
{'description': self._og_search_description(webpage, default=None)})
{'description': self._og_search_description(webpage, default=None)})

42
youtube_dl/extractor/audiomack.py
View File

@@ -14,7 +14,7 @@ from ..utils import (
class AudiomackIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/song/(?P<id>[\w/-]+)'
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/(?:song/|(?=.+/song/))(?P<id>[\w/-]+)'
IE_NAME = 'audiomack'
_TESTS = [
# hosted on audiomack
@@ -29,25 +29,27 @@ class AudiomackIE(InfoExtractor):
}
},
# audiomack wrapper around soundcloud song
# Needs new test URL.
{
'add_ie': ['Soundcloud'],
'url': 'http://www.audiomack.com/song/hip-hop-daily/black-mamba-freestyle',
'info_dict': {
'id': '258901379',
'ext': 'mp3',
'description': 'mamba day freestyle for the legend Kobe Bryant ',
'title': 'Black Mamba Freestyle [Prod. By Danny Wolf]',
'uploader': 'ILOVEMAKONNEN',
'upload_date': '20160414',
}
'only_matching': True,
# 'info_dict': {
# 'id': '258901379',
# 'ext': 'mp3',
# 'description': 'mamba day freestyle for the legend Kobe Bryant ',
# 'title': 'Black Mamba Freestyle [Prod. By Danny Wolf]',
# 'uploader': 'ILOVEMAKONNEN',
# 'upload_date': '20160414',
# }
},
]
def _real_extract(self, url):
# URLs end with [uploader name]/[uploader title]
# URLs end with [uploader name]/song/[uploader title]
# this title is whatever the user types in, and is rarely
# the proper song title. Real metadata is in the api response
album_url_tag = self._match_id(url)
album_url_tag = self._match_id(url).replace('/song/', '/')
# Request the extended version of the api for extra fields like artist and title
api_response = self._download_json(
@@ -73,13 +75,13 @@ class AudiomackIE(InfoExtractor):
class AudiomackAlbumIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/album/(?P<id>[\w/-]+)'
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/(?:album/|(?=.+/album/))(?P<id>[\w/-]+)'
IE_NAME = 'audiomack:album'
_TESTS = [
# Standard album playlist
{
'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape',
'playlist_count': 15,
'playlist_count': 11,
'info_dict':
{
'id': '812251',
@@ -95,24 +97,24 @@ class AudiomackAlbumIE(InfoExtractor):
},
'playlist': [{
'info_dict': {
'title': 'PPP (Pistol P Project) - 9. Heaven or Hell (CHIMACA) ft Zuse (prod by DJ FU)',
'id': '837577',
'title': 'PPP (Pistol P Project) - 10. 4 Minutes Of Hell Part 4 (prod by DY OF 808 MAFIA)',
'id': '837580',
'ext': 'mp3',
'uploader': 'Lil Herb a.k.a. G Herbo',
}
}],
'params': {
'playliststart': 9,
'playlistend': 9,
'playliststart': 2,
'playlistend': 2,
}
}
]
def _real_extract(self, url):
# URLs end with [uploader name]/[uploader title]
# URLs end with [uploader name]/album/[uploader title]
# this title is whatever the user types in, and is rarely
# the proper song title. Real metadata is in the api response
album_url_tag = self._match_id(url)
album_url_tag = self._match_id(url).replace('/album/', '/')
result = {'_type': 'playlist', 'entries': []}
# There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata
# Therefore we don't know how many songs the album has and must infi-loop until failure
@@ -134,7 +136,7 @@ class AudiomackAlbumIE(InfoExtractor):
# Pull out the album metadata and add to result (if it exists)
for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]:
if apikey in api_response and resultkey not in result:
result[resultkey] = api_response[apikey]
result[resultkey] = compat_str(api_response[apikey])
song_id = url_basename(api_response['url']).rpartition('.')[0]
result['entries'].append({
'id': compat_str(api_response.get('id', song_id)),

57
youtube_dl/extractor/bbc.py
View File

@@ -12,6 +12,7 @@ from ..compat import (
compat_HTTPError,
compat_parse_qs,
compat_str,
compat_urllib_error,
compat_urllib_parse_urlparse,
compat_urlparse,
)
@@ -39,7 +40,7 @@ from ..utils import (
class BBCCoUkIE(InfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
_ID_REGEX = r'(?:[pbm][\da-z]{7}|w[\da-z]{7,14})'
_ID_REGEX = r'(?:[pbml][\da-z]{7}|w[\da-z]{7,14})'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?bbc\.co\.uk/
@@ -395,9 +396,17 @@ class BBCCoUkIE(InfoExtractor):
formats.extend(self._extract_mpd_formats(
href, programme_id, mpd_id=format_id, fatal=False))
elif transfer_format == 'hls':
formats.extend(self._extract_m3u8_formats(
href, programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False))
# TODO: let expected_status be passed into _extract_xxx_formats() instead
try:
fmts = self._extract_m3u8_formats(
href, programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False)
except ExtractorError as e:
if not (isinstance(e.exc_info[1], compat_urllib_error.HTTPError)
and e.exc_info[1].code in (403, 404)):
raise
fmts = []
formats.extend(fmts)
elif transfer_format == 'hds':
formats.extend(self._extract_f4m_formats(
href, programme_id, f4m_id=format_id, fatal=False))
@@ -775,21 +784,33 @@ class BBCIE(BBCCoUkIE):
'timestamp': 1437785037,
'upload_date': '20150725',
},
}, {
# video with window.__INITIAL_DATA__ and value as JSON string
'url': 'https://www.bbc.com/news/av/world-europe-59468682',
'info_dict': {
'id': 'p0b71qth',
'ext': 'mp4',
'title': 'Why France is making this woman a national hero',
'description': 'md5:7affdfab80e9c3a1f976230a1ff4d5e4',
'thumbnail': r're:https?://.+/.+\.jpg',
'timestamp': 1638230731,
'upload_date': '20211130',
},
}, {
# single video article embedded with data-media-vpid
'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
'only_matching': True,
}, {
# bbcthreeConfig
'url': 'https://www.bbc.co.uk/bbcthree/clip/73d0bbd0-abc3-4cea-b3c0-cdae21905eb1',
'info_dict': {
'id': 'p06556y7',
'ext': 'mp4',
'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
'description': 'md5:4b7dfd063d5a789a1512e99662be3ddd',
'title': 'Things Not To Say to people that live on council estates',
'description': "From being labelled a 'chav', to the presumption that they're 'scroungers', people who live on council estates encounter all kinds of prejudices and false assumptions about themselves, their families, and their lifestyles. Here, eight people discuss the common statements, misconceptions, and clichés that they're tired of hearing.",
'duration': 360,
'thumbnail': r're:https?://.+/.+\.jpg',
},
'params': {
'skip_download': True,
}
}, {
# window.__PRELOADED_STATE__
'url': 'https://www.bbc.co.uk/radio/play/b0b9z4yl',
@@ -1162,9 +1183,16 @@ class BBCIE(BBCCoUkIE):
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
initial_data = self._parse_json(self._search_regex(
r'window\.__INITIAL_DATA__\s*=\s*({.+?});', webpage,
'preload state', default='{}'), playlist_id, fatal=False)
initial_data = self._search_regex(
r'window\.__INITIAL_DATA__\s*=\s*("{.+?}")\s*;', webpage,
'quoted preload state', default=None)
if initial_data is None:
initial_data = self._search_regex(
r'window\.__INITIAL_DATA__\s*=\s*({.+?})\s*;', webpage,
'preload state', default={})
else:
initial_data = self._parse_json(initial_data or '"{}"', playlist_id, fatal=False)
initial_data = self._parse_json(initial_data, playlist_id, fatal=False)
if initial_data:
def parse_media(media):
if not media:
@@ -1205,7 +1233,10 @@ class BBCIE(BBCCoUkIE):
if name == 'media-experience':
parse_media(try_get(resp, lambda x: x['data']['initialItem']['mediaItem'], dict))
elif name == 'article':
for block in (try_get(resp, lambda x: x['data']['blocks'], list) or []):
for block in (try_get(resp,
(lambda x: x['data']['blocks'],
lambda x: x['data']['content']['model']['blocks'],),
list) or []):
if block.get('type') != 'media':
continue
parse_media(block.get('model'))

59
youtube_dl/extractor/bigo.py Normal file
View File

@@ -0,0 +1,59 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import ExtractorError, urlencode_postdata
class BigoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bigo\.tv/(?:[a-z]{2,}/)?(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://www.bigo.tv/ja/221338632',
'info_dict': {
'id': '6576287577575737440',
'title': '土よ〜💁‍♂️ 休憩室/REST room',
'thumbnail': r're:https?://.+',
'uploader': '✨Shin💫',
'uploader_id': '221338632',
'is_live': True,
},
'skip': 'livestream',
}, {
'url': 'https://www.bigo.tv/th/Tarlerm1304',
'only_matching': True,
}, {
'url': 'https://bigo.tv/115976881',
'only_matching': True,
}]
def _real_extract(self, url):
user_id = self._match_id(url)
info_raw = self._download_json(
'https://bigo.tv/studio/getInternalStudioInfo',
user_id, data=urlencode_postdata({'siteId': user_id}))
if not isinstance(info_raw, dict):
raise ExtractorError('Received invalid JSON data')
if info_raw.get('code'):
raise ExtractorError(
'Bigo says: %s (code %s)' % (info_raw.get('msg'), info_raw.get('code')), expected=True)
info = info_raw.get('data') or {}
if not info.get('alive'):
raise ExtractorError('This user is offline.', expected=True)
return {
'id': info.get('roomId') or user_id,
'title': info.get('roomTopic') or info.get('nick_name') or user_id,
'formats': [{
'url': info.get('hls_src'),
'ext': 'mp4',
'protocol': 'm3u8',
}],
'thumbnail': info.get('snapshot'),
'uploader': info.get('nick_name'),
'uploader_id': user_id,
'is_live': True,
}

5
youtube_dl/extractor/bilibili.py
View File

@@ -369,6 +369,11 @@ class BilibiliAudioIE(BilibiliAudioBaseIE):
'filesize': int_or_none(play_data.get('size')),
}]
for a_format in formats:
a_format.setdefault('http_headers', {}).update({
'Referer': url,
})
song = self._call_api('song/info', au_id)
title = song['title']
statistic = song.get('statistic') or {}

173
youtube_dl/extractor/blerp.py Normal file
View File

@@ -0,0 +1,173 @@
# coding: utf-8
from __future__ import unicode_literals
import json
from ..utils import (
strip_or_none,
traverse_obj,
)
from .common import InfoExtractor
class BlerpIE(InfoExtractor):
IE_NAME = 'blerp'
_VALID_URL = r'https?://(?:www\.)?blerp\.com/soundbites/(?P<id>[0-9a-zA-Z]+)'
_TESTS = [{
'url': 'https://blerp.com/soundbites/6320fe8745636cb4dd677a5a',
'info_dict': {
'id': '6320fe8745636cb4dd677a5a',
'title': 'Samsung Galaxy S8 Over the Horizon Ringtone 2016',
'uploader': 'luminousaj',
'uploader_id': '5fb81e51aa66ae000c395478',
'ext': 'mp3',
'tags': ['samsung', 'galaxy', 's8', 'over the horizon', '2016', 'ringtone'],
}
}, {
'url': 'https://blerp.com/soundbites/5bc94ef4796001000498429f',
'info_dict': {
'id': '5bc94ef4796001000498429f',
'title': 'Yee',
'uploader': '179617322678353920',
'uploader_id': '5ba99cf71386730004552c42',
'ext': 'mp3',
'tags': ['YEE', 'YEET', 'wo ha haah catchy tune yee', 'yee']
}
}]
_GRAPHQL_OPERATIONNAME = "webBitePageGetBite"
_GRAPHQL_QUERY = (
'''query webBitePageGetBite($_id: MongoID!) {
web {
biteById(_id: $_id) {
...bitePageFrag
__typename
}
__typename
}
}
fragment bitePageFrag on Bite {
_id
title
userKeywords
keywords
color
visibility
isPremium
owned
price
extraReview
isAudioExists
image {
filename
original {
url
__typename
}
__typename
}
userReactions {
_id
reactions
createdAt
__typename
}
topReactions
totalSaveCount
saved
blerpLibraryType
license
licenseMetaData
playCount
totalShareCount
totalFavoriteCount
totalAddedToBoardCount
userCategory
userAudioQuality
audioCreationState
transcription
userTranscription
description
createdAt
updatedAt
author
listingType
ownerObject {
_id
username
profileImage {
filename
original {
url
__typename
}
__typename
}
__typename
}
transcription
favorited
visibility
isCurated
sourceUrl
audienceRating
strictAudienceRating
ownerId
reportObject {
reportedContentStatus
__typename
}
giphy {
mp4
gif
__typename
}
audio {
filename
original {
url
__typename
}
mp3 {
url
__typename
}
__typename
}
__typename
}
''')
def _real_extract(self, url):
audio_id = self._match_id(url)
data = {
'operationName': self._GRAPHQL_OPERATIONNAME,
'query': self._GRAPHQL_QUERY,
'variables': {
'_id': audio_id
}
}
headers = {
'Content-Type': 'application/json'
}
json_result = self._download_json('https://api.blerp.com/graphql',
audio_id, data=json.dumps(data).encode('utf-8'), headers=headers)
bite_json = json_result['data']['web']['biteById']
info_dict = {
'id': bite_json['_id'],
'url': bite_json['audio']['mp3']['url'],
'title': bite_json['title'],
'uploader': traverse_obj(bite_json, ('ownerObject', 'username'), expected_type=strip_or_none),
'uploader_id': traverse_obj(bite_json, ('ownerObject', '_id'), expected_type=strip_or_none),
'ext': 'mp3',
'tags': list(filter(None, map(strip_or_none, (traverse_obj(bite_json, 'userKeywords', expected_type=list) or []))) or None)
}
return info_dict

18
youtube_dl/extractor/bongacams.py
View File

@@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import re
@@ -12,13 +13,28 @@ from ..utils import (
class BongaCamsIE(InfoExtractor):
_VALID_URL = r'https?://(?P<host>(?:[^/]+\.)?bongacams\d*\.com)/(?P<id>[^/?&#]+)'
_VALID_URL = r'https?://(?P<host>(?:[^/]+\.)?bongacams\d*\.(?:com|net))/(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://de.bongacams.com/azumi-8',
'only_matching': True,
}, {
'url': 'https://cn.bongacams.com/azumi-8',
'only_matching': True,
}, {
'url': 'https://de.bongacams.net/claireashton',
'info_dict': {
'id': 'claireashton',
'ext': 'mp4',
'title': r're:ClaireAshton \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
'age_limit': 18,
'uploader_id': 'ClaireAshton',
'uploader': 'ClaireAshton',
'like_count': int,
'is_live': True,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):

74
youtube_dl/extractor/callin.py Normal file
View File

@@ -0,0 +1,74 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
traverse_obj,
try_get,
)
class CallinIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?callin\.com/episode/(?:[^/#?-]+-)*(?P<id>[^/#?-]+)'
_TESTS = [{
'url': 'https://www.callin.com/episode/fcc-commissioner-brendan-carr-on-elons-PrumRdSQJW',
'md5': '14ede27ee2c957b7e4db93140fc0745c',
'info_dict': {
'id': 'PrumRdSQJW',
'ext': 'mp4',
'title': 'FCC Commissioner Brendan Carr on Elon’s Starlink',
'description': 'Or, why the government doesn’t like SpaceX',
'channel': 'The Pull Request',
'channel_url': 'https://callin.com/show/the-pull-request-ucnDJmEKAa',
}
}, {
'url': 'https://www.callin.com/episode/episode-81-elites-melt-down-over-student-debt-lzxMidUnjA',
'md5': '16f704ddbf82a27e3930533b12062f07',
'info_dict': {
'id': 'lzxMidUnjA',
'ext': 'mp4',
'title': 'Episode 81- Elites MELT DOWN over Student Debt Victory? Rumble in NYC?',
'description': 'Let’s talk todays episode about the primary election shake up in NYC and the elites melting down over student debt cancelation.',
'channel': 'The DEBRIEF With Briahna Joy Gray',
'channel_url': 'https://callin.com/show/the-debrief-with-briahna-joy-gray-siiFDzGegm',
}
}]
def _search_nextjs_data(self, webpage, video_id, transform_source=None, fatal=True, **kw):
return self._parse_json(
self._search_regex(
r'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>',
webpage, 'next.js data', fatal=fatal, **kw),
video_id, transform_source=transform_source, fatal=fatal)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
next_data = self._search_nextjs_data(webpage, video_id)
episode = traverse_obj(next_data, ('props', 'pageProps', 'episode'), expected_type=dict)
if not episode:
raise ExtractorError('Failed to find episode data')
title = episode.get('title') or self._og_search_title(webpage)
description = episode.get('description') or self._og_search_description(webpage)
formats = []
formats.extend(self._extract_m3u8_formats(
episode.get('m3u8'), video_id, 'mp4',
entry_protocol='m3u8_native', fatal=False))
self._sort_formats(formats)
channel = try_get(episode, lambda x: x['show']['title'], compat_str)
channel_url = try_get(episode, lambda x: x['show']['linkObj']['resourceUrl'], compat_str)
return {
'id': video_id,
'title': title,
'description': description,
'formats': formats,
'channel': channel,
'channel_url': channel_url,
}

34
youtube_dl/extractor/cammodels.py
View File

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
url_or_none,
)
@@ -20,32 +19,11 @@ class CamModelsIE(InfoExtractor):
def _real_extract(self, url):
user_id = self._match_id(url)
webpage = self._download_webpage(
url, user_id, headers=self.geo_verification_headers())
manifest_root = self._html_search_regex(
r'manifestUrlRoot=([^&\']+)', webpage, 'manifest', default=None)
if not manifest_root:
ERRORS = (
("I'm offline, but let's stay connected", 'This user is currently offline'),
('in a private show', 'This user is in a private show'),
('is currently performing LIVE', 'This model is currently performing live'),
)
for pattern, message in ERRORS:
if pattern in webpage:
error = message
expected = True
break
else:
error = 'Unable to find manifest URL root'
expected = False
raise ExtractorError(error, expected=expected)
manifest = self._download_json(
'%s%s.json' % (manifest_root, user_id), user_id)
'https://manifest-server.naiadsystems.com/live/s:%s.json' % user_id, user_id)
formats = []
thumbnails = []
for format_id, format_dict in manifest['formats'].items():
if not isinstance(format_dict, dict):
continue
@@ -85,6 +63,13 @@ class CamModelsIE(InfoExtractor):
'preference': -1,
})
else:
if format_id == 'jpeg':
thumbnails.append({
'url': f['url'],
'width': f['width'],
'height': f['height'],
'format_id': f['format_id'],
})
continue
formats.append(f)
self._sort_formats(formats)
@@ -92,6 +77,7 @@ class CamModelsIE(InfoExtractor):
return {
'id': user_id,
'title': self._live_title(user_id),
'thumbnails': thumbnails,
'is_live': True,
'formats': formats,
'age_limit': 18

178
youtube_dl/extractor/ceskatelevize.py
View File

@@ -12,35 +12,21 @@ from ..utils import (
ExtractorError,
float_or_none,
sanitized_Request,
unescapeHTML,
update_url_query,
str_or_none,
traverse_obj,
urlencode_postdata,
USER_AGENTS,
)
class CeskaTelevizeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/ivysilani/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(?:ivysilani|porady|zive)/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
_TESTS = [{
'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
'info_dict': {
'id': '61924494877246241',
'ext': 'mp4',
'title': 'Hyde Park Civilizace: Život v Grónsku',
'description': 'md5:3fec8f6bb497be5cdb0c9e8781076626',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 3350,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.ceskatelevize.cz/ivysilani/10441294653-hyde-park-civilizace/215411058090502/bonus/20641-bonus-01-en',
'info_dict': {
'id': '61924494877028507',
'ext': 'mp4',
'title': 'Hyde Park Civilizace: Bonus 01 - En',
'title': 'Bonus 01 - En - Hyde Park Civilizace',
'description': 'English Subtittles',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 81.3,
@@ -51,31 +37,111 @@ class CeskaTelevizeIE(InfoExtractor):
},
}, {
# live stream
'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
'url': 'http://www.ceskatelevize.cz/zive/ct1/',
'info_dict': {
'id': 402,
'id': '102',
'ext': 'mp4',
'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'title': r'ČT1 - živé vysílání online',
'description': 'Sledujte živé vysílání kanálu ČT1 online. Vybírat si můžete i z dalších kanálů České televize na kterémkoli z vašich zařízení.',
'is_live': True,
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'Georestricted to Czech Republic',
}, {
# another
'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
'only_matching': True,
'info_dict': {
'id': 402,
'ext': 'mp4',
'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'is_live': True,
},
# 'skip': 'Georestricted to Czech Republic',
}, {
'url': 'http://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php?hash=d6a3e1370d2e4fa76296b90bad4dfc19673b641e&IDEC=217 562 22150/0004&channelID=1&width=100%25',
'only_matching': True,
}, {
# video with 18+ caution trailer
'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
'info_dict': {
'id': '215562210900007-bogotart',
'title': 'Bogotart - Queer',
'description': 'Hlavní město Kolumbie v doprovodu queer umělců. Vroucí svět plný vášně, sebevědomí, ale i násilí a bolesti',
},
'playlist': [{
'info_dict': {
'id': '61924494877311053',
'ext': 'mp4',
'title': 'Bogotart - Queer (Varování 18+)',
'duration': 11.9,
},
}, {
'info_dict': {
'id': '61924494877068022',
'ext': 'mp4',
'title': 'Bogotart - Queer (Queer)',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 1558.3,
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
}, {
# iframe embed
'url': 'http://www.ceskatelevize.cz/porady/10614999031-neviditelni/21251212048/',
'only_matching': True,
}]
def _search_nextjs_data(self, webpage, video_id, **kw):
return self._parse_json(
self._search_regex(
r'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>',
webpage, 'next.js data', **kw),
video_id, **kw)
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(url, playlist_id)
parsed_url = compat_urllib_parse_urlparse(urlh.geturl())
site_name = self._og_search_property('site_name', webpage, fatal=False, default='Česká televize')
playlist_title = self._og_search_title(webpage, default=None)
if site_name and playlist_title:
playlist_title = re.split(r'\s*[—|]\s*%s' % (site_name, ), playlist_title, 1)[0]
playlist_description = self._og_search_description(webpage, default=None)
if playlist_description:
playlist_description = playlist_description.replace('\xa0', ' ')
webpage = self._download_webpage(url, playlist_id)
type_ = 'IDEC'
if re.search(r'(^/porady|/zive)/', parsed_url.path):
next_data = self._search_nextjs_data(webpage, playlist_id)
if '/zive/' in parsed_url.path:
idec = traverse_obj(next_data, ('props', 'pageProps', 'data', 'liveBroadcast', 'current', 'idec'), get_all=False)
else:
idec = traverse_obj(next_data, ('props', 'pageProps', 'data', ('show', 'mediaMeta'), 'idec'), get_all=False)
if not idec:
idec = traverse_obj(next_data, ('props', 'pageProps', 'data', 'videobonusDetail', 'bonusId'), get_all=False)
if idec:
type_ = 'bonus'
if not idec:
raise ExtractorError('Failed to find IDEC id')
iframe_hash = self._download_webpage(
'https://www.ceskatelevize.cz/v-api/iframe-hash/',
playlist_id, note='Getting IFRAME hash')
query = {'hash': iframe_hash, 'origin': 'iVysilani', 'autoStart': 'true', type_: idec, }
webpage = self._download_webpage(
'https://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php',
playlist_id, note='Downloading player', query=query)
NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
self.raise_geo_restricted(NOT_AVAILABLE_STRING)
if any(not_found in webpage for not_found in ('Neplatný parametr pro videopřehrávač', 'IDEC nebyl nalezen', )):
raise ExtractorError('no video with IDEC available', video_id=idec, expected=True)
type_ = None
episode_id = None
@@ -100,7 +166,7 @@ class CeskaTelevizeIE(InfoExtractor):
data = {
'playlist[0][type]': type_,
'playlist[0][id]': episode_id,
'requestUrl': compat_urllib_parse_urlparse(url).path,
'requestUrl': parsed_url.path,
'requestSource': 'iVysilani',
}
@@ -108,7 +174,7 @@ class CeskaTelevizeIE(InfoExtractor):
for user_agent in (None, USER_AGENTS['Safari']):
req = sanitized_Request(
'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist/',
data=urlencode_postdata(data))
req.add_header('Content-type', 'application/x-www-form-urlencoded')
@@ -130,9 +196,6 @@ class CeskaTelevizeIE(InfoExtractor):
req = sanitized_Request(compat_urllib_parse_unquote(playlist_url))
req.add_header('Referer', url)
playlist_title = self._og_search_title(webpage, default=None)
playlist_description = self._og_search_description(webpage, default=None)
playlist = self._download_json(req, playlist_id, fatal=False)
if not playlist:
continue
@@ -167,7 +230,7 @@ class CeskaTelevizeIE(InfoExtractor):
entries[num]['formats'].extend(formats)
continue
item_id = item.get('id') or item['assetId']
item_id = str_or_none(item.get('id') or item['assetId'])
title = item['title']
duration = float_or_none(item.get('duration'))
@@ -181,8 +244,6 @@ class CeskaTelevizeIE(InfoExtractor):
if playlist_len == 1:
final_title = playlist_title or title
if is_live:
final_title = self._live_title(final_title)
else:
final_title = '%s (%s)' % (playlist_title, title)
@@ -200,6 +261,8 @@ class CeskaTelevizeIE(InfoExtractor):
for e in entries:
self._sort_formats(e['formats'])
if len(entries) == 1:
return entries[0]
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
def _get_subtitles(self, episode_id, subs):
@@ -236,54 +299,3 @@ class CeskaTelevizeIE(InfoExtractor):
yield line
return '\r\n'.join(_fix_subtitle(subtitles))
class CeskaTelevizePoradyIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/porady/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
_TESTS = [{
# video with 18+ caution trailer
'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
'info_dict': {
'id': '215562210900007-bogotart',
'title': 'Queer: Bogotart',
'description': 'Alternativní průvodce současným queer světem',
},
'playlist': [{
'info_dict': {
'id': '61924494876844842',
'ext': 'mp4',
'title': 'Queer: Bogotart (Varování 18+)',
'duration': 10.2,
},
}, {
'info_dict': {
'id': '61924494877068022',
'ext': 'mp4',
'title': 'Queer: Bogotart (Queer)',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 1558.3,
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
}, {
# iframe embed
'url': 'http://www.ceskatelevize.cz/porady/10614999031-neviditelni/21251212048/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data_url = update_url_query(unescapeHTML(self._search_regex(
(r'<span[^>]*\bdata-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?ceskatelevize\.cz/ivysilani/embed/iFramePlayer\.php.*?)\1'),
webpage, 'iframe player url', group='url')), query={
'autoStart': 'true',
})
return self.url_result(data_url, ie=CeskaTelevizeIE.ie_key())

44
youtube_dl/extractor/common.py
View File

@@ -70,6 +70,7 @@ from ..utils import (
str_or_none,
str_to_int,
strip_or_none,
try_get,
unescapeHTML,
unified_strdate,
unified_timestamp,
@@ -1086,7 +1087,7 @@ class InfoExtractor(object):
# Helper functions for extracting OpenGraph info
@staticmethod
def _og_regexes(prop):
content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?))'
content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?)(?=\s|/?>))'
property_re = (r'(?:name|property)=(?:\'og[:-]%(prop)s\'|"og[:-]%(prop)s"|\s*og[:-]%(prop)s\b)'
% {'prop': re.escape(prop)})
template = r'<meta[^>]+?%s[^>]+?%s'
@@ -2713,7 +2714,7 @@ class InfoExtractor(object):
def _find_jwplayer_data(self, webpage, video_id=None, transform_source=js_to_json):
mobj = re.search(
r'(?s)jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)(?!</script>).*?\.setup\s*\((?P<options>[^)]+)\)',
r'''(?s)jwplayer\s*\(\s*(?P<q>'|")(?!(?P=q)).+(?P=q)\s*\)(?!</script>).*?\.\s*setup\s*\(\s*(?P<options>(?:\([^)]*\)|[^)])+)\s*\)''',
webpage)
if mobj:
try:
@@ -2734,9 +2735,14 @@ class InfoExtractor(object):
def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True,
m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
flat_pl = try_get(jwplayer_data, lambda x: x.get('playlist') or True)
if flat_pl is None:
# not even a dict
return []
# JWPlayer backward compatibility: flattened playlists
# https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96
if 'playlist' not in jwplayer_data:
if flat_pl is True:
jwplayer_data = {'playlist': [jwplayer_data]}
entries = []
@@ -2784,6 +2790,13 @@ class InfoExtractor(object):
'timestamp': int_or_none(video_data.get('pubdate')),
'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')),
'subtitles': subtitles,
'alt_title': clean_html(video_data.get('subtitle')), # attributes used e.g. by Tele5 ...
'genre': clean_html(video_data.get('genre')),
'channel': clean_html(dict_get(video_data, ('category', 'channel'))),
'season_number': int_or_none(video_data.get('season')),
'episode_number': int_or_none(video_data.get('episode')),
'release_year': int_or_none(video_data.get('releasedate')),
'age_limit': int_or_none(video_data.get('age_restriction')),
}
# https://github.com/jwplayer/jwplayer/blob/master/src/js/utils/validator.js#L32
if len(formats) == 1 and re.search(r'^(?:http|//).*(?:youtube\.com|youtu\.be)/.+', formats[0]['url']):
@@ -2792,7 +2805,9 @@ class InfoExtractor(object):
'url': formats[0]['url'],
})
else:
self._sort_formats(formats)
# avoid exception in case of only sttls
if formats:
self._sort_formats(formats)
entry['formats'] = formats
entries.append(entry)
if len(entries) == 1:
@@ -2802,7 +2817,7 @@ class InfoExtractor(object):
def _parse_jwplayer_formats(self, jwplayer_sources_data, video_id=None,
m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
urls = []
urls = set()
formats = []
for source in jwplayer_sources_data:
if not isinstance(source, dict):
@@ -2811,14 +2826,14 @@ class InfoExtractor(object):
base_url, self._proto_relative_url(source.get('file')))
if not source_url or source_url in urls:
continue
urls.append(source_url)
urls.add(source_url)
source_type = source.get('type') or ''
ext = mimetype2ext(source_type) or determine_ext(source_url)
if source_type == 'hls' or ext == 'm3u8':
if source_type == 'hls' or ext == 'm3u8' or 'format=m3u8-aapl' in source_url:
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=m3u8_id, fatal=False))
elif source_type == 'dash' or ext == 'mpd':
elif source_type == 'dash' or ext == 'mpd' or 'format=mpd-time-csf' in source_url:
formats.extend(self._extract_mpd_formats(
source_url, video_id, mpd_id=mpd_id, fatal=False))
elif ext == 'smil':
@@ -2833,20 +2848,23 @@ class InfoExtractor(object):
'ext': ext,
})
else:
format_id = str_or_none(source.get('label'))
height = int_or_none(source.get('height'))
if height is None:
if height is None and format_id:
# Often no height is provided but there is a label in
# format like "1080p", "720p SD", or 1080.
height = int_or_none(self._search_regex(
r'^(\d{3,4})[pP]?(?:\b|$)', compat_str(source.get('label') or ''),
'height', default=None))
height = parse_resolution(format_id).get('height')
a_format = {
'url': source_url,
'width': int_or_none(source.get('width')),
'height': height,
'tbr': int_or_none(source.get('bitrate')),
'tbr': int_or_none(source.get('bitrate'), scale=1000),
'filesize': int_or_none(source.get('filesize')),
'ext': ext,
}
if format_id:
a_format['format_id'] = format_id
if source_url.startswith('rtmp'):
a_format['ext'] = 'flv'
# See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as

148
youtube_dl/extractor/cpac.py Normal file
View File

@@ -0,0 +1,148 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
str_or_none,
try_get,
unified_timestamp,
update_url_query,
urljoin,
)
# compat_range
try:
if callable(xrange):
range = xrange
except (NameError, TypeError):
pass
class CPACIE(InfoExtractor):
IE_NAME = 'cpac'
_VALID_URL = r'https?://(?:www\.)?cpac\.ca/(?P<fr>l-)?episode\?id=(?P<id>[\da-f]{8}(?:-[\da-f]{4}){3}-[\da-f]{12})'
_TEST = {
# 'url': 'http://www.cpac.ca/en/programs/primetime-politics/episodes/65490909',
'url': 'https://www.cpac.ca/episode?id=fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
'md5': 'e46ad699caafd7aa6024279f2614e8fa',
'info_dict': {
'id': 'fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
'ext': 'mp4',
'upload_date': '20220215',
'title': 'News Conference to Celebrate National Kindness Week – February 15, 2022',
'description': 'md5:466a206abd21f3a6f776cdef290c23fb',
'timestamp': 1644901200,
},
'params': {
'format': 'bestvideo',
'hls_prefer_native': True,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
url_lang = 'fr' if '/l-episode?' in url else 'en'
content = self._download_json(
'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/episode/index.xml&crafterSite=cpacca&id=' + video_id,
video_id)
video_url = try_get(content, lambda x: x['page']['details']['videoUrl'], compat_str)
formats = []
if video_url:
content = content['page']
title = str_or_none(content['details']['title_%s_t' % (url_lang, )])
formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', ext='mp4')
for fmt in formats:
# prefer language to match URL
fmt_lang = fmt.get('language')
if fmt_lang == url_lang:
fmt['language_preference'] = 10
elif not fmt_lang:
fmt['language_preference'] = -1
else:
fmt['language_preference'] = -10
self._sort_formats(formats)
category = str_or_none(content['details']['category_%s_t' % (url_lang, )])
def is_live(v_type):
return (v_type == 'live') if v_type is not None else None
return {
'id': video_id,
'formats': formats,
'title': title,
'description': str_or_none(content['details'].get('description_%s_t' % (url_lang, ))),
'timestamp': unified_timestamp(content['details'].get('liveDateTime')),
'category': [category] if category else None,
'thumbnail': urljoin(url, str_or_none(content['details'].get('image_%s_s' % (url_lang, )))),
'is_live': is_live(content['details'].get('type')),
}
class CPACPlaylistIE(InfoExtractor):
IE_NAME = 'cpac:playlist'
_VALID_URL = r'(?i)https?://(?:www\.)?cpac\.ca/(?:program|search|(?P<fr>emission|rechercher))\?(?:[^&]+&)*?(?P<id>(?:id=\d+|programId=\d+|key=[^&]+))'
_TESTS = [{
'url': 'https://www.cpac.ca/program?id=6',
'info_dict': {
'id': 'id=6',
'title': 'Headline Politics',
'description': 'Watch CPAC’s signature long-form coverage of the day’s pressing political events as they unfold.',
},
'playlist_count': 10,
}, {
'url': 'https://www.cpac.ca/search?key=hudson&type=all&order=desc',
'info_dict': {
'id': 'key=hudson',
'title': 'hudson',
},
'playlist_count': 22,
}, {
'url': 'https://www.cpac.ca/search?programId=50',
'info_dict': {
'id': 'programId=50',
'title': '50',
},
'playlist_count': 9,
}, {
'url': 'https://www.cpac.ca/emission?id=6',
'only_matching': True,
}, {
'url': 'https://www.cpac.ca/rechercher?key=hudson&type=all&order=desc',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
url_lang = 'fr' if any(x in url for x in ('/emission?', '/rechercher?')) else 'en'
pl_type, list_type = ('program', 'itemList') if any(x in url for x in ('/program?', '/emission?')) else ('search', 'searchResult')
api_url = (
'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/%s/index.xml&crafterSite=cpacca&%s'
% (pl_type, video_id, ))
content = self._download_json(api_url, video_id)
entries = []
total_pages = int_or_none(try_get(content, lambda x: x['page'][list_type]['totalPages']), default=1)
for page in range(1, total_pages + 1):
if page > 1:
api_url = update_url_query(api_url, {'page': '%d' % (page, ), })
content = self._download_json(
api_url, video_id,
note='Downloading continuation - %d' % (page, ),
fatal=False)
for item in try_get(content, lambda x: x['page'][list_type]['item'], list) or []:
episode_url = urljoin(url, try_get(item, lambda x: x['url_%s_s' % (url_lang, )]))
if episode_url:
entries.append(episode_url)
return self.playlist_result(
(self.url_result(entry) for entry in entries),
playlist_id=video_id,
playlist_title=try_get(content, lambda x: x['page']['program']['title_%s_t' % (url_lang, )]) or video_id.split('=')[-1],
playlist_description=try_get(content, lambda x: x['page']['program']['description_%s_t' % (url_lang, )]),
)

52
youtube_dl/extractor/extractors.py
View File

@@ -51,6 +51,10 @@ from .anvato import AnvatoIE
from .aol import AolIE
from .allocine import AllocineIE
from .aliexpress import AliExpressLiveIE
from .alsace20tv import (
Alsace20TVIE,
Alsace20TVEmbedIE,
)
from .apa import APAIE
from .aparat import AparatIE
from .appleconnect import AppleConnectIE
@@ -71,6 +75,7 @@ from .arte import (
ArteTVIE,
ArteTVEmbedIE,
ArteTVPlaylistIE,
ArteTVCategoryIE,
)
from .arnes import ArnesIE
from .asiancrush import (
@@ -114,6 +119,7 @@ from .bfmtv import (
)
from .bibeltv import BibelTVIE
from .bigflix import BigflixIE
from .bigo import BigoIE
from .bild import BildIE
from .bilibili import (
BiliBiliIE,
@@ -132,6 +138,7 @@ from .bleacherreport import (
BleacherReportIE,
BleacherReportCMSIE,
)
from .blerp import BlerpIE
from .bloomberg import BloombergIE
from .bokecc import BokeCCIE
from .bongacams import BongaCamsIE
@@ -152,6 +159,7 @@ from .businessinsider import BusinessInsiderIE
from .buzzfeed import BuzzFeedIE
from .byutv import BYUtvIE
from .c56 import C56IE
from .callin import CallinIE
from .camdemy import (
CamdemyIE,
CamdemyFolderIE
@@ -202,10 +210,7 @@ from .ccc import (
from .ccma import CCMAIE
from .cctv import CCTVIE
from .cda import CDAIE
from .ceskatelevize import (
CeskaTelevizeIE,
CeskaTelevizePoradyIE,
)
from .ceskatelevize import CeskaTelevizeIE
from .channel9 import Channel9IE
from .charlierose import CharlieRoseIE
from .chaturbate import ChaturbateIE
@@ -253,6 +258,10 @@ from .commonprotocols import (
from .condenast import CondeNastIE
from .contv import CONtvIE
from .corus import CorusIE
from .cpac import (
CPACIE,
CPACPlaylistIE,
)
from .cracked import CrackedIE
from .crackle import CrackleIE
from .crooksandliars import CrooksAndLiarsIE
@@ -367,6 +376,8 @@ from .fc2 import (
FC2EmbedIE,
)
from .fczenit import FczenitIE
from .filemoon import FileMoonIE
from .fifa import FifaIE
from .filmon import (
FilmOnIE,
FilmOnChannelIE,
@@ -469,6 +480,7 @@ from .hotstar import (
)
from .howcast import HowcastIE
from .howstuffworks import HowStuffWorksIE
from .hrfernsehen import HRFernsehenIE
from .hrti import (
HRTiIE,
HRTiPlaylistIE,
@@ -545,8 +557,10 @@ from .khanacademy import (
from .kickstarter import KickStarterIE
from .kinja import KinjaEmbedIE
from .kinopoisk import KinoPoiskIE
from .kommunetv import KommunetvIE
from .konserthusetplay import KonserthusetPlayIE
from .krasview import KrasViewIE
from .kth import KTHIE
from .ku6 import Ku6IE
from .kusi import KUSIIE
from .kuwo import (
@@ -716,6 +730,7 @@ from .myvi import (
MyviIE,
MyviEmbedIE,
)
from .myvideoge import MyVideoGeIE
from .myvidster import MyVidsterIE
from .nationalgeographic import (
NationalGeographicVideoIE,
@@ -789,7 +804,14 @@ from .nick import (
NickNightIE,
NickRuIE,
)
from .niconico import NiconicoIE, NiconicoPlaylistIE
from .niconico import (
NiconicoIE,
NiconicoPlaylistIE,
NiconicoUserIE,
NicovideoSearchIE,
NicovideoSearchDateIE,
NicovideoSearchURLIE,
)
from .ninecninemedia import NineCNineMediaIE
from .ninegag import NineGagIE
from .ninenow import NineNowIE
@@ -893,6 +915,10 @@ from .parliamentliveuk import ParliamentLiveUKIE
from .patreon import PatreonIE
from .pbs import PBSIE
from .pearvideo import PearVideoIE
from .peekvids import (
PeekVidsIE,
PlayVidsIE,
)
from .peertube import PeerTubeIE
from .people import PeopleIE
from .performgroup import PerformGroupIE
@@ -986,6 +1012,10 @@ from .raywenderlich import (
RayWenderlichIE,
RayWenderlichCourseIE,
)
from .rbgtum import (
RbgTumIE,
RbgTumCourseIE,
)
from .rbmaradio import RBMARadioIE
from .rds import RDSIE
from .redbulltv import (
@@ -1176,6 +1206,7 @@ from .storyfire import (
from .streamable import StreamableIE
from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE
from .streamsb import StreamsbIE
from .streetvoice import StreetVoiceIE
from .stretchinternet import StretchInternetIE
from .stv import STVPlayerIE
@@ -1245,6 +1276,11 @@ from .theweatherchannel import TheWeatherChannelIE
from .thisamericanlife import ThisAmericanLifeIE
from .thisav import ThisAVIE
from .thisoldhouse import ThisOldHouseIE
from .thisvid import (
ThisVidIE,
ThisVidMemberIE,
ThisVidPlaylistIE,
)
from .threeqsdn import ThreeQSDNIE
from .tiktok import (
TikTokIE,
@@ -1606,7 +1642,7 @@ from .youtube import (
YoutubeRecommendedIE,
YoutubeSearchDateIE,
YoutubeSearchIE,
#YoutubeSearchURLIE,
YoutubeSearchURLIE,
YoutubeSubscriptionsIE,
YoutubeTruncatedIDIE,
YoutubeTruncatedURLIE,
@@ -1642,3 +1678,7 @@ from .zingmp3 import (
)
from .zoom import ZoomIE
from .zype import ZypeIE
from .pr0gramm import (
Pr0grammIE,
Pr0grammStaticIE,
)

101
youtube_dl/extractor/fifa.py Normal file
View File

@@ -0,0 +1,101 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
traverse_obj,
unified_timestamp,
)
if not callable(getattr(InfoExtractor, '_match_valid_url', None)):
BaseInfoExtractor = InfoExtractor
import re
class InfoExtractor(BaseInfoExtractor):
@classmethod
def _match_valid_url(cls, url):
return re.match(cls._VALID_URL, url)
class FifaIE(InfoExtractor):
_VALID_URL = r'https?://www.fifa.com/fifaplus/(?P<locale>\w{2})/watch/([^#?]+/)?(?P<id>\w+)'
_TESTS = [{
'url': 'https://www.fifa.com/fifaplus/en/watch/7on10qPcnyLajDDU3ntg6y',
'info_dict': {
'id': '7on10qPcnyLajDDU3ntg6y',
'title': 'Italy v France | Final | 2006 FIFA World Cup Germany™ | Full Match Replay',
'description': 'md5:f4520d0ee80529c8ba4134a7d692ff8b',
'ext': 'mp4',
'categories': ['FIFA Tournaments'],
'thumbnail': 'https://digitalhub.fifa.com/transform/135e2656-3a51-407b-8810-6c34bec5b59b/FMR_2006_Italy_France_Final_Hero',
'duration': 8165,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.fifa.com/fifaplus/pt/watch/1cg5r5Qt6Qt12ilkDgb1sV',
'info_dict': {
'id': '1cg5r5Qt6Qt12ilkDgb1sV',
'title': 'Brazil v Germany | Semi-finals | 2014 FIFA World Cup Brazil™ | Extended Highlights',
'description': 'md5:d908c74ee66322b804ae2e521b02a855',
'ext': 'mp4',
'categories': ['FIFA Tournaments', 'Highlights'],
'thumbnail': 'https://digitalhub.fifa.com/transform/d8fe6f61-276d-4a73-a7fe-6878a35fd082/FIFAPLS_100EXTHL_2014BRAvGER_TMB',
'duration': 902,
'release_timestamp': 1404777600,
'release_date': '20140708',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.fifa.com/fifaplus/fr/watch/3C6gQH9C2DLwzNx7BMRQdp',
'info_dict': {
'id': '3C6gQH9C2DLwzNx7BMRQdp',
'title': 'Josimar goal against Northern Ireland | Classic Goals',
'description': 'md5:cbe7e7bb52f603c9f1fe9a4780fe983b',
'ext': 'mp4',
'categories': ['FIFA Tournaments', 'Goal'],
'duration': 28,
'thumbnail': 'https://digitalhub.fifa.com/transform/f9301391-f8d9-48b5-823e-c093ac5e3e11/CG_MEN_1986_JOSIMAR',
},
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
video_id, locale = self._match_valid_url(url).group('id', 'locale')
webpage = self._download_webpage(url, video_id)
preconnect_link = self._search_regex(
r'<link\b[^>]+\brel\s*=\s*"preconnect"[^>]+href\s*=\s*"([^"]+)"', webpage, 'Preconnect Link')
video_details = self._download_json(
'{preconnect_link}/sections/videoDetails/{video_id}'.format(**locals()), video_id, 'Downloading Video Details', fatal=False)
preplay_parameters = self._download_json(
'{preconnect_link}/videoPlayerData/{video_id}'.format(**locals()), video_id, 'Downloading Preplay Parameters')['preplayParameters']
content_data = self._download_json(
# 1. query string is expected to be sent as-is
# 2. `sig` must be appended
# 3. if absent, the call appears to work but the manifest is bad (404)
'https://content.uplynk.com/preplay/{contentId}/multiple.json?{queryStr}&sig={signature}'.format(**preplay_parameters),
video_id, 'Downloading Content Data')
# formats, subtitles = self._extract_m3u8_formats_and_subtitles(content_data['playURL'], video_id)
formats, subtitles = self._extract_m3u8_formats(content_data['playURL'], video_id, ext='mp4', entry_protocol='m3u8_native'), None
self._sort_formats(formats)
return {
'id': video_id,
'title': video_details['title'],
'description': video_details.get('description'),
'duration': int_or_none(video_details.get('duration')),
'release_timestamp': unified_timestamp(video_details.get('dateOfRelease')),
'categories': traverse_obj(video_details, (('videoCategory', 'videoSubcategory'),)),
'thumbnail': traverse_obj(video_details, ('backgroundImage', 'src')),
'formats': formats,
'subtitles': subtitles,
}

43
youtube_dl/extractor/filemoon.py Normal file
View File

@@ -0,0 +1,43 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
decode_packed_codes,
js_to_json,
)
class FileMoonIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?filemoon\.sx/./(?P<id>\w+)'
_TEST = {
'url': 'https://filemoon.sx/e/dw40rxrzruqz',
'md5': '5a713742f57ac4aef29b74733e8dda01',
'info_dict': {
'id': 'dw40rxrzruqz',
'title': 'dw40rxrzruqz',
'ext': 'mp4'
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
matches = re.findall(r'(?s)(eval.*?)</script>', webpage)
packed = matches[-1]
unpacked = decode_packed_codes(packed)
jwplayer_sources = self._parse_json(
self._search_regex(
r'(?s)player\s*\.\s*setup\s*\(\s*\{\s*sources\s*:\s*(.*?])', unpacked, 'jwplayer sources'),
video_id, transform_source=js_to_json)
formats = self._parse_jwplayer_formats(jwplayer_sources, video_id)
return {
'id': video_id,
'title': self._generic_title(url) or video_id,
'formats': formats
}

200
youtube_dl/extractor/generic.py
View File

@@ -28,6 +28,7 @@ from ..utils import (
mimetype2ext,
orderedSet,
parse_duration,
parse_resolution,
sanitized_Request,
smuggle_url,
unescapeHTML,
@@ -35,6 +36,7 @@ from ..utils import (
unsmuggle_url,
UnsupportedError,
url_or_none,
urljoin,
xpath_attr,
xpath_text,
xpath_with_ns,
@@ -2227,6 +2229,97 @@ class GenericIE(InfoExtractor):
# Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
'only_matching': True,
}, {
# KVS Player
'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
'info_dict': {
'id': '105',
'display_id': 'kelis-4th-of-july',
'ext': 'mp4',
'title': 'Kelis - 4th Of July',
'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
},
}, {
# KVS Player
'url': 'https://www.kvs-demo.com/embed/105/',
'info_dict': {
'id': '105',
'display_id': 'kelis-4th-of-july',
'ext': 'mp4',
'title': 'Kelis - 4th Of July / Embed Player',
'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
},
'params': {
'skip_download': True,
},
}, {
# KVS Player (tested also in thisvid.py)
'url': 'https://youix.com/video/leningrad-zoj/',
'md5': '94f96ba95706dc3880812b27b7d8a2b8',
'info_dict': {
'id': '18485',
'display_id': 'leningrad-zoj',
'ext': 'mp4',
'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
},
}, {
# KVS Player
'url': 'https://youix.com/embed/18485',
'md5': '94f96ba95706dc3880812b27b7d8a2b8',
'info_dict': {
'id': '18485',
'display_id': 'leningrad-zoj',
'ext': 'mp4',
'title': 'Ленинград - ЗОЖ',
'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
},
}, {
# KVS Player
'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
'md5': '94166bdb26b4cb1fb9214319a629fc51',
'info_dict': {
'id': '21217',
'display_id': '40-nochey-2016',
'ext': 'mp4',
'title': '40 ночей (2016) - BogMedia.org',
'description': 'md5:4e6d7d622636eb7948275432eb256dc3',
'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
},
}, {
# KVS Player (for sites that serve kt_player.js via non-https urls)
'url': 'http://www.camhub.world/embed/389508',
'md5': 'fbe89af4cfb59c8fd9f34a202bb03e32',
'info_dict': {
'id': '389508',
'display_id': 'syren-de-mer-onlyfans-05-07-2020have-a-happy-safe-holiday5f014e68a220979bdb8cd-source',
'ext': 'mp4',
'title': 'Syren De Mer onlyfans_05-07-2020Have_a_happy_safe_holiday5f014e68a220979bdb8cd_source / Embed плеер',
'thumbnail': r're:https?://www\.camhub\.world/contents/videos_screenshots/389000/389508/preview\.mp4\.jpg',
},
}, {
'url': 'https://mrdeepfakes.com/video/5/selena-gomez-pov-deep-fakes',
'md5': 'fec4ad5ec150f655e0c74c696a4a2ff4',
'info_dict': {
'id': '5',
'display_id': 'selena-gomez-pov-deep-fakes',
'ext': 'mp4',
'title': 'Selena Gomez POV (Deep Fakes) DeepFake Porn - MrDeepFakes',
'description': 'md5:17d1f84b578c9c26875ac5ef9a932354',
'height': 720,
'age_limit': 18,
},
}, {
'url': 'https://shooshtime.com/videos/284002/just-out-of-the-shower-joi/',
'md5': 'e2f0a4c329f7986280b7328e24036d60',
'info_dict': {
'id': '284002',
'display_id': 'just-out-of-the-shower-joi',
'ext': 'mp4',
'title': 'Just Out Of The Shower JOI - Shooshtime',
'height': 720,
'age_limit': 18,
},
},
]
@@ -2332,6 +2425,88 @@ class GenericIE(InfoExtractor):
'title': title,
}
def _extract_kvs(self, url, webpage, video_id):
def getlicensetoken(license):
modlicense = license.replace('$', '').replace('0', '1')
center = int(len(modlicense) / 2)
fronthalf = int(modlicense[:center + 1])
backhalf = int(modlicense[center:])
modlicense = compat_str(4 * abs(fronthalf - backhalf))
def parts():
for o in range(0, center + 1):
for i in range(1, 5):
yield compat_str((int(license[o + i]) + int(modlicense[o])) % 10)
return ''.join(parts())
def getrealurl(video_url, license_code):
if not video_url.startswith('function/0/'):
return video_url # not obfuscated
url_path, _, url_query = video_url.partition('?')
urlparts = url_path.split('/')[2:]
license = getlicensetoken(license_code)
newmagic = urlparts[5][:32]
def spells(x, o):
l = (o + sum(int(n) for n in license[o:])) % 32
for i in range(0, len(x)):
yield {l: x[o], o: x[l]}.get(i, x[i])
for o in range(len(newmagic) - 1, -1, -1):
newmagic = ''.join(spells(newmagic, o))
urlparts[5] = newmagic + urlparts[5][32:]
return '/'.join(urlparts) + '?' + url_query
flashvars = self._search_regex(
r'(?s)<script\b[^>]*>.*?var\s+flashvars\s*=\s*(\{.+?\});.*?</script>',
webpage, 'flashvars')
flashvars = self._parse_json(flashvars, video_id, transform_source=js_to_json)
# extract the part after the last / as the display_id from the
# canonical URL.
display_id = self._search_regex(
r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
webpage, 'display_id', fatal=False
)
title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
thumbnail = flashvars['preview_url']
if thumbnail.startswith('//'):
protocol, _, _ = url.partition('/')
thumbnail = protocol + thumbnail
url_keys = list(filter(re.compile(r'^video_(?:url|alt_url\d*)$').match, flashvars.keys()))
formats = []
for key in url_keys:
if '/get_file/' not in flashvars[key]:
continue
format_id = flashvars.get(key + '_text', key)
formats.append(merge_dicts(
parse_resolution(format_id) or parse_resolution(flashvars[key]), {
'url': urljoin(url, getrealurl(flashvars[key], flashvars['license_code'])),
'format_id': format_id,
'ext': 'mp4',
'http_headers': {'Referer': url},
}))
if not formats[-1].get('height'):
formats[-1]['quality'] = 1
self._sort_formats(formats)
return {
'id': flashvars['video_id'],
'display_id': display_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}
def _real_extract(self, url):
if url.startswith('//'):
return self.url_result(self.http_scheme() + url)
@@ -2540,9 +2715,16 @@ class GenericIE(InfoExtractor):
# but actually don't.
AGE_LIMIT_MARKERS = [
r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
r'>[^<]*you acknowledge you are at least (\d+) years old',
r'>\s*(?:18\s+U(?:\.S\.C\.|SC)\s+)?(?:§+\s*)?2257\b',
]
if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
age_limit = 18
for marker in AGE_LIMIT_MARKERS:
m = re.search(marker, webpage)
if not m:
continue
age_limit = max(
age_limit or 0,
int_or_none(m.groups() and m.group(1), default=18))
# video uploader is domain name
video_uploader = self._search_regex(
@@ -3389,6 +3571,20 @@ class GenericIE(InfoExtractor):
info_dict['formats'] = formats
return info_dict
# Look for generic KVS player (before ld+json for tests)
found = self._search_regex(
(r'<script\b[^>]+?\bsrc\s*=\s*(["\'])https?://(?:\S+?/)+kt_player\.js\?v=(?P<ver>\d+(?:\.\d+)+)\1[^>]*>',
# kt_player('kt_player', 'https://i.shoosh.co/player/kt_player.swf?v=5.5.1', ...
r'kt_player\s*\(\s*(["\'])(?:(?!\1)[\w\W])+\1\s*,\s*(["\'])https?://(?:\S+?/)+kt_player\.swf\?v=(?P<ver>\d+(?:\.\d+)+)\2\s*,',
), webpage, 'KVS player', group='ver', default=False)
if found:
self.report_extraction('%s: KVS Player' % (video_id, ))
if found.split('.')[0] not in ('4', '5', '6'):
self.report_warning('Untested major version (%s) in player engine - download may fail.' % (found, ))
return merge_dicts(
self._extract_kvs(url, webpage, video_id),
info_dict)
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject')

101
youtube_dl/extractor/hrfernsehen.py Normal file
View File

@@ -0,0 +1,101 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from ..utils import (
int_or_none,
unified_timestamp,
unescapeHTML
)
from .common import InfoExtractor
class HRFernsehenIE(InfoExtractor):
IE_NAME = 'hrfernsehen'
_VALID_URL = r'^https?://www\.(?:hr-fernsehen|hessenschau)\.de/.*,video-(?P<id>[0-9]{6})\.html'
_TESTS = [{
'url': 'https://www.hessenschau.de/tv-sendung/hessenschau-vom-26082020,video-130546.html',
'md5': '5c4e0ba94677c516a2f65a84110fc536',
'info_dict': {
'id': '130546',
'ext': 'mp4',
'description': 'Sturmtief Kirsten fegt über Hessen / Die Corona-Pandemie – eine Chronologie / '
'Sterbehilfe: Die Lage in Hessen / Miss Hessen leitet zwei eigene Unternehmen / '
'Pop-Up Museum zeigt Schwarze Unterhaltung und Black Music',
'subtitles': {'de': [{
'url': 'https://hr-a.akamaihd.net/video/as/hessenschau/2020_08/hrLogo_200826200407_L385592_512x288-25p-500kbit.vtt'
}]},
'timestamp': 1598470200,
'upload_date': '20200826',
'thumbnail': 'https://www.hessenschau.de/tv-sendung/hs_ganz-1554~_t-1598465545029_v-16to9__medium.jpg',
'title': 'hessenschau vom 26.08.2020'
}
}, {
'url': 'https://www.hr-fernsehen.de/sendungen-a-z/mex/sendungen/fair-und-gut---was-hinter-aldis-eigenem-guetesiegel-steckt,video-130544.html',
'only_matching': True
}]
_GEO_COUNTRIES = ['DE']
def extract_airdate(self, loader_data):
airdate_str = loader_data.get('mediaMetadata', {}).get('agf', {}).get('airdate')
if airdate_str is None:
return None
return unified_timestamp(airdate_str)
def extract_formats(self, loader_data):
stream_formats = []
for stream_obj in loader_data["videoResolutionLevels"]:
stream_format = {
'format_id': str(stream_obj['verticalResolution']) + "p",
'height': stream_obj['verticalResolution'],
'url': stream_obj['url'],
}
quality_information = re.search(r'([0-9]{3,4})x([0-9]{3,4})-([0-9]{2})p-([0-9]{3,4})kbit',
stream_obj['url'])
if quality_information:
stream_format['width'] = int_or_none(quality_information.group(1))
stream_format['height'] = int_or_none(quality_information.group(2))
stream_format['fps'] = int_or_none(quality_information.group(3))
stream_format['tbr'] = int_or_none(quality_information.group(4))
stream_formats.append(stream_format)
self._sort_formats(stream_formats)
return stream_formats
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta(
['og:title', 'twitter:title', 'name'], webpage)
description = self._html_search_meta(
['description'], webpage)
loader_str = unescapeHTML(self._search_regex(r"data-new-hr-mediaplayer-loader='([^']*)'", webpage, "ardloader"))
loader_data = json.loads(loader_str)
info = {
'id': video_id,
'title': title,
'description': description,
'formats': self.extract_formats(loader_data),
'timestamp': self.extract_airdate(loader_data)
}
if "subtitle" in loader_data:
info["subtitles"] = {"de": [{"url": loader_data["subtitle"]}]}
thumbnails = list(set([t for t in loader_data.get("previewImageUrl", {}).values()]))
if len(thumbnails) > 0:
info["thumbnails"] = [{"url": t} for t in thumbnails]
return info

347
youtube_dl/extractor/ign.py
View File

@@ -1,19 +1,29 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_filter as filter,
compat_HTTPError,
compat_parse_qs,
compat_urllib_parse_urlparse,
compat_urlparse,
)
from ..utils import (
HEADRequest,
determine_ext,
error_to_compat_str,
extract_attributes,
ExtractorError,
int_or_none,
merge_dicts,
orderedSet,
parse_iso8601,
strip_or_none,
try_get,
traverse_obj,
url_or_none,
urljoin,
)
@@ -22,14 +32,102 @@ class IGNBaseIE(InfoExtractor):
return self._download_json(
'http://apis.ign.com/{0}/v3/{0}s/slug/{1}'.format(self._PAGE_TYPE, slug), slug)
def _checked_call_api(self, slug):
try:
return self._call_api(slug)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
e.cause.args = e.cause.args or [
e.cause.geturl(), e.cause.getcode(), e.cause.reason]
raise ExtractorError(
'Content not found: expired?', cause=e.cause,
expected=True)
raise
def _extract_video_info(self, video, fatal=True):
video_id = video['videoId']
formats = []
refs = traverse_obj(video, 'refs', expected_type=dict) or {}
m3u8_url = url_or_none(refs.get('m3uUrl'))
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
f4m_url = url_or_none(refs.get('f4mUrl'))
if f4m_url:
formats.extend(self._extract_f4m_formats(
f4m_url, video_id, f4m_id='hds', fatal=False))
for asset in (video.get('assets') or []):
asset_url = url_or_none(asset.get('url'))
if not asset_url:
continue
formats.append({
'url': asset_url,
'tbr': int_or_none(asset.get('bitrate'), 1000),
'fps': int_or_none(asset.get('frame_rate')),
'height': int_or_none(asset.get('height')),
'width': int_or_none(asset.get('width')),
})
mezzanine_url = traverse_obj(
video, ('system', 'mezzanineUrl'), expected_type=url_or_none)
if mezzanine_url:
formats.append({
'ext': determine_ext(mezzanine_url, 'mp4'),
'format_id': 'mezzanine',
'preference': 1,
'url': mezzanine_url,
})
if formats or fatal:
self._sort_formats(formats)
else:
return
thumbnails = traverse_obj(
video, ('thumbnails', Ellipsis, {'url': 'url'}), expected_type=url_or_none)
tags = traverse_obj(
video, ('tags', Ellipsis, 'displayName'),
expected_type=lambda x: x.strip() or None)
metadata = traverse_obj(video, 'metadata', expected_type=dict) or {}
title = traverse_obj(
metadata, 'longTitle', 'title', 'name',
expected_type=lambda x: x.strip() or None)
return {
'id': video_id,
'title': title,
'description': strip_or_none(metadata.get('description')),
'timestamp': parse_iso8601(metadata.get('publishDate')),
'duration': int_or_none(metadata.get('duration')),
'thumbnails': thumbnails,
'formats': formats,
'tags': tags,
}
# yt-dlp shim
@classmethod
def _extract_from_webpage(cls, url, webpage):
for embed_url in orderedSet(
cls._extract_embed_urls(url, webpage) or [], lazy=True):
yield cls.url_result(embed_url, None if cls._VALID_URL is False else cls)
class IGNIE(IGNBaseIE):
"""
Extractor for some of the IGN sites, like www.ign.com, es.ign.com de.ign.com.
Some videos of it.ign.com are also supported
"""
_VALID_URL = r'https?://(?:.+?\.ign|www\.pcmag)\.com/videos/(?:\d{4}/\d{2}/\d{2}/)?(?P<id>[^/?&#]+)'
_VIDEO_PATH_RE = r'/(?:\d{4}/\d{2}/\d{2}/)?(?P<id>.+?)'
_PLAYLIST_PATH_RE = r'(?:/?\?(?P<filt>[^&#]+))?'
_VALID_URL = (
r'https?://(?:.+?\.ign|www\.pcmag)\.com/videos(?:%s)'
% '|'.join((_VIDEO_PATH_RE + r'(?:[/?&#]|$)', _PLAYLIST_PATH_RE)))
IE_NAME = 'ign.com'
_PAGE_TYPE = 'video'
@@ -44,7 +142,10 @@ class IGNIE(IGNBaseIE):
'timestamp': 1370440800,
'upload_date': '20130605',
'tags': 'count:9',
}
},
'params': {
'nocheckcertificate': True,
},
}, {
'url': 'http://www.pcmag.com/videos/2015/01/06/010615-whats-new-now-is-gogo-snooping-on-your-data',
'md5': 'f1581a6fe8c5121be5b807684aeac3f6',
@@ -56,86 +157,51 @@ class IGNIE(IGNBaseIE):
'timestamp': 1420571160,
'upload_date': '20150106',
'tags': 'count:4',
}
},
'skip': '404 Not Found',
}, {
'url': 'https://www.ign.com/videos/is-a-resident-evil-4-remake-on-the-way-ign-daily-fix',
'only_matching': True,
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):
grids = re.findall(
r'''(?s)<section\b[^>]+\bclass\s*=\s*['"](?:[\w-]+\s+)*?content-feed-grid(?!\B|-)[^>]+>(.+?)</section[^>]*>''',
webpage)
return filter(None,
(urljoin(url, m.group('path')) for m in re.finditer(
r'''<a\b[^>]+\bhref\s*=\s*('|")(?P<path>/videos%s)\1'''
% cls._VIDEO_PATH_RE, grids[0] if grids else '')))
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
display_id = m.group('id')
if display_id:
return self._extract_video(url, display_id)
display_id = m.group('filt') or 'all'
return self._extract_playlist(url, display_id)
def _extract_playlist(self, url, display_id):
webpage = self._download_webpage(url, display_id)
return self.playlist_result(
(self.url_result(u, ie=self.ie_key())
for u in self._extract_embed_urls(url, webpage)),
playlist_id=display_id)
def _extract_video(self, url, display_id):
display_id = self._match_id(url)
video = self._call_api(display_id)
video_id = video['videoId']
metadata = video['metadata']
title = metadata.get('longTitle') or metadata.get('title') or metadata['name']
video = self._checked_call_api(display_id)
formats = []
refs = video.get('refs') or {}
info = self._extract_video_info(video)
m3u8_url = refs.get('m3uUrl')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
f4m_url = refs.get('f4mUrl')
if f4m_url:
formats.extend(self._extract_f4m_formats(
f4m_url, video_id, f4m_id='hds', fatal=False))
for asset in (video.get('assets') or []):
asset_url = asset.get('url')
if not asset_url:
continue
formats.append({
'url': asset_url,
'tbr': int_or_none(asset.get('bitrate'), 1000),
'fps': int_or_none(asset.get('frame_rate')),
'height': int_or_none(asset.get('height')),
'width': int_or_none(asset.get('width')),
})
mezzanine_url = try_get(video, lambda x: x['system']['mezzanineUrl'])
if mezzanine_url:
formats.append({
'ext': determine_ext(mezzanine_url, 'mp4'),
'format_id': 'mezzanine',
'preference': 1,
'url': mezzanine_url,
})
self._sort_formats(formats)
thumbnails = []
for thumbnail in (video.get('thumbnails') or []):
thumbnail_url = thumbnail.get('url')
if not thumbnail_url:
continue
thumbnails.append({
'url': thumbnail_url,
})
tags = []
for tag in (video.get('tags') or []):
display_name = tag.get('displayName')
if not display_name:
continue
tags.append(display_name)
return {
'id': video_id,
'title': title,
'description': strip_or_none(metadata.get('description')),
'timestamp': parse_iso8601(metadata.get('publishDate')),
'duration': int_or_none(metadata.get('duration')),
return merge_dicts({
'display_id': display_id,
'thumbnails': thumbnails,
'formats': formats,
'tags': tags,
}
}, info)
class IGNVideoIE(InfoExtractor):
class IGNVideoIE(IGNBaseIE):
_VALID_URL = r'https?://.+?\.ign\.com/(?:[a-z]{2}/)?[^/]+/(?P<id>\d+)/(?:video|trailer)/'
_TESTS = [{
'url': 'http://me.ign.com/en/videos/112203/video/how-hitman-aims-to-be-different-than-every-other-s',
@@ -147,7 +213,8 @@ class IGNVideoIE(InfoExtractor):
'description': 'Taking out assassination targets in Hitman has never been more stylish.',
'timestamp': 1444665600,
'upload_date': '20151012',
}
},
'expected_warnings': ['HTTP Error 400: Bad Request'],
}, {
'url': 'http://me.ign.com/ar/angry-birds-2/106533/video/lrd-ldyy-lwl-lfylm-angry-birds',
'only_matching': True,
@@ -167,22 +234,38 @@ class IGNVideoIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
req = HEADRequest(url.rsplit('/', 1)[0] + '/embed')
url = self._request_webpage(req, video_id).geturl()
parsed_url = compat_urlparse.urlparse(url)
embed_url = compat_urlparse.urlunparse(
parsed_url._replace(path=parsed_url.path.rsplit('/', 1)[0] + '/embed'))
webpage, urlh = self._download_webpage_handle(embed_url, video_id)
new_url = urlh.geturl()
ign_url = compat_parse_qs(
compat_urllib_parse_urlparse(url).query).get('url', [None])[0]
compat_urlparse.urlparse(new_url).query).get('url', [None])[-1]
if ign_url:
return self.url_result(ign_url, IGNIE.ie_key())
return self.url_result(url)
video = self._search_regex(r'(<div\b[^>]+\bdata-video-id\s*=\s*[^>]+>)', webpage, 'video element', fatal=False)
if not video:
if new_url == url:
raise ExtractorError('Redirect loop: ' + url)
return self.url_result(new_url)
video = extract_attributes(video)
video_data = video.get('data-settings') or '{}'
video_data = self._parse_json(video_data, video_id)['video']
info = self._extract_video_info(video_data)
return merge_dicts({
'display_id': video_id,
}, info)
class IGNArticleIE(IGNBaseIE):
_VALID_URL = r'https?://.+?\.ign\.com/(?:articles(?:/\d{4}/\d{2}/\d{2})?|(?:[a-z]{2}/)?feature/\d+)/(?P<id>[^/?&#]+)'
_VALID_URL = r'https?://.+?\.ign\.com/(?:articles(?:/\d{4}/\d{2}/\d{2})?|(?:[a-z]{2}/)?(?:[\w-]+/)*?feature/\d+)/(?P<id>[^/?&#]+)'
_PAGE_TYPE = 'article'
_TESTS = [{
'url': 'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
'info_dict': {
'id': '524497489e4e8ff5848ece34',
'id': '72113',
'title': '100 Little Things in GTA 5 That Will Blow Your Mind',
},
'playlist': [
@@ -190,7 +273,7 @@ class IGNArticleIE(IGNBaseIE):
'info_dict': {
'id': '5ebbd138523268b93c9141af17bec937',
'ext': 'mp4',
'title': 'GTA 5 Video Review',
'title': 'Grand Theft Auto V Video Review',
'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
'timestamp': 1379339880,
'upload_date': '20130916',
@@ -200,7 +283,7 @@ class IGNArticleIE(IGNBaseIE):
'info_dict': {
'id': '638672ee848ae4ff108df2a296418ee2',
'ext': 'mp4',
'title': '26 Twisted Moments from GTA 5 in Slow Motion',
'title': 'GTA 5 In Slow Motion',
'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
'timestamp': 1386878820,
'upload_date': '20131212',
@@ -208,16 +291,17 @@ class IGNArticleIE(IGNBaseIE):
},
],
'params': {
'playlist_items': '2-3',
'skip_download': True,
},
'expected_warnings': ['Backend fetch failed'],
}, {
'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch',
'info_dict': {
'id': '53ee806780a81ec46e0790f8',
'title': 'Rewind Theater - Wild Trailer Gamescom 2014',
},
'playlist_count': 2,
'playlist_count': 1,
'expected_warnings': ['Backend fetch failed'],
}, {
# videoId pattern
'url': 'http://www.ign.com/articles/2017/06/08/new-ducktales-short-donalds-birthday-doesnt-go-as-planned',
@@ -240,18 +324,91 @@ class IGNArticleIE(IGNBaseIE):
'only_matching': True,
}]
def _checked_call_api(self, slug):
try:
return self._call_api(slug)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
e.cause.args = e.cause.args or [
e.cause.geturl(), e.cause.getcode(), e.cause.reason]
if e.cause.code == 404:
raise ExtractorError(
'Content not found: expired?', cause=e.cause,
expected=True)
elif e.cause.code == 503:
self.report_warning(error_to_compat_str(e.cause))
return
raise
def _search_nextjs_data(self, webpage, video_id, **kw):
return self._parse_json(
self._search_regex(
r'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>',
webpage, 'next.js data', **kw),
video_id, **kw)
def _real_extract(self, url):
display_id = self._match_id(url)
article = self._call_api(display_id)
article = self._checked_call_api(display_id)
def entries():
media_url = try_get(article, lambda x: x['mediaRelations'][0]['media']['metadata']['url'])
if media_url:
yield self.url_result(media_url, IGNIE.ie_key())
for content in (article.get('content') or []):
for video_url in re.findall(r'(?:\[(?:ignvideo\s+url|youtube\s+clip_id)|<iframe[^>]+src)="([^"]+)"', content):
yield self.url_result(video_url)
if article:
# obsolete ?
def entries():
media_url = traverse_obj(
article, ('mediaRelations', 0, 'media', 'metadata', 'url'),
expected_type=url_or_none)
if media_url:
yield self.url_result(media_url, IGNIE.ie_key())
for content in (article.get('content') or []):
for video_url in re.findall(r'(?:\[(?:ignvideo\s+url|youtube\s+clip_id)|<iframe[^>]+src)="([^"]+)"', content):
if url_or_none(video_url):
yield self.url_result(video_url)
return self.playlist_result(
entries(), article.get('articleId'),
traverse_obj(
article, ('metadata', 'headline'),
expected_type=lambda x: x.strip() or None))
webpage = self._download_webpage(url, display_id)
playlist_id = self._html_search_meta('dable:item_id', webpage, default=None)
if playlist_id:
def entries():
for m in re.finditer(
r'''(?s)<object\b[^>]+\bclass\s*=\s*("|')ign-videoplayer\1[^>]*>(?P<params>.+?)</object''',
webpage):
flashvars = self._search_regex(
r'''(<param\b[^>]+\bname\s*=\s*("|')flashvars\2[^>]*>)''',
m.group('params'), 'flashvars', default='')
flashvars = compat_parse_qs(extract_attributes(flashvars).get('value') or '')
v_url = url_or_none((flashvars.get('url') or [None])[-1])
if v_url:
yield self.url_result(v_url)
else:
playlist_id = self._search_regex(
r'''\bdata-post-id\s*=\s*("|')(?P<id>[\da-f]+)\1''',
webpage, 'id', group='id', default=None)
nextjs_data = self._search_nextjs_data(webpage, display_id)
def entries():
for player in traverse_obj(
nextjs_data,
('props', 'apolloState', 'ROOT_QUERY', lambda k, _: k.startswith('videoPlayerProps('), '__ref')):
# skip promo links (which may not always be served, eg GH CI servers)
if traverse_obj(nextjs_data,
('props', 'apolloState', player.replace('PlayerProps', 'ModernContent')),
expected_type=dict):
continue
video = traverse_obj(nextjs_data, ('props', 'apolloState', player), expected_type=dict) or {}
info = self._extract_video_info(video, fatal=False)
if info:
yield merge_dicts({
'display_id': display_id,
}, info)
return self.playlist_result(
entries(), article.get('articleId'),
strip_or_none(try_get(article, lambda x: x['metadata']['headline'])))
entries(), playlist_id or display_id,
re.sub(r'\s+-\s+IGN\s*$', '', self._og_search_title(webpage, default='')) or None)

9
youtube_dl/extractor/infoq.py
View File

@@ -1,6 +1,9 @@
# coding: utf-8
from __future__ import unicode_literals
from ..utils import (
ExtractorError,
)
from ..compat import (
compat_b64decode,
@@ -90,7 +93,11 @@ class InfoQIE(BokeCCBaseIE):
}]
def _extract_http_audio(self, webpage, video_id):
fields = self._form_hidden_inputs('mp3Form', webpage)
try:
fields = self._form_hidden_inputs('mp3Form', webpage)
except ExtractorError:
fields = {}
http_audio_url = fields.get('filename')
if not http_audio_url:
return []

382
youtube_dl/extractor/itv.py
View File

@@ -3,123 +3,266 @@ from __future__ import unicode_literals
import json
import re
import sys
from .common import InfoExtractor
from .brightcove import BrightcoveNewIE
from ..compat import (
compat_HTTPError,
compat_integer_types,
compat_kwargs,
compat_urlparse,
)
from ..utils import (
clean_html,
determine_ext,
error_to_compat_str,
extract_attributes,
get_element_by_class,
JSON_LD_RE,
ExtractorError,
get_element_by_attribute,
int_or_none,
merge_dicts,
parse_duration,
parse_iso8601,
remove_start,
smuggle_url,
strip_or_none,
traverse_obj,
url_or_none,
urljoin,
)
class ITVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'
_GEO_COUNTRIES = ['GB']
class ITVBaseIE(InfoExtractor):
def _search_nextjs_data(self, webpage, video_id, **kw):
transform_source = kw.pop('transform_source', None)
fatal = kw.pop('fatal', True)
return self._parse_json(
self._search_regex(
r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
webpage, 'next.js data', group='js', fatal=fatal, **kw),
video_id, transform_source=transform_source, fatal=fatal)
def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
if errnote is False:
return False
if errnote is None:
errnote = 'Unable to download webpage'
errmsg = '%s: %s' % (errnote, error_to_compat_str(err))
if fatal:
raise ExtractorError(errmsg, sys.exc_info()[2], cause=err, video_id=video_id)
else:
self._downloader.report_warning(errmsg)
return False
@staticmethod
def _vanilla_ua_header():
return {'User-agent': 'Mozilla/5.0'}
def _download_webpage_handle(self, url, video_id, *args, **kwargs):
# specialised to (a) use vanilla UA (b) detect geo-block
params = self._downloader.params
nkwargs = {}
if (
'user_agent' not in params
and not any(re.match(r'(?i)user-agent\s*:', h)
for h in (params.get('headers') or []))
and 'User-agent' not in (kwargs.get('headers') or {})):
kwargs.setdefault('headers', {})
kwargs['headers'] = self._vanilla_ua_header()
nkwargs = kwargs
if kwargs.get('expected_status') is not None:
exp = kwargs['expected_status']
if isinstance(exp, compat_integer_types):
exp = [exp]
if isinstance(exp, (list, tuple)) and 403 not in exp:
kwargs['expected_status'] = [403]
kwargs['expected_status'].extend(exp)
nkwargs = kwargs
else:
kwargs['expected_status'] = 403
nkwargs = kwargs
if nkwargs:
kwargs = compat_kwargs(kwargs)
ret = super(ITVBaseIE, self)._download_webpage_handle(url, video_id, *args, **kwargs)
if ret is False:
return ret
webpage, urlh = ret
if urlh.getcode() == 403:
# geo-block error is like this, with an unnecessary 'Of':
# '{\n "Message" : "Request Originated Outside Of Allowed Geographic Region",\
# \n "TransactionId" : "oas-magni-475082-xbYF0W"\n}'
if '"Request Originated Outside Of Allowed Geographic Region"' in webpage:
self.raise_geo_restricted(countries=['GB'])
ret = self.__handle_request_webpage_error(
compat_HTTPError(urlh.geturl(), 403, 'HTTP Error 403: Forbidden', urlh.headers, urlh),
fatal=kwargs.get('fatal'))
return ret
class ITVIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
_IE_DESC = 'ITVX'
_TESTS = [{
'note': 'Hub URLs redirect to ITVX',
'url': 'https://www.itv.com/hub/liar/2a4547a0012',
'info_dict': {
'id': '2a4547a0012',
'ext': 'mp4',
'title': 'Liar - Series 2 - Episode 6',
'description': 'md5:d0f91536569dec79ea184f0a44cca089',
'series': 'Liar',
'season_number': 2,
'episode_number': 6,
},
'params': {
# m3u8 download
'skip_download': True,
},
'only_matching': True,
}, {
# unavailable via data-playlist-url
'note': 'Hub page unavailable via data-playlist-url (404 now)',
'url': 'https://www.itv.com/hub/through-the-keyhole/2a2271a0033',
'only_matching': True,
}, {
# InvalidVodcrid
'note': 'Hub page with InvalidVodcrid (404 now)',
'url': 'https://www.itv.com/hub/james-martins-saturday-morning/2a5159a0034',
'only_matching': True,
}, {
# ContentUnavailable
'note': 'Hub page with ContentUnavailable (404 now)',
'url': 'https://www.itv.com/hub/whos-doing-the-dishes/2a2898a0024',
'only_matching': True,
}]
}, {
'note': 'ITVX, or itvX, show',
'url': 'https://www.itv.com/watch/vera/1a7314/1a7314a0014',
'md5': 'bd0ad666b2c058fffe7d036785880064',
'info_dict': {
'id': '1a7314a0014',
'ext': 'mp4',
'title': 'Vera - Series 3 - Episode 4 - Prodigal Son',
'description': 'Vera and her team investigate the fatal stabbing of an ex-Met police officer outside a busy Newcastle nightclub - but there aren\'t many clues.',
'timestamp': 1653591600,
'upload_date': '20220526',
'uploader': 'ITVX',
'thumbnail': r're:https://\w+\.itv\.com/images/(?:\w+/)+\d+x\d+\?',
'duration': 5340.8,
'age_limit': 16,
'series': 'Vera',
'series_number': 3,
'episode': 'Prodigal Son',
'episode_number': 4,
'channel': 'ITV3',
'categories': list,
},
'params': {
# m3u8 download
# 'skip_download': True,
},
'skip': 'only available in UK',
}, {
'note': 'Latest ITV news bulletin: details change daily',
'url': 'https://www.itv.com/watch/news/varies-but-is-not-checked/6js5d0f',
'info_dict': {
'id': '6js5d0f',
'ext': 'mp4',
'title': r're:The latest ITV News headlines - \S.+',
'description': r'''re:.* today's top stories from the ITV News team.$''',
'timestamp': int,
'upload_date': r're:2\d\d\d(?:0[1-9]|1[0-2])(?:[012][1-9]|3[01])',
'uploader': 'ITVX',
'thumbnail': r're:https://images\.ctfassets\.net/(?:\w+/)+[\w.]+\.(?:jpg|png)',
'duration': float,
'age_limit': None,
},
'params': {
# variable download
# 'skip_download': True,
},
'skip': 'only available in UK',
}
]
def _og_extract(self, webpage, require_title=False):
return {
'title': self._og_search_title(webpage, fatal=require_title),
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'uploader': self._og_search_property('site_name', webpage, default=None),
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
params = extract_attributes(self._search_regex(
r'(?s)(<[^>]+id="video"[^>]*>)', webpage, 'params'))
ios_playlist_url = params.get('data-video-playlist') or params['data-video-id']
hmac = params['data-video-hmac']
webpage = self._download_webpage(url, video_id)
# now quite different params!
params = extract_attributes(self._search_regex(
r'''(<[^>]+\b(?:class|data-testid)\s*=\s*("|')genie-container\2[^>]*>)''',
webpage, 'params'))
ios_playlist_url = traverse_obj(
params, 'data-video-id', 'data-video-playlist',
get_all=False, expected_type=url_or_none)
headers = self.geo_verification_headers()
headers.update({
'Accept': 'application/vnd.itv.vod.playlist.v2+json',
'Content-Type': 'application/json',
'hmac': hmac.upper(),
})
ios_playlist = self._download_json(
ios_playlist_url, video_id, data=json.dumps({
'user': {
'itvUserId': '',
'entitlements': [],
'token': ''
},
'device': {
'manufacturer': 'Safari',
'model': '5',
'manufacturer': 'Mobile Safari',
'model': '5.1',
'os': {
'name': 'Windows NT',
'version': '6.1',
'type': 'desktop'
'name': 'iOS',
'version': '5.0',
'type': ' mobile'
}
},
'client': {
'version': '4.1',
'id': 'browser'
'id': 'browser',
'supportsAdPods': True,
'service': 'itv.x',
'appversion': '2.43.28',
},
'variantAvailability': {
'player': 'hls',
'featureset': {
'min': ['hls', 'aes', 'outband-webvtt'],
'max': ['hls', 'aes', 'outband-webvtt']
},
'platformTag': 'dotcom'
'platformTag': 'mobile'
}
}).encode(), headers=headers)
video_data = ios_playlist['Playlist']['Video']
ios_base_url = video_data.get('Base')
ios_base_url = traverse_obj(video_data, 'Base', expected_type=url_or_none)
media_url = (
(lambda u: url_or_none(urljoin(ios_base_url, u)))
if ios_base_url else url_or_none)
formats = []
for media_file in (video_data.get('MediaFiles') or []):
href = media_file.get('Href')
for media_file in traverse_obj(video_data, 'MediaFiles', expected_type=list) or []:
href = traverse_obj(media_file, 'Href', expected_type=media_url)
if not href:
continue
if ios_base_url:
href = ios_base_url + href
ext = determine_ext(href)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
href, video_id, 'mp4', entry_protocol='m3u8_native',
href, video_id, 'mp4', entry_protocol='m3u8',
m3u8_id='hls', fatal=False))
else:
formats.append({
'url': href,
})
self._sort_formats(formats)
for f in formats:
f.setdefault('http_headers', {})
f['http_headers'].update(self._vanilla_ua_header())
subtitles = {}
subs = video_data.get('Subtitles') or []
for sub in subs:
if not isinstance(sub, dict):
continue
href = url_or_none(sub.get('Href'))
for sub in traverse_obj(video_data, 'Subtitles', expected_type=list) or []:
href = traverse_obj(sub, 'Href', expected_type=url_or_none)
if not href:
continue
subtitles.setdefault('en', []).append({
@@ -127,59 +270,132 @@ class ITVIE(InfoExtractor):
'ext': determine_ext(href, 'vtt'),
})
info = self._search_json_ld(webpage, video_id, default={})
if not info:
json_ld = self._parse_json(self._search_regex(
JSON_LD_RE, webpage, 'JSON-LD', '{}',
group='json_ld'), video_id, fatal=False)
if json_ld and json_ld.get('@type') == 'BreadcrumbList':
for ile in (json_ld.get('itemListElement:') or []):
item = ile.get('item:') or {}
if item.get('@type') == 'TVEpisode':
item['@context'] = 'http://schema.org'
info = self._json_ld(item, video_id, fatal=False) or {}
break
next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
info = self._og_extract(webpage, require_title=not title)
tn = info.pop('thumbnail', None)
if tn:
info['thumbnails'] = [{'url': tn}]
# num. episode title
num_ep_title = video_data.get('numberedEpisodeTitle')
if not num_ep_title:
num_ep_title = clean_html(get_element_by_attribute('data-testid', 'episode-hero-description-strong', webpage))
num_ep_title = num_ep_title and num_ep_title.rstrip(' -')
ep_title = strip_or_none(
video_data.get('episodeTitle')
or (num_ep_title.split('.', 1)[-1] if num_ep_title else None))
title = title or re.sub(r'\s+-\s+ITVX$', '', info['title'])
if ep_title and ep_title != title:
title = title + ' - ' + ep_title
def get_thumbnails():
tns = []
for w, x in (traverse_obj(video_data, ('imagePresets'), expected_type=dict) or {}).items():
if isinstance(x, dict):
for y, z in x.items():
tns.append({'id': w + '_' + y, 'url': z})
return tns or None
video_str = lambda *x: traverse_obj(
video_data, *x, get_all=False, expected_type=strip_or_none)
return merge_dicts({
'id': video_id,
'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
'title': title,
'formats': formats,
'subtitles': subtitles,
'duration': parse_duration(video_data.get('Duration')),
'description': clean_html(get_element_by_class('episode-info__synopsis', webpage)),
# parsing hh:mm:ss:nnn not yet patched
'duration': parse_duration(re.sub(r'(\d{2})(:)(\d{3}$)', r'\1.\3', video_data.get('Duration') or '')),
'description': video_str('synopsis'),
'timestamp': traverse_obj(video_data, 'broadcastDateTime', 'dateTime', expected_type=parse_iso8601),
'thumbnails': get_thumbnails(),
'series': video_str('showTitle', 'programmeTitle'),
'series_number': int_or_none(video_data.get('seriesNumber')),
'episode': ep_title,
'episode_number': int_or_none((num_ep_title or '').split('.')[0]),
'channel': video_str('channel'),
'categories': traverse_obj(video_data, ('categories', 'formatted'), expected_type=list),
'age_limit': {False: 16, True: 0}.get(video_data.get('isChildrenCategory')),
}, info)
class ITVBTCCIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?itv\.com/btcc/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://www.itv.com/btcc/races/btcc-2018-all-the-action-from-brands-hatch',
class ITVBTCCIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
_IE_DESC = 'ITV articles: News, British Touring Car Championship'
_TESTS = [{
'note': 'British Touring Car Championship',
'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',
'info_dict': {
'id': 'btcc-2018-all-the-action-from-brands-hatch',
'title': 'BTCC 2018: All the action from Brands Hatch',
},
'playlist_mincount': 9,
}
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1582188683001/HkiHLnNRx_default/index.html?videoId=%s'
}, {
'note': 'redirects to /btcc/articles/...',
'url': 'http://www.itv.com/btcc/races/btcc-2018-all-the-action-from-brands-hatch',
'only_matching': True,
}, {
'note': 'news article',
'url': 'https://www.itv.com/news/wales/2020-07-23/sean-fletcher-shows-off-wales-coastline-in-new-itv-series-as-british-tourists-opt-for-staycations',
'info_dict': {
'id': 'sean-fletcher-shows-off-wales-coastline-in-new-itv-series-as-british-tourists-opt-for-staycations',
'title': '''Sean Fletcher on why Wales' coastline should be your 'staycation' destination | ITV News''',
},
'playlist_mincount': 1,
}]
# should really be a class var of the BC IE
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
BRIGHTCOVE_ACCOUNT = '1582188683001'
BRIGHTCOVE_PLAYER = 'HkiHLnNRx'
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
webpage, urlh = self._download_webpage_handle(url, playlist_id)
link = compat_urlparse.urlparse(urlh.geturl()).path.strip('/')
entries = [
self.url_result(
smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, {
# ITV does not like some GB IP ranges, so here are some
# IP blocks it accepts
'geo_ip_blocks': [
'193.113.0.0/16', '54.36.162.0/23', '159.65.16.0/21'
],
'referrer': url,
}),
ie=BrightcoveNewIE.ie_key(), video_id=video_id)
for video_id in re.findall(r'data-video-id=["\'](\d+)', webpage)]
next_data = self._search_nextjs_data(webpage, playlist_id, fatal=False, default='{}')
path_prefix = compat_urlparse.urlparse(next_data.get('assetPrefix') or '').path.strip('/')
link = remove_start(link, path_prefix).strip('/')
content = traverse_obj(
next_data, ('props', 'pageProps', Ellipsis),
expected_type=lambda x: x if x['link'] == link else None,
get_all=False, default={})
content = traverse_obj(
content, ('body', 'content', Ellipsis, 'data'),
expected_type=lambda x: x if x.get('name') == 'Brightcove' or x.get('type') == 'Brightcove' else None)
contraband = {
# ITV does not like some GB IP ranges, so here are some
# IP blocks it accepts
'geo_ip_blocks': [
'193.113.0.0/16', '54.36.162.0/23', '159.65.16.0/21'
],
'referrer': urlh.geturl(),
}
def entries():
for data in content or []:
video_id = data.get('id')
if not video_id:
continue
account = data.get('accountId') or self.BRIGHTCOVE_ACCOUNT
player = data.get('playerId') or self.BRIGHTCOVE_PLAYER
yield self.url_result(
smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % (account, player, video_id), contraband),
ie=BrightcoveNewIE.ie_key(), video_id=video_id)
# obsolete ?
for video_id in re.findall(r'''data-video-id=["'](\d+)''', webpage):
yield self.url_result(
smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % (self.BRIGHTCOVE_ACCOUNT, self.BRIGHTCOVE_PLAYER, video_id), contraband),
ie=BrightcoveNewIE.ie_key(), video_id=video_id)
title = self._og_search_title(webpage, fatal=False)
return self.playlist_result(entries, playlist_id, title)
return self.playlist_result(entries(), playlist_id, title)

2
youtube_dl/extractor/kaltura.py
View File

@@ -373,5 +373,5 @@ class KalturaIE(InfoExtractor):
'duration': info.get('duration'),
'timestamp': info.get('createdAt'),
'uploader_id': info.get('userId') if info.get('userId') != 'None' else None,
'view_count': info.get('plays'),
'view_count': int_or_none(info.get('plays')),
}

35
youtube_dl/extractor/kommunetv.py Normal file
View File

@@ -0,0 +1,35 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import update_url
class KommunetvIE(InfoExtractor):
_VALID_URL = r'https://(\w+).kommunetv.no/archive/(?P<id>\w+)'
_TEST = {
'url': 'https://oslo.kommunetv.no/archive/921',
'md5': '5f102be308ee759be1e12b63d5da4bbc',
'info_dict': {
'id': '921',
'title': 'Bystyremøte',
'ext': 'mp4'
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
headers = {
'Accept': 'application/json'
}
data = self._download_json('https://oslo.kommunetv.no/api/streams?streamType=1&id=%s' % video_id, video_id, headers=headers)
title = data['stream']['title']
file = data['playlist'][0]['playlist'][0]['file']
url = update_url(file, query=None, fragment=None)
formats = self._extract_m3u8_formats(url, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
self._sort_formats(formats)
return {
'id': video_id,
'formats': formats,
'title': title
}

31
youtube_dl/extractor/kth.py Normal file
View File

@@ -0,0 +1,31 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import smuggle_url
class KTHIE(InfoExtractor):
_VALID_URL = r'https?://play\.kth\.se/(?:[^/]+/)+(?P<id>[a-z0-9_]+)'
_TEST = {
'url': 'https://play.kth.se/media/Lunch+breakA+De+nya+aff%C3%A4rerna+inom+Fordonsdalen/0_uoop6oz9',
'md5': 'd83ada6d00ca98b73243a88efe19e8a6',
'info_dict': {
'id': '0_uoop6oz9',
'ext': 'mp4',
'title': 'md5:bd1d6931facb6828762a33e6ce865f37',
'thumbnail': 're:https?://.+/thumbnail/.+',
'duration': 3516,
'timestamp': 1647345358,
'upload_date': '20220315',
'uploader_id': 'md5:0ec23e33a89e795a4512930c8102509f',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
result = self.url_result(
smuggle_url('kaltura:308:%s' % video_id, {
'service_url': 'https://api.kaltura.nordu.net'}),
'Kaltura')
return result

123
youtube_dl/extractor/manyvids.py
View File

@@ -1,11 +1,16 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
extract_attributes,
int_or_none,
str_to_int,
url_or_none,
urlencode_postdata,
)
@@ -20,17 +25,20 @@ class ManyVidsIE(InfoExtractor):
'id': '133957',
'ext': 'mp4',
'title': 'everthing about me (Preview)',
'uploader': 'ellyxxix',
'view_count': int,
'like_count': int,
},
}, {
# full video
'url': 'https://www.manyvids.com/Video/935718/MY-FACE-REVEAL/',
'md5': 'f3e8f7086409e9b470e2643edb96bdcc',
'md5': 'bb47bab0e0802c2a60c24ef079dfe60f',
'info_dict': {
'id': '935718',
'ext': 'mp4',
'title': 'MY FACE REVEAL',
'description': 'md5:ec5901d41808b3746fed90face161612',
'uploader': 'Sarah Calanthe',
'view_count': int,
'like_count': int,
},
@@ -39,17 +47,50 @@ class ManyVidsIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
real_url = 'https://www.manyvids.com/video/%s/gtm.js' % (video_id, )
try:
webpage = self._download_webpage(real_url, video_id)
except Exception:
# probably useless fallback
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'video URL', group='url')
info = self._search_regex(
r'''(<div\b[^>]*\bid\s*=\s*(['"])pageMetaDetails\2[^>]*>)''',
webpage, 'meta details', default='')
info = extract_attributes(info)
title = self._html_search_regex(
(r'<span[^>]+class=["\']item-title[^>]+>([^<]+)',
r'<h2[^>]+class=["\']h2 m-0["\'][^>]*>([^<]+)'),
webpage, 'title', default=None) or self._html_search_meta(
'twitter:title', webpage, 'title', fatal=True)
player = self._search_regex(
r'''(<div\b[^>]*\bid\s*=\s*(['"])rmpPlayerStream\2[^>]*>)''',
webpage, 'player details', default='')
player = extract_attributes(player)
video_urls_and_ids = (
(info.get('data-meta-video'), 'video'),
(player.get('data-video-transcoded'), 'transcoded'),
(player.get('data-video-filepath'), 'filepath'),
(self._og_search_video_url(webpage, secure=False, default=None), 'og_video'),
)
def txt_or_none(s, default=None):
return (s.strip() or default) if isinstance(s, compat_str) else default
uploader = txt_or_none(info.get('data-meta-author'))
def mung_title(s):
if uploader:
s = re.sub(r'^\s*%s\s+[|-]' % (re.escape(uploader), ), '', s)
return txt_or_none(s)
title = (
mung_title(info.get('data-meta-title'))
or self._html_search_regex(
(r'<span[^>]+class=["\']item-title[^>]+>([^<]+)',
r'<h2[^>]+class=["\']h2 m-0["\'][^>]*>([^<]+)'),
webpage, 'title', default=None)
or self._html_search_meta(
'twitter:title', webpage, 'title', fatal=True))
title = re.sub(r'\s*[|-]\s+ManyVids\s*$', '', title) or title
if any(p in webpage for p in ('preview_videos', '_preview.mp4')):
title += ' (Preview)'
@@ -62,7 +103,8 @@ class ManyVidsIE(InfoExtractor):
# Sets some cookies
self._download_webpage(
'https://www.manyvids.com/includes/ajax_repository/you_had_me_at_hello.php',
video_id, fatal=False, data=urlencode_postdata({
video_id, note='Setting format cookies', fatal=False,
data=urlencode_postdata({
'mvtoken': mv_token,
'vid': video_id,
}), headers={
@@ -70,23 +112,56 @@ class ManyVidsIE(InfoExtractor):
'X-Requested-With': 'XMLHttpRequest'
})
if determine_ext(video_url) == 'm3u8':
formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
else:
formats = [{'url': video_url}]
formats = []
for v_url, fmt in video_urls_and_ids:
v_url = url_or_none(v_url)
if not v_url:
continue
if determine_ext(v_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
v_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls'))
else:
formats.append({
'url': v_url,
'format_id': fmt,
})
like_count = int_or_none(self._search_regex(
r'data-likes=["\'](\d+)', webpage, 'like count', default=None))
view_count = str_to_int(self._html_search_regex(
r'(?s)<span[^>]+class="views-wrapper"[^>]*>(.+?)</span', webpage,
'view count', default=None))
self._remove_duplicate_formats(formats)
for f in formats:
if f.get('height') is None:
f['height'] = int_or_none(
self._search_regex(r'_(\d{2,3}[02468])_', f['url'], 'video height', default=None))
if '/preview/' in f['url']:
f['format_id'] = '_'.join(filter(None, (f.get('format_id'), 'preview')))
f['preference'] = -10
if 'transcoded' in f['format_id']:
f['preference'] = f.get('preference', -1) - 1
self._sort_formats(formats)
def get_likes():
likes = self._search_regex(
r'''(<a\b[^>]*\bdata-id\s*=\s*(['"])%s\2[^>]*>)''' % (video_id, ),
webpage, 'likes', default='')
likes = extract_attributes(likes)
return int_or_none(likes.get('data-likes'))
def get_views():
return str_to_int(self._html_search_regex(
r'''(?s)<span\b[^>]*\bclass\s*=["']views-wrapper\b[^>]+>.+?<span\b[^>]+>\s*(\d[\d,.]*)\s*</span>''',
webpage, 'view count', default=None))
return {
'id': video_id,
'title': title,
'view_count': view_count,
'like_count': like_count,
'formats': formats,
'description': txt_or_none(info.get('data-meta-description')),
'uploader': txt_or_none(info.get('data-meta-author')),
'thumbnail': (
url_or_none(info.get('data-meta-image'))
or url_or_none(player.get('data-video-screenshot'))),
'view_count': get_views(),
'like_count': get_likes(),
}

6
youtube_dl/extractor/mediaset.py
View File

@@ -24,7 +24,7 @@ class MediasetIE(ThePlatformBaseIE):
(?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/
(?:
(?:video|on-demand|movie)/(?:[^/]+/)+[^/]+_|
player/index\.html\?.*?\bprogramGuid=
player(?:/v\d+)?/index\.html\?.*?\bprogramGuid=
)
)(?P<id>[0-9A-Z]{16,})
'''
@@ -73,6 +73,10 @@ class MediasetIE(ThePlatformBaseIE):
# iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665104&id=665104',
'only_matching': True,
}, {
# embedUrl (from https://www.wittytv.it/amici/est-ce-que-tu-maimes-gabriele-5-dicembre-copia/)
'url': 'https://static3.mediasetplay.mediaset.it/player/v2/index.html?partnerId=wittytv&configId=&programGuid=FD00000000153323&autoplay=true&purl=http://www.wittytv.it/amici/est-ce-que-tu-maimes-gabriele-5-dicembre-copia/',
'only_matching': True,
}, {
'url': 'mediaset:FAFU000000665924',
'only_matching': True,

2
youtube_dl/extractor/minds.py
View File

@@ -78,7 +78,7 @@ class MindsIE(MindsBaseIE):
else:
return self.url_result(entity['perma_url'])
else:
assert(entity['subtype'] == 'video')
assert (entity['subtype'] == 'video')
video_id = entity_id
# 1080p and webm formats available only on the sources array
video = self._call_api(

42
youtube_dl/extractor/motherless.py
View File

@@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import datetime
@@ -71,7 +72,7 @@ class MotherlessIE(InfoExtractor):
'title': 'a/ Hot Teens',
'categories': list,
'upload_date': '20210104',
'uploader_id': 'yonbiw',
'uploader_id': 'anonymous',
'thumbnail': r're:https?://.*\.jpg',
'age_limit': 18,
},
@@ -125,9 +126,10 @@ class MotherlessIE(InfoExtractor):
kwargs = {_AGO_UNITS.get(uploaded_ago[-1]): delta}
upload_date = (datetime.datetime.utcnow() - datetime.timedelta(**kwargs)).strftime('%Y%m%d')
comment_count = webpage.count('class="media-comment-contents"')
comment_count = len(re.findall(r'''class\s*=\s*['"]media-comment-contents\b''', webpage))
uploader_id = self._html_search_regex(
r'"thumb-member-username">\s+<a href="/m/([^"]+)"',
(r'''<span\b[^>]+\bclass\s*=\s*["']username\b[^>]*>([^<]+)</span>''',
r'''(?s)['"](?:media-meta-member|thumb-member-username)\b[^>]+>\s*<a\b[^>]+\bhref\s*=\s*['"]/m/([^"']+)'''),
webpage, 'uploader_id')
categories = self._html_search_meta('keywords', webpage, default=None)
@@ -169,7 +171,18 @@ class MotherlessGroupIE(InfoExtractor):
'description': 'Sex can be funny. Wide smiles,laugh, games, fun of '
'any kind!'
},
'playlist_mincount': 9,
'playlist_mincount': 0,
'expected_warnings': [
'This group has no videos.',
]
}, {
'url': 'https://motherless.com/g/beautiful_cock',
'info_dict': {
'id': 'beautiful_cock',
'title': 'Beautiful Cock',
'description': 'Group for lovely cocks yours, mine, a friends anything human',
},
'playlist_mincount': 2500,
}]
@classmethod
@@ -208,16 +221,23 @@ class MotherlessGroupIE(InfoExtractor):
r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
description = self._html_search_meta(
'description', webpage, fatal=False)
page_count = self._int(self._search_regex(
r'(\d+)</(?:a|span)><(?:a|span)[^>]+>\s*NEXT',
webpage, 'page_count'), 'page_count')
page_count = str_to_int(self._search_regex(
r'(\d+)\s*</(?:a|span)>\s*<(?:a|span)[^>]+(?:>\s*NEXT|\brel\s*=\s*["\']?next)\b',
webpage, 'page_count', default=0))
if not page_count:
message = self._search_regex(
r'''class\s*=\s*['"]error-page\b[^>]*>\s*<p[^>]*>\s*(?P<error_msg>[^<]+)(?<=\S)\s*''',
webpage, 'error_msg', default=None) or 'This group has no videos.'
self.report_warning(message, group_id)
page_count = 1
PAGE_SIZE = 80
def _get_page(idx):
webpage = self._download_webpage(
page_url, group_id, query={'page': idx + 1},
note='Downloading page %d/%d' % (idx + 1, page_count)
)
if idx > 0:
webpage = self._download_webpage(
page_url, group_id, query={'page': idx + 1},
note='Downloading page %d/%d' % (idx + 1, page_count)
)
for entry in self._extract_entries(webpage, url):
yield entry

4
youtube_dl/extractor/myspass.py
View File

@@ -35,7 +35,9 @@ class MySpassIE(InfoExtractor):
title = xpath_text(metadata, 'title', fatal=True)
video_url = xpath_text(metadata, 'url_flv', 'download url', True)
video_id_int = int(video_id)
for group in re.search(r'/myspass2009/\d+/(\d+)/(\d+)/(\d+)/', video_url).groups():
grps = re.search(r'/myspass2009/\d+/(\d+)/(\d+)/(\d+)/', video_url)
for group in grps.groups() if grps else []:
group_int = int(group)
if group_int > video_id_int:
video_url = video_url.replace(

87
youtube_dl/extractor/myvideoge.py Normal file
View File

@@ -0,0 +1,87 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
get_element_by_id,
get_element_by_class,
int_or_none,
js_to_json,
MONTH_NAMES,
qualities,
unified_strdate,
)
class MyVideoGeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?myvideo\.ge/v/(?P<id>[0-9]+)'
_TEST = {
'url': 'https://www.myvideo.ge/v/3941048',
'md5': '8c192a7d2b15454ba4f29dc9c9a52ea9',
'info_dict': {
'id': '3941048',
'ext': 'mp4',
'title': 'The best prikol',
'upload_date': '20200611',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'chixa33',
'description': 'md5:5b067801318e33c2e6eea4ab90b1fdd3',
},
# working from local dev system
'skip': 'site blocks CI servers',
}
_MONTH_NAMES_KA = ['იანვარი', 'თებერვალი', 'მარტი', 'აპრილი', 'მაისი', 'ივნისი', 'ივლისი', 'აგვისტო', 'სექტემბერი', 'ოქტომბერი', 'ნოემბერი', 'დეკემბერი']
_quality = staticmethod(qualities(('SD', 'HD')))
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = (
self._og_search_title(webpage, default=None)
or clean_html(get_element_by_class('my_video_title', webpage))
or self._html_search_regex(r'<title\b[^>]*>([^<]+)</title\b', webpage, 'title'))
jwplayer_sources = self._parse_json(
self._search_regex(
r'''(?s)jwplayer\s*\(\s*['"]mvplayer['"]\s*\)\s*\.\s*setup\s*\(.*?\bsources\s*:\s*(\[.*?])\s*[,});]''', webpage, 'jwplayer sources', fatal=False)
or '',
video_id, transform_source=js_to_json, fatal=False)
formats = self._parse_jwplayer_formats(jwplayer_sources or [], video_id)
for f in formats or []:
f['preference'] = self._quality(f['format_id'])
self._sort_formats(formats)
description = (
self._og_search_description(webpage)
or get_element_by_id('long_desc_holder', webpage)
or self._html_search_meta('description', webpage))
uploader = self._search_regex(r'<a[^>]+class="mv_user_name"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False)
upload_date = get_element_by_class('mv_vid_upl_date', webpage)
# as ka locale may not be present roll a local date conversion
upload_date = (unified_strdate(
# translate any ka month to an en one
re.sub('|'.join(self._MONTH_NAMES_KA),
lambda m: MONTH_NAMES['en'][self._MONTH_NAMES_KA.index(m.group(0))],
upload_date, re.I))
if upload_date else None)
return {
'id': video_id,
'title': title,
'description': description,
'uploader': uploader,
'formats': formats,
'thumbnail': self._og_search_thumbnail(webpage),
'upload_date': upload_date,
'view_count': int_or_none(get_element_by_class('mv_vid_views', webpage)),
'like_count': int_or_none(get_element_by_id('likes_count', webpage)),
'dislike_count': int_or_none(get_element_by_id('dislikes_count', webpage)),
}

101
youtube_dl/extractor/ndr.py
View File

@@ -4,8 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlparse
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
merge_dicts,
parse_iso8601,
@@ -20,13 +22,13 @@ class NDRBaseIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
display_id = next(group for group in mobj.groups() if group)
webpage = self._download_webpage(url, display_id)
return self._extract_embed(webpage, display_id)
return self._extract_embed(webpage, display_id, url)
class NDRIE(NDRBaseIE):
IE_NAME = 'ndr'
IE_DESC = 'NDR.de - Norddeutscher Rundfunk'
_VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html'
_VALID_URL = r'https?://(?:\w+\.)*ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html'
_TESTS = [{
# httpVideo, same content id
'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
@@ -38,13 +40,14 @@ class NDRIE(NDRBaseIE):
'title': 'Party, Pötte und Parade',
'description': 'md5:ad14f9d2f91d3040b6930c697e5f6b4c',
'uploader': 'ndrtv',
'timestamp': 1431108900,
'timestamp': 1431255671,
'upload_date': '20150510',
'duration': 3498,
},
'params': {
'skip_download': True,
},
'expected_warnings': ['Unable to download f4m manifest'],
}, {
# httpVideo, different content id
'url': 'http://www.ndr.de/sport/fussball/40-Osnabrueck-spielt-sich-in-einen-Rausch,osna270.html',
@@ -63,6 +66,7 @@ class NDRIE(NDRBaseIE):
'params': {
'skip_download': True,
},
'skip': 'No longer available',
}, {
# httpAudio, same content id
'url': 'http://www.ndr.de/info/La-Valette-entgeht-der-Hinrichtung,audio51535.html',
@@ -74,8 +78,8 @@ class NDRIE(NDRBaseIE):
'title': 'La Valette entgeht der Hinrichtung',
'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
'uploader': 'ndrinfo',
'timestamp': 1290626100,
'upload_date': '20140729',
'timestamp': 1631711863,
'upload_date': '20210915',
'duration': 884,
},
'params': {
@@ -89,9 +93,10 @@ class NDRIE(NDRBaseIE):
'display_id': 'extra-3-Satiremagazin-mit-Christian-Ehring',
'ext': 'mp4',
'title': 'Extra 3 vom 11.11.2020 mit Christian Ehring',
'description': 'md5:42ee53990a715eaaf4dc7f13a3bd56c6',
'description': 'md5:700f6de264010585012a72f97b0ac0c9',
'uploader': 'ndrtv',
'upload_date': '20201113',
'upload_date': '20201207',
'timestamp': 1614349457,
'duration': 1749,
'subtitles': {
'de': [{
@@ -109,19 +114,38 @@ class NDRIE(NDRBaseIE):
'only_matching': True,
}]
def _extract_embed(self, webpage, display_id):
embed_url = self._html_search_meta(
'embedURL', webpage, 'embed URL',
default=None) or self._search_regex(
r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'embed URL', group='url')
def _extract_embed(self, webpage, display_id, url):
embed_url = (
self._html_search_meta(
'embedURL', webpage, 'embed URL',
default=None)
or self._search_regex(
r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'embed URL', group='url', default=None)
or self._search_regex(
r'\bvar\s*sophoraID\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'embed URL', group='url', default=''))
# some more work needed if we only found sophoraID
if re.match(r'^[a-z]+\d+$', embed_url):
# get the initial part of the url path,. eg /panorama/archiv/2022/
parsed_url = compat_urllib_parse_urlparse(url)
path = self._search_regex(r'(.+/)%s' % display_id, parsed_url.path or '', 'embed URL', default='')
# find tell-tale image with the actual ID
ndr_id = self._search_regex(r'%s([a-z]+\d+)(?!\.)\b' % (path, ), webpage, 'embed URL', default=None)
# or try to use special knowledge!
NDR_INFO_URL_TPL = 'https://www.ndr.de/info/%s-player.html'
embed_url = 'ndr:%s' % (ndr_id, ) if ndr_id else NDR_INFO_URL_TPL % (embed_url, )
if not embed_url:
raise ExtractorError('Unable to extract embedUrl')
description = self._search_regex(
r'<p[^>]+itemprop="description">([^<]+)</p>',
webpage, 'description', default=None) or self._og_search_description(webpage)
timestamp = parse_iso8601(
self._search_regex(
r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"',
webpage, 'upload date', default=None))
(r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="(?P<cont>[^"]+)"',
r'\bvar\s*pdt\s*=\s*(?P<q>["\'])(?P<cont>(?:(?!(?P=q)).)+)(?P=q)', ),
webpage, 'upload date', group='cont', default=None))
info = self._search_json_ld(webpage, display_id, default={})
return merge_dicts({
'_type': 'url_transparent',
@@ -153,19 +177,19 @@ class NJoyIE(NDRBaseIE):
'params': {
'skip_download': True,
},
'skip': 'No longer available',
}, {
# httpVideo, different content id
'url': 'http://www.n-joy.de/musik/Das-frueheste-DJ-Set-des-Nordens-live-mit-Felix-Jaehn-,felixjaehn168.html',
'md5': '417660fffa90e6df2fda19f1b40a64d8',
'info_dict': {
'id': 'dockville882',
'id': 'livestream283',
'display_id': 'Das-frueheste-DJ-Set-des-Nordens-live-mit-Felix-Jaehn-',
'ext': 'mp4',
'title': '"Ich hab noch nie" mit Felix Jaehn',
'description': 'md5:85dd312d53be1b99e1f998a16452a2f3',
'ext': 'mp3',
'title': 'Das frueheste DJ Set des Nordens live mit Felix Jaehn',
'description': 'md5:681698f527b8601e511e7b79edde7d2c',
'uploader': 'njoy',
'upload_date': '20150822',
'duration': 211,
'upload_date': '20210830',
},
'params': {
'skip_download': True,
@@ -175,18 +199,25 @@ class NJoyIE(NDRBaseIE):
'only_matching': True,
}]
def _extract_embed(self, webpage, display_id):
def _extract_embed(self, webpage, display_id, url=None):
# find tell-tale URL with the actual ID, or ...
video_id = self._search_regex(
r'<iframe[^>]+id="pp_([\da-z]+)"', webpage, 'embed id')
description = self._search_regex(
r'<div[^>]+class="subline"[^>]*>[^<]+</div>\s*<p>([^<]+)</p>',
webpage, 'description', fatal=False)
(r'''\bsrc\s*=\s*["']?(?:/\w+)+/([a-z]+\d+)(?!\.)\b''',
r'<iframe[^>]+id="pp_([\da-z]+)"', ),
webpage, 'NDR id', default=None)
description = (
self._html_search_meta('description', webpage)
or self._search_regex(
r'<div[^>]+class="subline"[^>]*>[^<]+</div>\s*<p>([^<]+)</p>',
webpage, 'description', fatal=False))
return {
'_type': 'url_transparent',
'ie_key': 'NDREmbedBase',
'url': 'ndr:%s' % video_id,
'display_id': display_id,
'description': description,
'title': display_id.replace('-', ' ').strip(),
}
@@ -291,7 +322,7 @@ class NDREmbedBaseIE(InfoExtractor):
class NDREmbedIE(NDREmbedBaseIE):
IE_NAME = 'ndr:embed'
_VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
_VALID_URL = r'https?://(?:\w+\.)*ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:(?:ard)?player|externalPlayer)\.html'
_TESTS = [{
'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html',
'md5': '8b9306142fe65bbdefb5ce24edb6b0a9',
@@ -304,6 +335,7 @@ class NDREmbedIE(NDREmbedBaseIE):
'upload_date': '20150907',
'duration': 132,
},
'skip': 'No longer available',
}, {
'url': 'http://www.ndr.de/ndr2/events/soundcheck/soundcheck3366-player.html',
'md5': '002085c44bae38802d94ae5802a36e78',
@@ -319,6 +351,7 @@ class NDREmbedIE(NDREmbedBaseIE):
'params': {
'skip_download': True,
},
'skip': 'No longer available',
}, {
'url': 'http://www.ndr.de/info/audio51535-player.html',
'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
@@ -328,7 +361,7 @@ class NDREmbedIE(NDREmbedBaseIE):
'title': 'La Valette entgeht der Hinrichtung',
'is_live': False,
'uploader': 'ndrinfo',
'upload_date': '20140729',
'upload_date': '20210915',
'duration': 884,
},
'params': {
@@ -349,15 +382,17 @@ class NDREmbedIE(NDREmbedBaseIE):
'params': {
'skip_download': True,
},
'skip': 'No longer available',
}, {
# httpVideoLive
'url': 'http://www.ndr.de/fernsehen/livestream/livestream217-externalPlayer.html',
'info_dict': {
'id': 'livestream217',
'ext': 'flv',
'ext': 'mp4',
'title': r're:^NDR Fernsehen Niedersachsen \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'is_live': True,
'upload_date': '20150910',
'upload_date': '20210409',
'uploader': 'ndrtv',
},
'params': {
'skip_download': True,
@@ -395,9 +430,10 @@ class NJoyEmbedIE(NDREmbedBaseIE):
'ext': 'mp4',
'title': 'Zehn Jahre Reeperbahn Festival - die Doku',
'is_live': False,
'upload_date': '20150807',
'upload_date': '20200826',
'duration': 1011,
},
'expected_warnings': ['Unable to download f4m manifest'],
}, {
# httpAudio
'url': 'http://www.n-joy.de/news_wissen/stefanrichter100-player_image-d5e938b1-f21a-4b9a-86b8-aaba8bca3a13_theme-n-joy.html',
@@ -414,6 +450,7 @@ class NJoyEmbedIE(NDREmbedBaseIE):
'params': {
'skip_download': True,
},
'skip': 'No longer available',
}, {
# httpAudioLive, no explicit ext
'url': 'http://www.n-joy.de/news_wissen/webradioweltweit100-player_image-3fec0484-2244-4565-8fb8-ed25fd28b173_theme-n-joy.html',
@@ -423,7 +460,7 @@ class NJoyEmbedIE(NDREmbedBaseIE):
'title': r're:^N-JOY Weltweit \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'is_live': True,
'uploader': 'njoy',
'upload_date': '20150810',
'upload_date': '20210830',
},
'params': {
'skip_download': True,

157
youtube_dl/extractor/neteasemusic.py
View File

@@ -1,20 +1,32 @@
# coding: utf-8
from __future__ import unicode_literals
from hashlib import md5
from base64 import b64encode
from binascii import hexlify
from datetime import datetime
from hashlib import md5
from random import randint
import json
import re
import time
from .common import InfoExtractor
from ..aes import aes_ecb_encrypt, pkcs7_padding
from ..compat import (
compat_urllib_parse_urlencode,
compat_str,
compat_itertools_count,
)
from ..utils import (
sanitized_Request,
ExtractorError,
bytes_to_intlist,
error_to_compat_str,
float_or_none,
int_or_none,
intlist_to_bytes,
sanitized_Request,
std_headers,
try_get,
)
@@ -35,32 +47,106 @@ class NetEaseMusicBaseIE(InfoExtractor):
result = b64encode(m.digest()).decode('ascii')
return result.replace('/', '_').replace('+', '-')
@classmethod
def make_player_api_request_data_and_headers(cls, song_id, bitrate):
KEY = b'e82ckenh8dichen8'
URL = '/api/song/enhance/player/url'
now = int(time.time() * 1000)
rand = randint(0, 1000)
cookie = {
'osver': None,
'deviceId': None,
'appver': '8.0.0',
'versioncode': '140',
'mobilename': None,
'buildver': '1623435496',
'resolution': '1920x1080',
'__csrf': '',
'os': 'pc',
'channel': None,
'requestId': '{0}_{1:04}'.format(now, rand),
}
request_text = json.dumps(
{'ids': '[{0}]'.format(song_id), 'br': bitrate, 'header': cookie},
separators=(',', ':'))
message = 'nobody{0}use{1}md5forencrypt'.format(
URL, request_text).encode('latin1')
msg_digest = md5(message).hexdigest()
data = '{0}-36cd479b6b5-{1}-36cd479b6b5-{2}'.format(
URL, request_text, msg_digest)
data = pkcs7_padding(bytes_to_intlist(data))
encrypted = intlist_to_bytes(aes_ecb_encrypt(data, bytes_to_intlist(KEY)))
encrypted_params = hexlify(encrypted).decode('ascii').upper()
cookie = '; '.join(
['{0}={1}'.format(k, v if v is not None else 'undefined')
for [k, v] in cookie.items()])
headers = {
'User-Agent': std_headers['User-Agent'],
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': 'https://music.163.com',
'Cookie': cookie,
}
return ('params={0}'.format(encrypted_params), headers)
def _call_player_api(self, song_id, bitrate):
url = 'https://interface3.music.163.com/eapi/song/enhance/player/url'
data, headers = self.make_player_api_request_data_and_headers(song_id, bitrate)
try:
msg = 'empty result'
result = self._download_json(
url, song_id, data=data.encode('ascii'), headers=headers)
if result:
return result
except ExtractorError as e:
if type(e.cause) in (ValueError, TypeError):
# JSON load failure
raise
except Exception as e:
msg = error_to_compat_str(e)
self.report_warning('%s API call (%s) failed: %s' % (
song_id, bitrate, msg))
return {}
def extract_formats(self, info):
err = 0
formats = []
song_id = info['id']
for song_format in self._FORMATS:
details = info.get(song_format)
if not details:
continue
song_file_path = '/%s/%s.%s' % (
self._encrypt(details['dfsId']), details['dfsId'], details['extension'])
# 203.130.59.9, 124.40.233.182, 115.231.74.139, etc is a reverse proxy-like feature
# from NetEase's CDN provider that can be used if m5.music.126.net does not
# work, especially for users outside of Mainland China
# via: https://github.com/JixunMoe/unblock-163/issues/3#issuecomment-163115880
for host in ('http://m5.music.126.net', 'http://115.231.74.139/m1.music.126.net',
'http://124.40.233.182/m1.music.126.net', 'http://203.130.59.9/m1.music.126.net'):
song_url = host + song_file_path
bitrate = int_or_none(details.get('bitrate')) or 999000
data = self._call_player_api(song_id, bitrate)
for song in try_get(data, lambda x: x['data'], list) or []:
song_url = try_get(song, lambda x: x['url'])
if not song_url:
continue
if self._is_valid_url(song_url, info['id'], 'song'):
formats.append({
'url': song_url,
'ext': details.get('extension'),
'abr': float_or_none(details.get('bitrate'), scale=1000),
'abr': float_or_none(song.get('br'), scale=1000),
'format_id': song_format,
'filesize': details.get('size'),
'asr': details.get('sr')
'filesize': int_or_none(song.get('size')),
'asr': int_or_none(details.get('sr')),
})
break
elif err == 0:
err = try_get(song, lambda x: x['code'], int)
if not formats:
msg = 'No media links found'
if err != 0 and (err < 200 or err >= 400):
raise ExtractorError(
'%s (site code %d)' % (msg, err, ), expected=True)
else:
self.raise_geo_restricted(
msg + ': probably this video is not available from your location due to geo restriction.',
countries=['CN'])
return formats
@classmethod
@@ -76,33 +162,19 @@ class NetEaseMusicBaseIE(InfoExtractor):
class NetEaseMusicIE(NetEaseMusicBaseIE):
IE_NAME = 'netease:song'
IE_DESC = '网易云音乐'
_VALID_URL = r'https?://music\.163\.com/(#/)?song\?id=(?P<id>[0-9]+)'
_VALID_URL = r'https?://(y\.)?music\.163\.com/(?:[#m]/)?song\?.*?\bid=(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://music.163.com/#/song?id=32102397',
'md5': 'f2e97280e6345c74ba9d5677dd5dcb45',
'md5': '3e909614ce09b1ccef4a3eb205441190',
'info_dict': {
'id': '32102397',
'ext': 'mp3',
'title': 'Bad Blood (feat. Kendrick Lamar)',
'title': 'Bad Blood',
'creator': 'Taylor Swift / Kendrick Lamar',
'upload_date': '20150517',
'timestamp': 1431878400,
'description': 'md5:a10a54589c2860300d02e1de821eb2ef',
'upload_date': '20150516',
'timestamp': 1431792000,
'description': 'md5:25fc5f27e47aad975aa6d36382c7833c',
},
'skip': 'Blocked outside Mainland China',
}, {
'note': 'No lyrics translation.',
'url': 'http://music.163.com/#/song?id=29822014',
'info_dict': {
'id': '29822014',
'ext': 'mp3',
'title': '听见下雨的声音',
'creator': '周杰伦',
'upload_date': '20141225',
'timestamp': 1419523200,
'description': 'md5:a4d8d89f44656af206b7b2555c0bce6c',
},
'skip': 'Blocked outside Mainland China',
}, {
'note': 'No lyrics.',
'url': 'http://music.163.com/song?id=17241424',
@@ -112,9 +184,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
'title': 'Opus 28',
'creator': 'Dustin O\'Halloran',
'upload_date': '20080211',
'description': 'md5:f12945b0f6e0365e3b73c5032e1b0ff4',
'timestamp': 1202745600,
},
'skip': 'Blocked outside Mainland China',
}, {
'note': 'Has translated name.',
'url': 'http://music.163.com/#/song?id=22735043',
@@ -128,7 +200,18 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
'timestamp': 1264608000,
'alt_title': '说出愿望吧(Genie)',
},
'skip': 'Blocked outside Mainland China',
}, {
'url': 'https://y.music.163.com/m/song?app_version=8.8.45&id=95670&uct2=sKnvS4+0YStsWkqsPhFijw%3D%3D&dlt=0846',
'md5': '95826c73ea50b1c288b22180ec9e754d',
'info_dict': {
'id': '95670',
'ext': 'mp3',
'title': '国际歌',
'creator': '马备',
'upload_date': '19911130',
'timestamp': 691516800,
'description': 'md5:1ba2f911a2b0aa398479f595224f2141',
},
}]
def _process_lyrics(self, lyrics_info):

21
youtube_dl/extractor/nhk.py
View File

@@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import re
@@ -7,7 +8,7 @@ from ..utils import urljoin
class NhkBaseIE(InfoExtractor):
_API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7a/%s/%s/%s/all%s.json'
_API_URL_TEMPLATE = 'https://nwapi.nhk.jp/nhkworld/%sod%slist/v7b/%s/%s/%s/all%s.json'
_BASE_URL_REGEX = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand'
_TYPE_REGEX = r'/(?P<type>video|audio)/'
@@ -23,7 +24,7 @@ class NhkBaseIE(InfoExtractor):
def _extract_episode_info(self, url, episode=None):
fetch_episode = episode is None
lang, m_type, episode_id = re.match(NhkVodIE._VALID_URL, url).groups()
if episode_id.isdigit():
if len(episode_id) == 7:
episode_id = episode_id[:4] + '-' + episode_id[4:]
is_video = m_type == 'video'
@@ -84,7 +85,8 @@ class NhkBaseIE(InfoExtractor):
class NhkVodIE(NhkBaseIE):
_VALID_URL = r'%s%s(?P<id>\d{7}|[^/]+?-\d{8}-[0-9a-z]+)' % (NhkBaseIE._BASE_URL_REGEX, NhkBaseIE._TYPE_REGEX)
# the 7-character IDs can have alphabetic chars too: assume [a-z] rather than just [a-f], eg
_VALID_URL = r'%s%s(?P<id>[0-9a-z]{7}|[^/]+?-\d{8}-[0-9a-z]+)' % (NhkBaseIE._BASE_URL_REGEX, NhkBaseIE._TYPE_REGEX)
# Content available only for a limited period of time. Visit
# https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
_TESTS = [{
@@ -124,6 +126,19 @@ class NhkVodIE(NhkBaseIE):
}, {
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/j_art-20150903-1/',
'only_matching': True,
}, {
# video, alphabetic character in ID #29670
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999a34/',
'only_matching': True,
'info_dict': {
'id': 'qfjay6cg',
'ext': 'mp4',
'title': 'DESIGN TALKS plus - Fishermen’s Finery',
'description': 'md5:8a8f958aaafb0d7cb59d38de53f1e448',
'thumbnail': r're:^https?:/(/[a-z0-9.-]+)+\.jpg\?w=1920&h=1080$',
'upload_date': '20210615',
'timestamp': 1623722008,
}
}]
def _real_extract(self, url):

664
youtube_dl/extractor/niconico.py
View File

@@ -2,25 +2,28 @@
from __future__ import unicode_literals
import datetime
import functools
import itertools
import json
import math
import re
from .common import InfoExtractor
from .common import InfoExtractor, SearchInfoExtractor
from ..postprocessor.ffmpeg import FFmpegPostProcessor
from ..compat import (
compat_parse_qs,
compat_str,
compat_urllib_parse_urlparse,
)
from ..utils import (
determine_ext,
dict_get,
ExtractorError,
dict_get,
float_or_none,
InAdvancePagedList,
int_or_none,
OnDemandPagedList,
parse_duration,
parse_iso8601,
PostProcessingError,
remove_start,
str_or_none,
try_get,
unified_timestamp,
urlencode_postdata,
@@ -34,7 +37,7 @@ class NiconicoIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.nicovideo.jp/watch/sm22312215',
'md5': 'd1a75c0823e2f629128c43e1212760f9',
'md5': 'a5bad06f1347452102953f323c69da34s',
'info_dict': {
'id': 'sm22312215',
'ext': 'mp4',
@@ -157,11 +160,34 @@ class NiconicoIE(InfoExtractor):
}, {
'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
'only_matching': True,
}, {
# DMC video with heartbeat
'url': 'https://www.nicovideo.jp/watch/sm34815188',
'md5': '9360c6e1f1519d7759e2fe8e1326ae83',
'info_dict': {
'id': 'sm34815188',
'ext': 'mp4',
'title': 'md5:aee93e9f3366db72f902f6cd5d389cb7',
'description': 'md5:7b9149fc7a00ab053cafaf5c19662704',
'thumbnail': r're:https?://.*',
'uploader': 'md5:2762e18fa74dbb40aa1ad27c6291ee32',
'uploader_id': '67449889',
'upload_date': '20190322',
'timestamp': int, # timestamp is unstable
'duration': 1082.0,
'view_count': int,
'comment_count': int,
},
}]
_VALID_URL = r'https?://(?:www\.|secure\.|sp\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
_NETRC_MACHINE = 'niconico'
_API_HEADERS = {
'X-Frontend-ID': '6',
'X-Frontend-Version': '0'
}
def _real_initialize(self):
self._login()
@@ -191,37 +217,89 @@ class NiconicoIE(InfoExtractor):
self._downloader.report_warning('unable to log in: bad username or password')
return login_ok
def _extract_format_for_quality(self, api_data, video_id, audio_quality, video_quality):
def yesno(boolean):
return 'yes' if boolean else 'no'
def _get_heartbeat_info(self, info_dict):
session_api_data = api_data['video']['dmcInfo']['session_api']
session_api_endpoint = session_api_data['urls'][0]
video_id, video_src_id, audio_src_id = info_dict['url'].split(':')[1].split('/')
format_id = '-'.join(map(lambda s: remove_start(s['id'], 'archive_'), [video_quality, audio_quality]))
api_data = (
info_dict.get('_api_data')
or self._parse_json(
self._html_search_regex(
'data-api-data="([^"]+)"',
self._download_webpage('http://www.nicovideo.jp/watch/' + video_id, video_id),
'API data', default='{}'),
video_id))
session_api_data = try_get(api_data, lambda x: x['media']['delivery']['movie']['session'])
session_api_endpoint = try_get(session_api_data, lambda x: x['urls'][0])
def ping():
status = try_get(
self._download_json(
'https://nvapi.nicovideo.jp/v1/2ab0cbaa/watch', video_id,
query={'t': try_get(api_data, lambda x: x['media']['delivery']['trackingId'])},
note='Acquiring permission for downloading video',
headers=self._API_HEADERS),
lambda x: x['meta']['status'])
if status != 200:
self.report_warning('Failed to acquire permission for playing video. The video may not download.')
yesno = lambda x: 'yes' if x else 'no'
# m3u8 (encryption)
if try_get(api_data, lambda x: x['media']['delivery']['encryption']) is not None:
protocol = 'm3u8'
encryption = self._parse_json(session_api_data['token'], video_id)['hls_encryption']
session_api_http_parameters = {
'parameters': {
'hls_parameters': {
'encryption': {
encryption: {
'encrypted_key': try_get(api_data, lambda x: x['media']['delivery']['encryption']['encryptedKey']),
'key_uri': try_get(api_data, lambda x: x['media']['delivery']['encryption']['keyUri'])
}
},
'transfer_preset': '',
'use_ssl': yesno(session_api_endpoint['isSsl']),
'use_well_known_port': yesno(session_api_endpoint['isWellKnownPort']),
'segment_duration': 6000,
}
}
}
# http
else:
protocol = 'http'
session_api_http_parameters = {
'parameters': {
'http_output_download_parameters': {
'use_ssl': yesno(session_api_endpoint['isSsl']),
'use_well_known_port': yesno(session_api_endpoint['isWellKnownPort']),
}
}
}
session_response = self._download_json(
session_api_endpoint['url'], video_id,
query={'_format': 'json'},
headers={'Content-Type': 'application/json'},
note='Downloading JSON metadata for %s' % format_id,
note='Downloading JSON metadata for %s' % info_dict['format_id'],
data=json.dumps({
'session': {
'client_info': {
'player_id': session_api_data['player_id'],
'player_id': session_api_data.get('playerId'),
},
'content_auth': {
'auth_type': session_api_data['auth_types'][session_api_data['protocols'][0]],
'content_key_timeout': session_api_data['content_key_timeout'],
'auth_type': try_get(session_api_data, lambda x: x['authTypes'][session_api_data['protocols'][0]]),
'content_key_timeout': session_api_data.get('contentKeyTimeout'),
'service_id': 'nicovideo',
'service_user_id': session_api_data['service_user_id']
'service_user_id': session_api_data.get('serviceUserId')
},
'content_id': session_api_data['content_id'],
'content_id': session_api_data.get('contentId'),
'content_src_id_sets': [{
'content_src_ids': [{
'src_id_to_mux': {
'audio_src_ids': [audio_quality['id']],
'video_src_ids': [video_quality['id']],
'audio_src_ids': [audio_src_id],
'video_src_ids': [video_src_id],
}
}]
}],
@@ -229,52 +307,81 @@ class NiconicoIE(InfoExtractor):
'content_uri': '',
'keep_method': {
'heartbeat': {
'lifetime': session_api_data['heartbeat_lifetime']
'lifetime': session_api_data.get('heartbeatLifetime')
}
},
'priority': session_api_data['priority'],
'priority': session_api_data.get('priority'),
'protocol': {
'name': 'http',
'parameters': {
'http_parameters': {
'parameters': {
'http_output_download_parameters': {
'use_ssl': yesno(session_api_endpoint['is_ssl']),
'use_well_known_port': yesno(session_api_endpoint['is_well_known_port']),
}
}
}
'http_parameters': session_api_http_parameters
}
},
'recipe_id': session_api_data['recipe_id'],
'recipe_id': session_api_data.get('recipeId'),
'session_operation_auth': {
'session_operation_auth_by_signature': {
'signature': session_api_data['signature'],
'token': session_api_data['token'],
'signature': session_api_data.get('signature'),
'token': session_api_data.get('token'),
}
},
'timing_constraint': 'unlimited'
}
}).encode())
resolution = video_quality.get('resolution', {})
info_dict['url'] = session_response['data']['session']['content_uri']
info_dict['protocol'] = protocol
# get heartbeat info
heartbeat_info_dict = {
'url': session_api_endpoint['url'] + '/' + session_response['data']['session']['id'] + '?_format=json&_method=PUT',
'data': json.dumps(session_response['data']),
# interval, convert milliseconds to seconds, then halve to make a buffer.
'interval': float_or_none(session_api_data.get('heartbeatLifetime'), scale=3000),
'ping': ping
}
return info_dict, heartbeat_info_dict
def _extract_format_for_quality(self, api_data, video_id, audio_quality, video_quality):
def parse_format_id(id_code):
mobj = re.match(r'''(?x)
(?:archive_)?
(?:(?P<codec>[^_]+)_)?
(?:(?P<br>[\d]+)kbps_)?
(?:(?P<res>[\d+]+)p_)?
''', '%s_' % id_code)
return mobj.groupdict() if mobj else {}
protocol = 'niconico_dmc'
format_id = '-'.join(map(lambda s: remove_start(s['id'], 'archive_'), [video_quality, audio_quality]))
vdict = parse_format_id(video_quality['id'])
adict = parse_format_id(audio_quality['id'])
resolution = try_get(video_quality, lambda x: x['metadata']['resolution'], dict) or {'height': vdict.get('res')}
vbr = try_get(video_quality, lambda x: x['metadata']['bitrate'], float)
return {
'url': session_response['data']['session']['content_uri'],
'url': '%s:%s/%s/%s' % (protocol, video_id, video_quality['id'], audio_quality['id']),
'format_id': format_id,
'format_note': 'DMC %s' % try_get(video_quality, lambda x: x['metadata']['label'], compat_str),
'ext': 'mp4', # Session API are used in HTML5, which always serves mp4
'abr': float_or_none(audio_quality.get('bitrate'), 1000),
'vbr': float_or_none(video_quality.get('bitrate'), 1000),
'height': resolution.get('height'),
'width': resolution.get('width'),
'vcodec': vdict.get('codec'),
'acodec': adict.get('codec'),
'vbr': float_or_none(vbr, 1000) or float_or_none(vdict.get('br')),
'abr': float_or_none(audio_quality.get('bitrate'), 1000) or float_or_none(adict.get('br')),
'height': int_or_none(resolution.get('height', vdict.get('res'))),
'width': int_or_none(resolution.get('width')),
'quality': -2 if 'low' in format_id else -1, # Default quality value is -1
'protocol': protocol,
'http_headers': {
'Origin': 'https://www.nicovideo.jp',
'Referer': 'https://www.nicovideo.jp/watch/' + video_id,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
# Get video webpage. We are not actually interested in it for normal
# cases, but need the cookies in order to be able to download the
# info webpage
# Get video webpage for API data.
webpage, handle = self._download_webpage_handle(
'http://www.nicovideo.jp/watch/' + video_id, video_id)
if video_id.startswith('so'):
@@ -284,86 +391,136 @@ class NiconicoIE(InfoExtractor):
'data-api-data="([^"]+)"', webpage,
'API data', default='{}'), video_id)
def _format_id_from_url(video_url):
return 'economy' if video_real_url.endswith('low') else 'normal'
def get_video_info_web(items):
return dict_get(api_data['video'], items)
try:
video_real_url = api_data['video']['smileInfo']['url']
except KeyError: # Flash videos
# Get flv info
flv_info_webpage = self._download_webpage(
'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
video_id, 'Downloading flv info')
# Get video info
video_info_xml = self._download_xml(
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id,
video_id, note='Downloading video info page')
flv_info = compat_parse_qs(flv_info_webpage)
if 'url' not in flv_info:
if 'deleted' in flv_info:
raise ExtractorError('The video has been deleted.',
expected=True)
elif 'closed' in flv_info:
raise ExtractorError('Niconico videos now require logging in',
expected=True)
elif 'error' in flv_info:
raise ExtractorError('%s reports error: %s' % (
self.IE_NAME, flv_info['error'][0]), expected=True)
else:
raise ExtractorError('Unable to find video URL')
def get_video_info_xml(items):
if not isinstance(items, list):
items = [items]
for item in items:
ret = xpath_text(video_info_xml, './/' + item)
if ret:
return ret
video_info_xml = self._download_xml(
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id,
video_id, note='Downloading video info page')
if get_video_info_xml('error'):
error_code = get_video_info_xml('code')
def get_video_info(items):
if not isinstance(items, list):
items = [items]
for item in items:
ret = xpath_text(video_info_xml, './/' + item)
if ret:
return ret
if error_code == 'DELETED':
raise ExtractorError('The video has been deleted.',
expected=True)
elif error_code == 'NOT_FOUND':
raise ExtractorError('The video is not found.',
expected=True)
elif error_code == 'COMMUNITY':
self.to_screen('%s: The video is community members only.' % video_id)
else:
raise ExtractorError('%s reports error: %s' % (self.IE_NAME, error_code))
video_real_url = flv_info['url'][0]
# Start extracting video formats
formats = []
extension = get_video_info('movie_type')
if not extension:
extension = determine_ext(video_real_url)
# Get HTML5 videos info
quality_info = try_get(api_data, lambda x: x['media']['delivery']['movie'])
if not quality_info:
raise ExtractorError('The video can\'t be downloaded', expected=True)
formats = [{
'url': video_real_url,
'ext': extension,
'format_id': _format_id_from_url(video_real_url),
}]
else:
formats = []
for audio_quality in quality_info.get('audios') or {}:
for video_quality in quality_info.get('videos') or {}:
if not audio_quality.get('isAvailable') or not video_quality.get('isAvailable'):
continue
formats.append(self._extract_format_for_quality(
api_data, video_id, audio_quality, video_quality))
dmc_info = api_data['video'].get('dmcInfo')
if dmc_info: # "New" HTML5 videos
quality_info = dmc_info['quality']
for audio_quality in quality_info['audios']:
for video_quality in quality_info['videos']:
if not audio_quality['available'] or not video_quality['available']:
continue
formats.append(self._extract_format_for_quality(
api_data, video_id, audio_quality, video_quality))
# Get flv/swf info
timestamp = None
video_real_url = try_get(api_data, lambda x: x['video']['smileInfo']['url'])
if video_real_url:
is_economy = video_real_url.endswith('low')
self._sort_formats(formats)
else: # "Old" HTML5 videos
formats = [{
if is_economy:
self.report_warning('Site is currently in economy mode! You will only have access to lower quality streams')
# Invoking ffprobe to determine resolution
pp = FFmpegPostProcessor(self._downloader)
cookies = self._get_cookies('https://nicovideo.jp').output(header='', sep='; path=/; domain=nicovideo.jp;\n')
self.to_screen('%s: %s' % (video_id, 'Checking smile format with ffprobe'))
try:
metadata = pp.get_metadata_object(video_real_url, ['-cookies', cookies])
except PostProcessingError as err:
raise ExtractorError(err.msg, expected=True)
v_stream = a_stream = {}
# Some complex swf files doesn't have video stream (e.g. nm4809023)
for stream in metadata['streams']:
if stream['codec_type'] == 'video':
v_stream = stream
elif stream['codec_type'] == 'audio':
a_stream = stream
# Community restricted videos seem to have issues with the thumb API not returning anything at all
filesize = int(
(get_video_info_xml('size_high') if not is_economy else get_video_info_xml('size_low'))
or metadata['format']['size']
)
extension = (
get_video_info_xml('movie_type')
or 'mp4' if 'mp4' in metadata['format']['format_name'] else metadata['format']['format_name']
)
# 'creation_time' tag on video stream of re-encoded SMILEVIDEO mp4 files are '1970-01-01T00:00:00.000000Z'.
timestamp = (
parse_iso8601(get_video_info_web('first_retrieve'))
or unified_timestamp(get_video_info_web('postedDateTime'))
)
metadata_timestamp = (
parse_iso8601(try_get(v_stream, lambda x: x['tags']['creation_time']))
or timestamp if extension != 'mp4' else 0
)
# According to compconf, smile videos from pre-2017 are always better quality than their DMC counterparts
smile_threshold_timestamp = parse_iso8601('2016-12-08T00:00:00+09:00')
is_source = timestamp < smile_threshold_timestamp or metadata_timestamp > 0
# If movie file size is unstable, old server movie is not source movie.
if filesize > 1:
formats.append({
'url': video_real_url,
'ext': 'mp4',
'format_id': _format_id_from_url(video_real_url),
}]
'format_id': 'smile' if not is_economy else 'smile_low',
'format_note': 'SMILEVIDEO source' if not is_economy else 'SMILEVIDEO low quality',
'ext': extension,
'container': extension,
'vcodec': v_stream.get('codec_name'),
'acodec': a_stream.get('codec_name'),
# Some complex swf files doesn't have total bit rate metadata (e.g. nm6049209)
'tbr': int_or_none(metadata['format'].get('bit_rate'), scale=1000),
'vbr': int_or_none(v_stream.get('bit_rate'), scale=1000),
'abr': int_or_none(a_stream.get('bit_rate'), scale=1000),
'height': int_or_none(v_stream.get('height')),
'width': int_or_none(v_stream.get('width')),
'source_preference': 5 if not is_economy else -2,
'quality': 5 if is_source and not is_economy else None,
'filesize': filesize
})
def get_video_info(items):
return dict_get(api_data['video'], items)
self._sort_formats(formats)
# Start extracting information
title = get_video_info('title')
if not title:
title = self._og_search_title(webpage, default=None)
if not title:
title = self._html_search_regex(
title = (
get_video_info_xml('title') # prefer to get the untranslated original title
or get_video_info_web(['originalTitle', 'title'])
or self._og_search_title(webpage, default=None)
or self._html_search_regex(
r'<span[^>]+class="videoHeaderTitle"[^>]*>([^<]+)</span>',
webpage, 'video title')
webpage, 'video title'))
watch_api_data_string = self._html_search_regex(
r'<div[^>]+id="watchAPIDataContainer"[^>]+>([^<]+)</div>',
@@ -372,14 +529,15 @@ class NiconicoIE(InfoExtractor):
video_detail = watch_api_data.get('videoDetail', {})
thumbnail = (
get_video_info(['thumbnail_url', 'thumbnailURL'])
self._html_search_regex(r'<meta property="og:image" content="([^"]+)">', webpage, 'thumbnail data', default=None)
or dict_get( # choose highest from 720p to 240p
get_video_info_web('thumbnail'),
['ogp', 'player', 'largeUrl', 'middleUrl', 'url'])
or self._html_search_meta('image', webpage, 'thumbnail', default=None)
or video_detail.get('thumbnail'))
description = get_video_info('description')
description = get_video_info_web('description')
timestamp = (parse_iso8601(get_video_info('first_retrieve'))
or unified_timestamp(get_video_info('postedDateTime')))
if not timestamp:
match = self._html_search_meta('datePublished', webpage, 'date published', default=None)
if match:
@@ -388,19 +546,25 @@ class NiconicoIE(InfoExtractor):
timestamp = parse_iso8601(
video_detail['postedAt'].replace('/', '-'),
delimiter=' ', timezone=datetime.timedelta(hours=9))
timestamp = timestamp or try_get(api_data, lambda x: parse_iso8601(x['video']['registeredAt']))
view_count = int_or_none(get_video_info(['view_counter', 'viewCount']))
view_count = int_or_none(get_video_info_web(['view_counter', 'viewCount']))
if not view_count:
match = self._html_search_regex(
r'>Views: <strong[^>]*>([^<]+)</strong>',
webpage, 'view count', default=None)
if match:
view_count = int_or_none(match.replace(',', ''))
view_count = view_count or video_detail.get('viewCount')
view_count = (
view_count
or video_detail.get('viewCount')
or try_get(api_data, lambda x: x['video']['count']['view']))
comment_count = (
int_or_none(get_video_info_web('comment_num'))
or video_detail.get('commentCount')
or try_get(api_data, lambda x: x['video']['count']['comment']))
comment_count = (int_or_none(get_video_info('comment_num'))
or video_detail.get('commentCount')
or try_get(api_data, lambda x: x['thread']['commentCount']))
if not comment_count:
match = self._html_search_regex(
r'>Comments: <strong[^>]*>([^<]+)</strong>',
@@ -409,22 +573,41 @@ class NiconicoIE(InfoExtractor):
comment_count = int_or_none(match.replace(',', ''))
duration = (parse_duration(
get_video_info('length')
get_video_info_web('length')
or self._html_search_meta(
'video:duration', webpage, 'video duration', default=None))
or video_detail.get('length')
or get_video_info('duration'))
or get_video_info_web('duration'))
webpage_url = get_video_info('watch_url') or url
webpage_url = get_video_info_web('watch_url') or url
# for channel movie and community movie
channel_id = try_get(
api_data,
(lambda x: x['channel']['globalId'],
lambda x: x['community']['globalId']))
channel = try_get(
api_data,
(lambda x: x['channel']['name'],
lambda x: x['community']['name']))
# Note: cannot use api_data.get('owner', {}) because owner may be set to "null"
# in the JSON, which will cause None to be returned instead of {}.
owner = try_get(api_data, lambda x: x.get('owner'), dict) or {}
uploader_id = get_video_info(['ch_id', 'user_id']) or owner.get('id')
uploader = get_video_info(['ch_name', 'user_nickname']) or owner.get('nickname')
uploader_id = str_or_none(
get_video_info_web(['ch_id', 'user_id'])
or owner.get('id')
or channel_id
)
uploader = (
get_video_info_web(['ch_name', 'user_nickname'])
or owner.get('nickname')
or channel
)
return {
'id': video_id,
'_api_data': api_data,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
@@ -432,6 +615,8 @@ class NiconicoIE(InfoExtractor):
'uploader': uploader,
'timestamp': timestamp,
'uploader_id': uploader_id,
'channel': channel,
'channel_id': channel_id,
'view_count': view_count,
'comment_count': comment_count,
'duration': duration,
@@ -440,7 +625,7 @@ class NiconicoIE(InfoExtractor):
class NiconicoPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/(?:user/\d+/)?mylist/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/(?:user/\d+/|my/)?mylist/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.nicovideo.jp/mylist/27411728',
@@ -456,60 +641,185 @@ class NiconicoPlaylistIE(InfoExtractor):
'url': 'https://www.nicovideo.jp/user/805442/mylist/27411728',
'only_matching': True,
}]
_PAGE_SIZE = 100
def _call_api(self, list_id, resource, query):
return self._download_json(
'https://nvapi.nicovideo.jp/v2/mylists/' + list_id, list_id,
'Downloading %s JSON metatdata' % resource, query=query,
headers={'X-Frontend-Id': 6})['data']['mylist']
def _parse_owner(self, item):
owner = item.get('owner') or {}
if owner:
return {
'uploader': owner.get('name'),
'uploader_id': owner.get('id'),
}
return {}
def _fetch_page(self, list_id, page):
page += 1
items = self._call_api(list_id, 'page %d' % page, {
'page': page,
'pageSize': self._PAGE_SIZE,
})['items']
for item in items:
video = item.get('video') or {}
video_id = video.get('id')
if not video_id:
continue
count = video.get('count') or {}
get_count = lambda x: int_or_none(count.get(x))
info = {
'_type': 'url',
'id': video_id,
'title': video.get('title'),
'url': 'https://www.nicovideo.jp/watch/' + video_id,
'description': video.get('shortDescription'),
'duration': int_or_none(video.get('duration')),
'view_count': get_count('view'),
'comment_count': get_count('comment'),
'ie_key': NiconicoIE.ie_key(),
}
info.update(self._parse_owner(video))
yield info
_API_HEADERS = {
'X-Frontend-ID': '6',
'X-Frontend-Version': '0'
}
def _real_extract(self, url):
list_id = self._match_id(url)
mylist = self._call_api(list_id, 'list', {
'pageSize': 1,
})
entries = InAdvancePagedList(
functools.partial(self._fetch_page, list_id),
math.ceil(mylist['totalItemCount'] / self._PAGE_SIZE),
self._PAGE_SIZE)
result = self.playlist_result(
entries, list_id, mylist.get('name'), mylist.get('description'))
result.update(self._parse_owner(mylist))
return result
def get_page_data(pagenum, pagesize):
return self._download_json(
'http://nvapi.nicovideo.jp/v2/mylists/' + list_id, list_id,
query={'page': 1 + pagenum, 'pageSize': pagesize},
headers=self._API_HEADERS).get('data').get('mylist')
data = get_page_data(0, 1)
title = data.get('name')
description = data.get('description')
uploader = data.get('owner').get('name')
uploader_id = data.get('owner').get('id')
def pagefunc(pagenum):
data = get_page_data(pagenum, 25)
return ({
'_type': 'url',
'url': 'http://www.nicovideo.jp/watch/' + item.get('watchId'),
} for item in data.get('items'))
return {
'_type': 'playlist',
'id': list_id,
'title': title,
'description': description,
'uploader': uploader,
'uploader_id': uploader_id,
'entries': OnDemandPagedList(pagefunc, 25),
}
class NicovideoSearchBaseIE(InfoExtractor):
_MAX_RESULTS = float('inf')
def _entries(self, url, item_id, query=None, note='Downloading page %(page)s'):
query = query or {}
pages = [query['page']] if 'page' in query else itertools.count(1)
for page_num in pages:
query['page'] = str(page_num)
webpage = self._download_webpage(url, item_id, query=query, note=note % {'page': page_num})
results = re.findall(r'(?<=data-video-id=)["\']?(?P<videoid>.+?)(?=["\'])', webpage)
for item in results:
yield self.url_result('http://www.nicovideo.jp/watch/%s' % item, 'Niconico', item)
if not results:
break
def _get_n_results(self, query, n):
entries = self._entries(self._proto_relative_url('//www.nicovideo.jp/search/%s' % query), query)
if n < self._MAX_RESULTS:
entries = itertools.islice(entries, 0, n)
return self.playlist_result(entries, query, query)
class NicovideoSearchIE(NicovideoSearchBaseIE, SearchInfoExtractor):
IE_DESC = 'Nico video search'
IE_NAME = 'nicovideo:search'
_SEARCH_KEY = 'nicosearch'
def _search_results(self, query):
return self._entries(
self._proto_relative_url('//www.nicovideo.jp/search/%s' % query), query)
class NicovideoSearchURLIE(NicovideoSearchBaseIE):
IE_NAME = '%s_url' % NicovideoSearchIE.IE_NAME
IE_DESC = 'Nico video search URLs'
_VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/search/(?P<id>[^?#&]+)?'
_TESTS = [{
'url': 'http://www.nicovideo.jp/search/sm9',
'info_dict': {
'id': 'sm9',
'title': 'sm9'
},
'playlist_mincount': 40,
}, {
'url': 'https://www.nicovideo.jp/search/sm9?sort=h&order=d&end=2020-12-31&start=2020-01-01',
'info_dict': {
'id': 'sm9',
'title': 'sm9'
},
'playlist_count': 31,
}]
def _real_extract(self, url):
query = self._match_id(url)
return self.playlist_result(self._entries(url, query), query, query)
class NicovideoSearchDateIE(NicovideoSearchBaseIE, SearchInfoExtractor):
IE_DESC = 'Nico video search, newest first'
IE_NAME = '%s:date' % NicovideoSearchIE.IE_NAME
_SEARCH_KEY = 'nicosearchdate'
_TESTS = [{
'url': 'nicosearchdateall:a',
'info_dict': {
'id': 'a',
'title': 'a'
},
'playlist_mincount': 1610,
}]
_START_DATE = datetime.date(2007, 1, 1)
_RESULTS_PER_PAGE = 32
_MAX_PAGES = 50
def _entries(self, url, item_id, start_date=None, end_date=None):
start_date, end_date = start_date or self._START_DATE, end_date or datetime.datetime.now().date()
# If the last page has a full page of videos, we need to break down the query interval further
last_page_len = len(list(self._get_entries_for_date(
url, item_id, start_date, end_date, self._MAX_PAGES,
note='Checking number of videos from {0} to {1}'.format(start_date, end_date))))
if (last_page_len == self._RESULTS_PER_PAGE and start_date != end_date):
midpoint = start_date + ((end_date - start_date) // 2)
for entry in itertools.chain(
iter(self._entries(url, item_id, midpoint, end_date)),
iter(self._entries(url, item_id, start_date, midpoint))):
yield entry
else:
self.to_screen('{0}: Downloading results from {1} to {2}'.format(item_id, start_date, end_date))
for entry in iter(self._get_entries_for_date(
url, item_id, start_date, end_date, note=' Downloading page %(page)s')):
yield entry
def _get_entries_for_date(self, url, item_id, start_date, end_date=None, page_num=None, note=None):
query = {
'start': compat_str(start_date),
'end': compat_str(end_date or start_date),
'sort': 'f',
'order': 'd',
}
if page_num:
query['page'] = compat_str(page_num)
for entry in iter(super(NicovideoSearchDateIE, self)._entries(url, item_id, query=query, note=note)):
yield entry
class NiconicoUserIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/user/(?P<id>\d+)/?(?:$|[#?])'
_TEST = {
'url': 'https://www.nicovideo.jp/user/419948',
'info_dict': {
'id': '419948',
},
'playlist_mincount': 101,
}
_API_URL = "https://nvapi.nicovideo.jp/v1/users/%s/videos?sortKey=registeredAt&sortOrder=desc&pageSize=%s&page=%s"
_PAGE_SIZE = 100
_API_HEADERS = {
'X-Frontend-ID': '6',
'X-Frontend-Version': '0'
}
def _entries(self, list_id):
total_count = 1
count = page_num = 0
while count < total_count:
json_parsed = self._download_json(
self._API_URL % (list_id, self._PAGE_SIZE, page_num + 1), list_id,
headers=self._API_HEADERS,
note='Downloading JSON metadata%s' % (' page %d' % page_num if page_num else ''))
if not page_num:
total_count = int_or_none(json_parsed['data'].get('totalCount'))
for entry in json_parsed["data"]["items"]:
count += 1
yield self.url_result('https://www.nicovideo.jp/watch/%s' % entry['id'])
page_num += 1
def _real_extract(self, url):
list_id = self._match_id(url)
return self.playlist_result(self._entries(list_id), list_id)

3
youtube_dl/extractor/nrk.py
View File

@@ -60,8 +60,7 @@ class NRKBaseIE(InfoExtractor):
return self._download_json(
urljoin('https://psapi.nrk.no/', path),
video_id, note or 'Downloading %s JSON' % item,
fatal=fatal, query=query,
headers={'Accept-Encoding': 'gzip, deflate, br'})
fatal=fatal, query=query)
class NRKIE(NRKBaseIE):

120
youtube_dl/extractor/nuvid.py
View File

@@ -1,71 +1,113 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
parse_duration,
int_or_none,
try_get,
url_or_none,
)
import re
class NuvidIE(InfoExtractor):
_VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://m.nuvid.com/video/1310741/',
'md5': 'eab207b7ac4fccfb4e23c86201f11277',
_TESTS = [{
'url': 'https://www.nuvid.com/video/6513023/italian-babe',
'md5': '772d2f8288f3d3c5c45f7a41761c7844',
'info_dict': {
'id': '1310741',
'id': '6513023',
'ext': 'mp4',
'title': 'Horny babes show their awesome bodeis and',
'duration': 129,
'title': 'italian babe',
'format_id': '360p',
'duration': 321.0,
'age_limit': 18,
'thumbnail': r're:https?://.+\.jpg',
'thumbnails': list,
}
}
}, {
'url': 'https://m.nuvid.com/video/6523263',
'md5': 'ebd22ce8e47e1d9a4d0756a15c67da52',
'info_dict': {
'id': '6523263',
'ext': 'mp4',
'title': 'Slut brunette college student anal dorm',
'format_id': '720p',
'duration': 421.0,
'age_limit': 18,
'thumbnail': r're:https?://.+\.jpg',
'thumbnails': list,
}
}, {
'url': 'http://m.nuvid.com/video/6415801/',
'md5': '638d5ececb138d5753593f751ae3f697',
'info_dict': {
'id': '6415801',
'ext': 'mp4',
'title': 'My best friend wanted to fuck my wife for a long time',
'format_id': '720p',
'duration': 1882,
'age_limit': 18,
'thumbnail': r're:https?://.+\.jpg',
'thumbnails': list,
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
page_url = 'http://m.nuvid.com/video/%s' % video_id
qualities = {
'lq': '360p',
'hq': '720p',
}
json_url = 'https://www.nuvid.com/player_config_json/?vid={video_id}&aid=0&domain_id=0&embed=0&check_speed=0'.format(**locals())
video_data = self._download_json(
json_url, video_id, headers={
'Accept': 'application/json, text/javascript, */*; q = 0.01',
'Content-Type': 'application/x-www-form-urlencoded; charset=utf-8',
}) or {}
# nice to have, not required
webpage = self._download_webpage(
page_url, video_id, 'Downloading video page')
# When dwnld_speed exists and has a value larger than the MP4 file's
# bitrate, Nuvid returns the MP4 URL
# It's unit is 100bytes/millisecond, see mobile-nuvid-min.js for the algorithm
self._set_cookie('nuvid.com', 'dwnld_speed', '10.0')
mp4_webpage = self._download_webpage(
page_url, video_id, 'Downloading video page for MP4 format')
'http://m.nuvid.com/video/%s' % (video_id, ),
video_id, 'Downloading video page', fatal=False) or ''
title = (
try_get(video_data, lambda x: x['title'], compat_str)
or self._html_search_regex(
(r'''<span\s[^>]*?\btitle\s*=\s*(?P<q>"|'|\b)(?P<title>[^"]+)(?P=q)\s*>''',
r'''<div\s[^>]*?\bclass\s*=\s*(?P<q>"|'|\b)thumb-holder video(?P=q)>\s*<h5\b[^>]*>(?P<title>[^<]+)</h5''',
r'''<span\s[^>]*?\bclass\s*=\s*(?P<q>"|'|\b)title_thumb(?P=q)>(?P<title>[^<]+)</span'''),
webpage, 'title', group='title')).strip()
html5_video_re = r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']',
video_url = self._html_search_regex(html5_video_re, webpage, video_id)
mp4_video_url = self._html_search_regex(html5_video_re, mp4_webpage, video_id)
formats = [{
'url': video_url,
}]
if mp4_video_url != video_url:
formats.append({
'url': mp4_video_url,
})
'url': source,
'format_id': qualities.get(quality),
'height': int_or_none(qualities.get(quality)[:-1]),
} for quality, source in video_data.get('files').items() if source]
title = self._html_search_regex(
[r'<span title="([^"]+)">',
r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>',
r'<span[^>]+class="title_thumb">([^<]+)</span>'], webpage, 'title').strip()
self._check_formats(formats, video_id)
self._sort_formats(formats)
duration = parse_duration(video_data.get('duration') or video_data.get('duration_format'))
thumbnails = [
{
'url': thumb_url,
} for thumb_url in re.findall(r'<img src="([^"]+)" alt="" />', webpage)
{'url': thumb_url, }
for thumb_url in (
url_or_none(src) for src in re.findall(
r'<div\s+class\s*=\s*"video-tmb-wrap"\s*>\s*<img\s+src\s*=\s*"([^"]+)"\s*/>',
webpage))
]
thumbnail = thumbnails[0]['url'] if thumbnails else None
duration = parse_duration(self._html_search_regex(
[r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})',
r'<span[^>]+class="view_time">([^<]+)</span>'], webpage, 'duration', fatal=False))
return {
'id': video_id,
'formats': formats,
'title': title,
'thumbnail': url_or_none(video_data.get('poster')),
'thumbnails': thumbnails,
'thumbnail': thumbnail,
'duration': duration,
'age_limit': 18,
'formats': formats,
}

3
youtube_dl/extractor/openload.py
View File

@@ -16,6 +16,7 @@ from ..utils import (
ExtractorError,
get_exe_version,
is_outdated_version,
process_communicate_or_kill,
std_headers,
)
@@ -226,7 +227,7 @@ class PhantomJSwrapper(object):
self.exe, '--ssl-protocol=any',
self._TMP_FILES['script'].name
], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
out, err = p.communicate()
out, err = process_communicate_or_kill(p)
if p.returncode != 0:
raise ExtractorError(
'Executing JS failed\n:' + encodeArgument(err))

193
youtube_dl/extractor/peekvids.py Normal file
View File

@@ -0,0 +1,193 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
get_element_by_class,
int_or_none,
merge_dicts,
url_or_none,
)
class PeekVidsIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://(?:www\.)?peekvids\.com/
(?:(?:[^/?#]+/){2}|embed/?\?(?:[^#]*&)?v=)
(?P<id>[^/?&#]*)
'''
_TESTS = [{
'url': 'https://peekvids.com/pc/dane-jones-cute-redhead-with-perfect-tits-with-mini-vamp/BSyLMbN0YCd',
'md5': '2ff6a357a9717dc9dc9894b51307e9a2',
'info_dict': {
'id': '1262717',
'display_id': 'BSyLMbN0YCd',
'title': ' Dane Jones - Cute redhead with perfect tits with Mini Vamp',
'ext': 'mp4',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:0a61df3620de26c0af8963b1a730cd69',
'timestamp': 1642579329,
'upload_date': '20220119',
'duration': 416,
'view_count': int,
'age_limit': 18,
'uploader': 'SEXYhub.com',
'categories': list,
'tags': list,
},
}]
_DOMAIN = 'www.peekvids.com'
def _get_detail(self, html):
return get_element_by_class('detail-video-block', html)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id, expected_status=429)
if '>Rate Limit Exceeded' in webpage:
raise ExtractorError(
'[%s] %s: %s' % (self.IE_NAME, video_id, 'You are suspected as a bot. Wait, or pass the captcha test on the site and provide --cookies.'),
expected=True)
title = self._html_search_regex(r'(?s)<h1\b[^>]*>(.+?)</h1>', webpage, 'title')
display_id = video_id
video_id = self._search_regex(r'(?s)<video\b[^>]+\bdata-id\s*=\s*["\']?([\w-]+)', webpage, 'short video ID')
srcs = self._download_json(
'https://%s/v-alt/%s' % (self._DOMAIN, video_id), video_id,
note='Downloading list of source files')
formats = [{
'url': f_url,
'format_id': f_id,
'height': int_or_none(f_id),
} for f_url, f_id in (
(url_or_none(f_v), f_match.group(1))
for f_v, f_match in (
(v, re.match(r'^data-src(\d{3,})$', k))
for k, v in srcs.items() if v) if f_match)
if f_url
]
if not formats:
formats = [{'url': url} for url in srcs.values()]
self._sort_formats(formats)
info = self._search_json_ld(webpage, video_id, expected_type='VideoObject', default={})
info.pop('url', None)
# may not have found the thumbnail if it was in a list in the ld+json
info.setdefault('thumbnail', self._og_search_thumbnail(webpage))
detail = self._get_detail(webpage) or ''
info['description'] = self._html_search_regex(
r'(?s)(.+?)(?:%s\s*<|<ul\b)' % (re.escape(info.get('description', '')), ),
detail, 'description', default=None) or None
info['title'] = re.sub(r'\s*[,-][^,-]+$', '', info.get('title') or title) or self._generic_title(url)
def cat_tags(name, html):
l = self._html_search_regex(
r'(?s)<span\b[^>]*>\s*%s\s*:\s*</span>(.+?)</li>' % (re.escape(name), ),
html, name, default='')
return [x for x in re.split(r'\s+', l) if x]
return merge_dicts({
'id': video_id,
'display_id': display_id,
'age_limit': 18,
'formats': formats,
'categories': cat_tags('Categories', detail),
'tags': cat_tags('Tags', detail),
'uploader': self._html_search_regex(r'[Uu]ploaded\s+by\s(.+?)"', webpage, 'uploader', default=None),
}, info)
class PlayVidsIE(PeekVidsIE):
_VALID_URL = r'https?://(?:www\.)?playvids\.com/(?:embed/|\w\w?/)?(?P<id>[^/?#]*)'
_TESTS = [{
'url': 'https://www.playvids.com/U3pBrYhsjXM/pc/dane-jones-cute-redhead-with-perfect-tits-with-mini-vamp',
'md5': '2f12e50213dd65f142175da633c4564c',
'info_dict': {
'id': '1978030',
'display_id': 'U3pBrYhsjXM',
'title': ' Dane Jones - Cute redhead with perfect tits with Mini Vamp',
'ext': 'mp4',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:0a61df3620de26c0af8963b1a730cd69',
'timestamp': 1640435839,
'upload_date': '20211225',
'duration': 416,
'view_count': int,
'age_limit': 18,
'uploader': 'SEXYhub.com',
'categories': list,
'tags': list,
},
}, {
'url': 'https://www.playvids.com/es/U3pBrYhsjXM/pc/dane-jones-cute-redhead-with-perfect-tits-with-mini-vamp',
'only_matching': True,
}, {
'url': 'https://www.playvids.com/embed/U3pBrYhsjXM',
'only_matching': True,
}, {
'url': 'https://www.playvids.com/bKmGLe3IwjZ/sv/brazzers-800-phone-sex-madison-ivy-always-on-the-line',
'md5': 'e783986e596cafbf46411a174ab42ba6',
'info_dict': {
'id': '762385',
'display_id': 'bKmGLe3IwjZ',
'ext': 'mp4',
'title': 'Brazzers - 1 800 Phone Sex: Madison Ivy Always On The Line 6',
'description': 'md5:bdcd2db2b8ad85831a491d7c8605dcef',
'timestamp': 1516958544,
'upload_date': '20180126',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 480,
'uploader': 'Brazzers',
'age_limit': 18,
'view_count': int,
'age_limit': 18,
'categories': list,
'tags': list,
},
}, {
'url': 'https://www.playvids.com/v/47iUho33toY',
'md5': 'b056b5049d34b648c1e86497cf4febce',
'info_dict': {
'id': '700621',
'display_id': '47iUho33toY',
'ext': 'mp4',
'title': 'KATEE OWEN STRIPTIASE IN SEXY RED LINGERIE',
'description': None,
'timestamp': 1507052209,
'upload_date': '20171003',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 332,
'uploader': 'Cacerenele',
'age_limit': 18,
'view_count': int,
'categories': list,
'tags': list,
}
}, {
'url': 'https://www.playvids.com/z3_7iwWCmqt/sexy-teen-filipina-striptease-beautiful-pinay-bargirl-strips-and-dances',
'md5': 'efa09be9f031314b7b7e3bc6510cd0df',
'info_dict': {
'id': '1523518',
'display_id': 'z3_7iwWCmqt',
'ext': 'mp4',
'title': 'SEXY TEEN FILIPINA STRIPTEASE - Beautiful Pinay Bargirl Strips and Dances',
'description': None,
'timestamp': 1607470323,
'upload_date': '20201208',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 593,
'uploader': 'yorours',
'age_limit': 18,
'view_count': int,
'categories': list,
'tags': list,
},
}]
_DOMAIN = 'www.playvids.com'
def _get_detail(self, html):
return get_element_by_class('detail-block', html)

105
youtube_dl/extractor/pr0gramm.py Normal file
View File

@@ -0,0 +1,105 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
import re
from ..utils import (
merge_dicts,
)
class Pr0grammStaticIE(InfoExtractor):
# Possible urls:
# https://pr0gramm.com/static/5466437
_VALID_URL = r'https?://pr0gramm\.com/static/(?P<id>[0-9]+)'
_TEST = {
'url': 'https://pr0gramm.com/static/5466437',
'md5': '52fa540d70d3edc286846f8ca85938aa',
'info_dict': {
'id': '5466437',
'ext': 'mp4',
'title': 'pr0gramm-5466437 by g11st',
'uploader': 'g11st',
'upload_date': '20221221',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
# Fetch media sources
entries = self._parse_html5_media_entries(url, webpage, video_id)
media_info = entries[0]
# this raises if there are no formats
self._sort_formats(media_info.get('formats') or [])
# Fetch author
uploader = self._html_search_regex(r'by\W+([\w-]+)\W+', webpage, 'uploader')
# Fetch approx upload timestamp from filename
# Have None-defaults in case the extraction fails
uploadDay = None
uploadMon = None
uploadYear = None
uploadTimestr = None
# (//img.pr0gramm.com/2022/12/21/62ae8aa5e2da0ebf.mp4)
m = re.search(r'//img\.pr0gramm\.com/(?P<year>[\d]+)/(?P<mon>[\d]+)/(?P<day>[\d]+)/\w+\.\w{,4}', webpage)
if (m):
# Up to a day of accuracy should suffice...
uploadDay = m.groupdict().get('day')
uploadMon = m.groupdict().get('mon')
uploadYear = m.groupdict().get('year')
uploadTimestr = uploadYear + uploadMon + uploadDay
return merge_dicts({
'id': video_id,
'title': 'pr0gramm-%s%s' % (video_id, (' by ' + uploader) if uploader else ''),
'uploader': uploader,
'upload_date': uploadTimestr
}, media_info)
# This extractor is for the primary url (used for sharing, and appears in the
# location bar) Since this page loads the DOM via JS, yt-dl can't find any
# video information here. So let's redirect to a compatibility version of
# the site, which does contain the <video>-element by itself, without requiring
# js to be ran.
class Pr0grammIE(InfoExtractor):
# Possible urls:
# https://pr0gramm.com/new/546637
# https://pr0gramm.com/new/video/546637
# https://pr0gramm.com/top/546637
# https://pr0gramm.com/top/video/546637
# https://pr0gramm.com/user/g11st/uploads/5466437
# https://pr0gramm.com/user/froschler/dafur-ist-man-hier/5091290
# https://pr0gramm.com/user/froschler/reinziehen-1elf/5232030
# https://pr0gramm.com/user/froschler/1elf/5232030
# https://pr0gramm.com/new/5495710:comment62621020 <- this is not the id!
# https://pr0gramm.com/top/fruher war alles damals/5498175
_VALID_URL = r'https?:\/\/pr0gramm\.com\/(?!static/\d+).+?\/(?P<id>[\d]+)(:|$)'
_TEST = {
'url': 'https://pr0gramm.com/new/video/5466437',
'info_dict': {
'id': '5466437',
'ext': 'mp4',
'title': 'pr0gramm-5466437 by g11st',
'uploader': 'g11st',
'upload_date': '20221221',
}
}
def _generic_title():
return "oof"
def _real_extract(self, url):
video_id = self._match_id(url)
return self.url_result(
'https://pr0gramm.com/static/' + video_id,
video_id=video_id,
ie=Pr0grammStaticIE.ie_key())

122
youtube_dl/extractor/rai.py
View File

@@ -5,15 +5,16 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
compat_str,
compat_urlparse,
)
from ..utils import (
ExtractorError,
determine_ext,
ExtractorError,
find_xpath_attr,
fix_xml_ampersands,
GeoRestrictedError,
HEADRequest,
int_or_none,
parse_duration,
remove_start,
@@ -96,12 +97,100 @@ class RaiBaseIE(InfoExtractor):
if not formats and geoprotection is True:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
formats.extend(self._create_http_urls(relinker_url, formats))
return dict((k, v) for k, v in {
'is_live': is_live,
'duration': duration,
'formats': formats,
}.items() if v is not None)
def _create_http_urls(self, relinker_url, fmts):
_RELINKER_REG = r'https?://(?P<host>[^/]+?)/(?:i/)?(?P<extra>[^/]+?)/(?P<path>.+?)/(?P<id>\w+)(?:_(?P<quality>[\d\,]+))?(?:\.mp4|/playlist\.m3u8).+?'
_MP4_TMPL = '%s&overrideUserAgentRule=mp4-%s'
_QUALITY = {
# tbr: w, h
'250': [352, 198],
'400': [512, 288],
'700': [512, 288],
'800': [700, 394],
'1200': [736, 414],
'1800': [1024, 576],
'2400': [1280, 720],
'3200': [1440, 810],
'3600': [1440, 810],
'5000': [1920, 1080],
'10000': [1920, 1080],
}
def test_url(url):
resp = self._request_webpage(
HEADRequest(url), None, headers={'User-Agent': 'Rai'},
fatal=False, errnote=False, note=False)
if resp is False:
return False
if resp.code == 200:
return False if resp.url == url else resp.url
return None
def get_format_info(tbr):
import math
br = int_or_none(tbr)
if len(fmts) == 1 and not br:
br = fmts[0].get('tbr')
if br > 300:
tbr = compat_str(math.floor(br / 100) * 100)
else:
tbr = '250'
# try extracting info from available m3u8 formats
format_copy = None
for f in fmts:
if f.get('tbr'):
br_limit = math.floor(br / 100)
if br_limit - 1 <= math.floor(f['tbr'] / 100) <= br_limit + 1:
format_copy = f.copy()
return {
'width': format_copy.get('width'),
'height': format_copy.get('height'),
'tbr': format_copy.get('tbr'),
'vcodec': format_copy.get('vcodec'),
'acodec': format_copy.get('acodec'),
'fps': format_copy.get('fps'),
'format_id': 'https-%s' % tbr,
} if format_copy else {
'width': _QUALITY[tbr][0],
'height': _QUALITY[tbr][1],
'format_id': 'https-%s' % tbr,
'tbr': int(tbr),
}
loc = test_url(_MP4_TMPL % (relinker_url, '*'))
if not isinstance(loc, compat_str):
return []
mobj = re.match(
_RELINKER_REG,
test_url(relinker_url) or '')
if not mobj:
return []
available_qualities = mobj.group('quality').split(',') if mobj.group('quality') else ['*']
available_qualities = [i for i in available_qualities if i]
formats = []
for q in available_qualities:
fmt = {
'url': _MP4_TMPL % (relinker_url, q),
'protocol': 'https',
'ext': 'mp4',
}
fmt.update(get_format_info(q))
formats.append(fmt)
return formats
@staticmethod
def _extract_subtitles(url, video_data):
STL_EXT = 'stl'
@@ -151,6 +240,22 @@ class RaiPlayIE(RaiBaseIE):
'params': {
'skip_download': True,
},
}, {
# 1080p direct mp4 url
'url': 'https://www.raiplay.it/video/2021/03/Leonardo-S1E1-b5703b02-82ee-475a-85b6-c9e4a8adf642.html',
'md5': '2e501e8651d72f05ffe8f5d286ad560b',
'info_dict': {
'id': 'b5703b02-82ee-475a-85b6-c9e4a8adf642',
'ext': 'mp4',
'title': 'Leonardo - S1E1',
'alt_title': 'St 1 Ep 1 - Episodio 1',
'description': 'md5:f5360cd267d2de146e4e3879a5a47d31',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Rai 1',
'duration': 3229,
'series': 'Leonardo',
'season': 'Season 1',
},
}, {
'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
'only_matching': True,
@@ -158,6 +263,10 @@ class RaiPlayIE(RaiBaseIE):
# subtitles at 'subtitlesArray' key (see #27698)
'url': 'https://www.raiplay.it/video/2020/12/Report---04-01-2021-2e90f1de-8eee-4de4-ac0e-78d21db5b600.html',
'only_matching': True,
}, {
# DRM protected
'url': 'https://www.raiplay.it/video/2020/09/Lo-straordinario-mondo-di-Zoey-S1E1-Lo-straordinario-potere-di-Zoey-ed493918-1d32-44b7-8454-862e473d00ff.html',
'only_matching': True,
}]
def _real_extract(self, url):
@@ -166,6 +275,13 @@ class RaiPlayIE(RaiBaseIE):
media = self._download_json(
base + '.json', video_id, 'Downloading video JSON')
if try_get(
media,
(lambda x: x['rights_management']['rights']['drm'],
lambda x: x['program_info']['rights_management']['rights']['drm']),
dict):
raise ExtractorError('This video is DRM protected.', expected=True)
title = media['name']
video = media['video']
@@ -307,7 +423,7 @@ class RaiIE(RaiBaseIE):
}, {
# with ContentItem in og:url
'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html',
'md5': '6865dd00cf0bbf5772fdd89d59bd768a',
'md5': '06345bd97c932f19ffb129973d07a020',
'info_dict': {
'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
'ext': 'mp4',

97
youtube_dl/extractor/rbgtum.py Normal file
View File

@@ -0,0 +1,97 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class RbgTumIE(InfoExtractor):
_VALID_URL = r'https://live\.rbg\.tum\.de/w/(?P<id>.+)'
_TESTS = [{
# Combined view
'url': 'https://live.rbg.tum.de/w/cpp/22128',
'md5': '53a5e7b3e07128e33bbf36687fe1c08f',
'info_dict': {
'id': 'cpp/22128',
'ext': 'mp4',
'title': 'Lecture: October 18. 2022',
'series': 'Concepts of C++ programming (IN2377)',
}
}, {
# Presentation only
'url': 'https://live.rbg.tum.de/w/I2DL/12349/PRES',
'md5': '36c584272179f3e56b0db5d880639cba',
'info_dict': {
'id': 'I2DL/12349/PRES',
'ext': 'mp4',
'title': 'Lecture 3: Introduction to Neural Networks',
'series': 'Introduction to Deep Learning (IN2346)',
}
}, {
# Camera only
'url': 'https://live.rbg.tum.de/w/fvv-info/16130/CAM',
'md5': 'e04189d92ff2f56aedf5cede65d37aad',
'info_dict': {
'id': 'fvv-info/16130/CAM',
'ext': 'mp4',
'title': 'Fachschaftsvollversammlung',
'series': 'Fachschaftsvollversammlung Informatik',
}
}, ]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
m3u8 = self._html_search_regex(r'(https://.+?\.m3u8)', webpage, 'm3u8')
lecture_title = self._html_search_regex(r'(?si)<h1.*?>(.*)</h1>', webpage, 'title')
lecture_series_title = self._html_search_regex(
r'(?s)<title\b[^>]*>\s*(?:TUM-Live\s\|\s?)?([^:]+):?.*?</title>', webpage, 'series')
formats = self._extract_m3u8_formats(m3u8, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
self._sort_formats(formats)
return {
'id': video_id,
'title': lecture_title,
'series': lecture_series_title,
'formats': formats,
}
class RbgTumCourseIE(InfoExtractor):
_VALID_URL = r'https://live\.rbg\.tum\.de/course/(?P<id>.+)'
_TESTS = [{
'url': 'https://live.rbg.tum.de/course/2022/S/fpv',
'info_dict': {
'title': 'Funktionale Programmierung und Verifikation (IN0003)',
'id': '2022/S/fpv',
},
'params': {
'noplaylist': False,
},
'playlist_count': 13,
}, {
'url': 'https://live.rbg.tum.de/course/2022/W/set',
'info_dict': {
'title': 'SET FSMPIC',
'id': '2022/W/set',
},
'params': {
'noplaylist': False,
},
'playlist_count': 6,
}, ]
def _real_extract(self, url):
course_id = self._match_id(url)
webpage = self._download_webpage(url, course_id)
lecture_series_title = self._html_search_regex(r'(?si)<h1.*?>(.*)</h1>', webpage, 'title')
lecture_urls = []
for lecture_url in re.findall(r'(?i)href="/w/(.+)(?<!/cam)(?<!/pres)(?<!/chat)"', webpage):
lecture_urls.append(self.url_result('https://live.rbg.tum.de/w/' + lecture_url, ie=RbgTumIE.ie_key()))
return self.playlist_result(lecture_urls, course_id, lecture_series_title)

5
youtube_dl/extractor/rutv.py
View File

@@ -6,7 +6,8 @@ import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none
int_or_none,
str_to_int
)
@@ -179,7 +180,7 @@ class RUTVIE(InfoExtractor):
'player_url': 'http://player.rutv.ru/flash3v/osmf.swf?i=22',
'rtmp_live': True,
'ext': 'flv',
'vbr': int(quality),
'vbr': str_to_int(quality),
'preference': preference,
}
elif transport == 'm3u8':

171
youtube_dl/extractor/streamcz.py
View File

@@ -1,105 +1,126 @@
# coding: utf-8
from __future__ import unicode_literals
import hashlib
import time
import json
import re
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
sanitized_Request,
merge_dicts,
parse_codecs,
urljoin,
)
def _get_api_key(api_path):
if api_path.endswith('?'):
api_path = api_path[:-1]
api_key = 'fb5f58a820353bd7095de526253c14fd'
a = '{0:}{1:}{2:}'.format(api_key, api_path, int(round(time.time() / 24 / 3600)))
return hashlib.md5(a.encode('ascii')).hexdigest()
class StreamCZIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<id>[0-9]+)'
_API_URL = 'http://www.stream.cz/API'
_VALID_URL = r'https?://(?:www\.)?(?:stream|televizeseznam)\.cz/[^?#]+/(?P<display_id>[^?#]+)-(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti',
'md5': '934bb6a6d220d99c010783c9719960d5',
'url': 'https://www.televizeseznam.cz/video/lajna/buh-57953890',
'md5': '40c41ade1464a390a0b447e333df4239',
'info_dict': {
'id': '765767',
'id': '57953890',
'ext': 'mp4',
'title': 'Peklo na talíři: Éčka pro děti',
'description': 'Taška s grónskou pomazánkou a další pekelnosti ZDE',
'thumbnail': 're:^http://im.stream.cz/episode/52961d7e19d423f8f06f0100',
'duration': 256,
},
'title': 'Bůh',
'display_id': 'buh',
'description': 'md5:8f5f09b9b7bc67df910486cdd88f7165',
'duration': 1369.6,
'view_count': int,
}
}, {
'url': 'http://www.stream.cz/blanik/10002447-tri-roky-pro-mazanka',
'md5': '849a88c1e1ca47d41403c2ba5e59e261',
'url': 'https://www.stream.cz/kdo-to-mluvi/kdo-to-mluvi-velke-odhaleni-prinasi-novy-porad-uz-od-25-srpna-64087937',
'md5': '41fd358000086a1ccdb068c77809b158',
'info_dict': {
'id': '10002447',
'id': '64087937',
'ext': 'mp4',
'title': 'Kancelář Blaník: Tři roky pro Mazánka',
'description': 'md5:3862a00ba7bf0b3e44806b544032c859',
'thumbnail': 're:^http://im.stream.cz/episode/537f838c50c11f8d21320000',
'duration': 368,
},
'title': 'Kdo to mluví? Velké odhalení přináší nový pořad už od 25. srpna',
'display_id': 'kdo-to-mluvi-velke-odhaleni-prinasi-novy-porad-uz-od-25-srpna',
'description': 'md5:97a811000a6460266029d6c1c2ebcd59',
'duration': 50.2,
'view_count': int,
}
}, {
'url': 'https://www.stream.cz/tajemno/znicehonic-jim-skrz-strechu-prolitnul-zahadny-predmet-badatele-vse-objasnili-64147267',
'md5': '3ee4d0be040e8f4a543e67e509d55e3f',
'info_dict': {
'id': '64147267',
'ext': 'mp4',
'title': 'Zničehonic jim skrz střechu prolítnul záhadný předmět. Badatelé vše objasnili',
'display_id': 'znicehonic-jim-skrz-strechu-prolitnul-zahadny-predmet-badatele-vse-objasnili',
'description': 'md5:4b8ada6718d34bb011c4e04ca4bc19bf',
'duration': 442.84,
'view_count': int,
}
}]
def _extract_formats(self, spl_url, video):
for ext, pref, streams in (
('ts', -1, video.get('http_stream', {}).get('qualities', {})),
('mp4', 1, video.get('mp4'))):
for format_id, stream in streams.items():
if not stream.get('url'):
continue
yield merge_dicts({
'format_id': '-'.join((format_id, ext)),
'ext': ext,
'source_preference': pref,
'url': urljoin(spl_url, stream['url']),
'tbr': float_or_none(stream.get('bandwidth'), scale=1000),
'duration': float_or_none(stream.get('duration'), scale=1000),
'width': stream.get('resolution', 2 * [0])[0] or None,
'height': stream.get('resolution', 2 * [0])[1] or int_or_none(format_id.replace('p', '')),
}, parse_codecs(stream.get('codec')))
def _real_extract(self, url):
video_id = self._match_id(url)
api_path = '/episode/%s' % video_id
display_id, video_id = re.match(self._VALID_URL, url).groups()
req = sanitized_Request(self._API_URL + api_path)
req.add_header('Api-Password', _get_api_key(api_path))
data = self._download_json(req, video_id)
data = self._download_json(
'https://www.televizeseznam.cz/api/graphql', video_id, 'Downloading GraphQL result',
data=json.dumps({
'variables': {'urlName': video_id},
'query': '''
query LoadEpisode($urlName : String){ episode(urlName: $urlName){ ...VideoDetailFragmentOnEpisode } }
fragment VideoDetailFragmentOnEpisode on Episode {
id
spl
urlName
name
perex
duration
views
}'''
}).encode('utf-8'),
headers={'Content-Type': 'application/json;charset=UTF-8'}
)['data']['episode']
formats = []
for quality, video in enumerate(data['video_qualities']):
for f in video['formats']:
typ = f['type'].partition('/')[2]
qlabel = video.get('quality_label')
formats.append({
'format_note': '%s-%s' % (qlabel, typ) if qlabel else typ,
'format_id': '%s-%s' % (typ, f['quality']),
'url': f['source'],
'height': int_or_none(f['quality'].rstrip('p')),
'quality': quality,
})
self._sort_formats(formats)
image = data.get('image')
if image:
thumbnail = self._proto_relative_url(
image.replace('{width}', '1240').replace('{height}', '697'),
scheme='http:',
)
else:
thumbnail = None
stream = data.get('_embedded', {}).get('stream:show', {}).get('name')
if stream:
title = '%s: %s' % (stream, data['name'])
else:
title = data['name']
spl_url = data['spl'] + 'spl2,3'
metadata = self._download_json(spl_url, video_id, 'Downloading playlist')
if 'Location' in metadata and 'data' not in metadata:
spl_url = metadata['Location']
metadata = self._download_json(spl_url, video_id, 'Downloading redirected playlist')
video = metadata['data']
subtitles = {}
srt_url = data.get('subtitles_srt')
if srt_url:
subtitles['cs'] = [{
'ext': 'srt',
'url': srt_url,
}]
for subs in video.get('subtitles', {}).values():
if not subs.get('language'):
continue
for ext, sub_url in subs.get('urls').items():
subtitles.setdefault(subs['language'], []).append({
'ext': ext,
'url': urljoin(spl_url, sub_url)
})
formats = list(self._extract_formats(spl_url, video))
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
'description': data.get('web_site_text'),
'duration': int_or_none(data.get('duration')),
'display_id': display_id,
'title': data.get('name'),
'description': data.get('perex'),
'duration': float_or_none(data.get('duration')),
'view_count': int_or_none(data.get('views')),
'formats': formats,
'subtitles': subtitles,
}

61
youtube_dl/extractor/streamsb.py Normal file
View File

@@ -0,0 +1,61 @@
# coding: utf-8
from __future__ import unicode_literals
import binascii
import random
import re
import string
from .common import InfoExtractor
from ..utils import urljoin, url_basename
def to_ascii_hex(str1):
return binascii.hexlify(str1.encode('utf-8')).decode('ascii')
def generate_random_string(length):
return ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(length))
class StreamsbIE(InfoExtractor):
_DOMAINS = ('viewsb.com', )
_VALID_URL = r'https://(?P<domain>%s)/(?P<id>.+)' % '|'.join(_DOMAINS)
_TEST = {
'url': 'https://viewsb.com/dxfvlu4qanjx',
'md5': '488d111a63415369bf90ea83adc8a325',
'info_dict': {
'id': 'dxfvlu4qanjx',
'ext': 'mp4',
'title': 'Sintel'
}
}
def _real_extract(self, url):
domain, video_id = re.match(self._VALID_URL, url).group('domain', 'id')
webpage = self._download_webpage(url, video_id)
iframe_rel_url = self._search_regex(r'''(?i)<iframe\b[^>]+\bsrc\s*=\s*('|")(?P<path>/.*\.html)\1''', webpage, 'iframe', group='path')
iframe_url = urljoin('https://' + domain, iframe_rel_url)
iframe_data = self._download_webpage(iframe_url, video_id)
app_version = self._search_regex(r'''<script\b[^>]+\bsrc\s*=\s*["|'].*/app\.min\.(\d+)\.js''', iframe_data, 'app version', fatal=False) or '50'
video_code = url_basename(iframe_url).rsplit('.')[0]
length = 12
req = '||'.join((generate_random_string(length), video_code, generate_random_string(length), 'streamsb'))
ereq = 'https://{0}/sources{1}/{2}'.format(domain, app_version, to_ascii_hex(req))
video_data = self._download_webpage(ereq, video_id, headers={
'Referer': iframe_url,
'watchsb': 'sbstream',
})
player_data = self._parse_json(video_data, video_id)
title = player_data['stream_data']['title']
formats = self._extract_m3u8_formats(player_data['stream_data']['file'], video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
return {
'id': video_id,
'formats': formats,
'title': title,
}

86
youtube_dl/extractor/tele5.py
View File

@@ -1,19 +1,16 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .jwplatform import JWPlatformIE
from .nexx import NexxIE
from ..compat import compat_urlparse
from ..utils import (
NO_DEFAULT,
smuggle_url,
ExtractorError,
extract_attributes,
)
from .dplay import DPlayIE
class Tele5IE(InfoExtractor):
class Tele5IE(DPlayIE):
_VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_GEO_COUNTRIES = ['DE']
_TESTS = [{
@@ -28,6 +25,7 @@ class Tele5IE(InfoExtractor):
'params': {
'skip_download': True,
},
'skip': 'No longer available: "404 Seite nicht gefunden"',
}, {
# jwplatform, nexx unavailable
'url': 'https://www.tele5.de/filme/ghoul-das-geheimnis-des-friedhofmonsters/',
@@ -42,7 +40,20 @@ class Tele5IE(InfoExtractor):
'params': {
'skip_download': True,
},
'add_ie': [JWPlatformIE.ie_key()],
'skip': 'No longer available, redirects to Filme page',
}, {
'url': 'https://tele5.de/mediathek/angel-of-mine/',
'info_dict': {
'id': '1252360',
'ext': 'mp4',
'upload_date': '20220109',
'timestamp': 1641762000,
'title': 'Angel of Mine',
'description': 'md5:a72546a175e1286eb3251843a52d1ad7',
},
'params': {
'format': 'bestvideo',
},
}, {
'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
'only_matching': True,
@@ -64,45 +75,18 @@ class Tele5IE(InfoExtractor):
}]
def _real_extract(self, url):
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0]
NEXX_ID_RE = r'\d{6,}'
JWPLATFORM_ID_RE = r'[a-zA-Z0-9]{8}'
def nexx_result(nexx_id):
return self.url_result(
'https://api.nexx.cloud/v3/759/videos/byid/%s' % nexx_id,
ie=NexxIE.ie_key(), video_id=nexx_id)
nexx_id = jwplatform_id = None
if video_id:
if re.match(NEXX_ID_RE, video_id):
return nexx_result(video_id)
elif re.match(JWPLATFORM_ID_RE, video_id):
jwplatform_id = video_id
if not nexx_id:
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
def extract_id(pattern, name, default=NO_DEFAULT):
return self._html_search_regex(
(r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](%s)' % pattern,
r'\s+id\s*=\s*["\']player_(%s)' % pattern,
r'\bdata-id\s*=\s*["\'](%s)' % pattern), webpage, name,
default=default)
nexx_id = extract_id(NEXX_ID_RE, 'nexx id', default=None)
if nexx_id:
return nexx_result(nexx_id)
if not jwplatform_id:
jwplatform_id = extract_id(JWPLATFORM_ID_RE, 'jwplatform id')
return self.url_result(
smuggle_url(
'jwplatform:%s' % jwplatform_id,
{'geo_countries': self._GEO_COUNTRIES}),
ie=JWPlatformIE.ie_key(), video_id=jwplatform_id)
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
player_element = self._search_regex(r'(<hyoga-player\b[^>]+?>)', webpage, 'video player')
player_info = extract_attributes(player_element)
asset_id, country, realm = (player_info[x] for x in ('assetid', 'locale', 'realm', ))
endpoint = compat_urlparse.urlparse(player_info['endpoint']).hostname
source_type = player_info.get('sourcetype')
if source_type:
endpoint = '%s-%s' % (source_type, endpoint)
try:
return self._get_disco_api_info(url, asset_id, endpoint, realm, country)
except ExtractorError as e:
if getattr(e, 'message', '') == 'Missing deviceId in context':
raise ExtractorError('DRM protected', cause=e, expected=True)
raise

4
youtube_dl/extractor/telegraaf.py
View File

@@ -34,7 +34,9 @@ class TelegraafIE(InfoExtractor):
article_id = self._match_id(url)
video_id = self._download_json(
'https://www.telegraaf.nl/graphql', article_id, query={
'https://app.telegraaf.nl/graphql', article_id,
headers={'User-Agent': 'De Telegraaf/6.8.11 (Android 11; en_US)'},
query={
'query': '''{
article(uid: %s) {
videos {

218
youtube_dl/extractor/thisvid.py Normal file
View File

@@ -0,0 +1,218 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
)
from ..utils import (
clean_html,
get_element_by_class,
int_or_none,
merge_dicts,
url_or_none,
urljoin,
)
class ThisVidIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?thisvid\.com/(?P<type>videos|embed)/(?P<id>[A-Za-z0-9-]+)'
_TESTS = [{
'url': 'https://thisvid.com/videos/sitting-on-ball-tight-jeans/',
'md5': '839becb572995687e11a69dc4358a386',
'info_dict': {
'id': '3533241',
'ext': 'mp4',
'title': 'Sitting on ball tight jeans',
'description': 'md5:372353bb995883d1b65fddf507489acd',
'thumbnail': r're:https?://\w+\.thisvid\.com/(?:[^/]+/)+3533241/preview\.jpg',
'uploader_id': '150629',
'uploader': 'jeanslevisjeans',
'age_limit': 18,
}
}, {
'url': 'https://thisvid.com/embed/3533241/',
'md5': '839becb572995687e11a69dc4358a386',
'info_dict': {
'id': '3533241',
'ext': 'mp4',
'title': 'Sitting on ball tight jeans',
'thumbnail': r're:https?://\w+\.thisvid\.com/(?:[^/]+/)+3533241/preview\.jpg',
'uploader_id': '150629',
'uploader': 'jeanslevisjeans',
'age_limit': 18,
}
}]
def _real_extract(self, url):
main_id, type_ = re.match(self._VALID_URL, url).group('id', 'type')
webpage = self._download_webpage(url, main_id)
title = self._html_search_regex(
r'<title\b[^>]*?>(?:Video:\s+)?(.+?)(?:\s+-\s+ThisVid(?:\.com| tube))?</title>',
webpage, 'title')
if type_ == 'embed':
# look for more metadata
video_alt_url = url_or_none(self._search_regex(
r'''video_alt_url\s*:\s+'(%s/)',''' % (self._VALID_URL, ),
webpage, 'video_alt_url', default=None))
if video_alt_url and video_alt_url != url:
webpage = self._download_webpage(
video_alt_url, main_id,
note='Redirecting embed to main page', fatal=False) or webpage
video_holder = get_element_by_class('video-holder', webpage) or ''
if '>This video is a private video' in video_holder:
self.raise_login_required(
(clean_html(video_holder) or 'Private video').split('\n', 1)[0])
uploader = self._html_search_regex(
r'''(?s)<span\b[^>]*>Added by:\s*</span><a\b[^>]+\bclass\s*=\s*["']author\b[^>]+\bhref\s*=\s*["']https://thisvid\.com/members/([0-9]+/.{3,}?)\s*</a>''',
webpage, 'uploader', default='')
uploader = re.split(r'''/["'][^>]*>\s*''', uploader)
if len(uploader) == 2:
# id must be non-empty, uploader could be ''
uploader_id, uploader = uploader
uploader = uploader or None
else:
uploader_id = uploader = None
return merge_dicts({
'_type': 'url_transparent',
'title': title,
'age_limit': 18,
'uploader': uploader,
'uploader_id': uploader_id,
}, self.url_result(url, ie='Generic'))
class ThisVidMemberIE(InfoExtractor):
_VALID_URL = r'https?://thisvid\.com/members/(?P<id>\d+)'
_TESTS = [{
'url': 'https://thisvid.com/members/2140501/',
'info_dict': {
'id': '2140501',
'title': 'Rafflesia\'s Profile',
},
'playlist_mincount': 16,
}, {
'url': 'https://thisvid.com/members/2140501/favourite_videos/',
'info_dict': {
'id': '2140501',
'title': 'Rafflesia\'s Favourite Videos',
},
'playlist_mincount': 15,
}, {
'url': 'https://thisvid.com/members/636468/public_videos/',
'info_dict': {
'id': '636468',
'title': 'Happymouth\'s Public Videos',
},
'playlist_mincount': 196,
},
]
def _urls(self, html):
for m in re.finditer(r'''<a\b[^>]+\bhref\s*=\s*["'](?P<url>%s\b)[^>]+>''' % (ThisVidIE._VALID_URL, ), html):
yield m.group('url')
def _real_extract(self, url):
pl_id = self._match_id(url)
webpage = self._download_webpage(url, pl_id)
title = re.split(
r'(?i)\s*\|\s*ThisVid\.com\s*$',
self._og_search_title(webpage, default=None) or self._html_search_regex(r'(?s)<title\b[^>]*>(.+?)</title', webpage, 'title', fatal=False) or '', 1)[0] or None
def entries(page_url, html=None):
for page in itertools.count(1):
if not html:
html = self._download_webpage(
page_url, pl_id, note='Downloading page %d' % (page, ),
fatal=False) or ''
for u in self._urls(html):
yield u
next_page = get_element_by_class('pagination-next', html) or ''
if next_page:
# member list page
next_page = urljoin(url, self._search_regex(
r'''<a\b[^>]+\bhref\s*=\s*("|')(?P<url>(?!#)(?:(?!\1).)+)''',
next_page, 'next page link', group='url', default=None))
# in case a member page should have pagination-next with empty link, not just `else:`
if next_page is None:
# playlist page
parsed_url = compat_urlparse.urlparse(page_url)
base_path, num = parsed_url.path.rsplit('/', 1)
num = int_or_none(num)
if num is None:
base_path, num = parsed_url.path.rstrip('/'), 1
parsed_url = parsed_url._replace(path=base_path + ('/%d' % (num + 1, )))
next_page = compat_urlparse.urlunparse(parsed_url)
if page_url == next_page:
next_page = None
if not next_page:
break
page_url, html = next_page, None
return self.playlist_from_matches(
entries(url, webpage), playlist_id=pl_id, playlist_title=title, ie='ThisVid')
class ThisVidPlaylistIE(ThisVidMemberIE):
_VALID_URL = r'https?://thisvid\.com/playlist/(?P<id>\d+)/video/(?P<video_id>[A-Za-z0-9-]+)'
_TESTS = [{
'url': 'https://thisvid.com/playlist/6615/video/big-italian-booty-28/',
'info_dict': {
'id': '6615',
'title': 'Underwear Stuff',
},
'playlist_mincount': 200,
}, {
'url': 'https://thisvid.com/playlist/6615/video/big-italian-booty-28/',
'info_dict': {
'id': '1072387',
'ext': 'mp4',
'title': 'Big Italian Booty 28',
'description': 'md5:1bccf7b13765e18fb27bf764dba7ede2',
'uploader_id': '367912',
'uploader': 'Jcmusclefun',
'age_limit': 18,
},
'params': {
'noplaylist': True,
},
}]
def _get_video_url(self, pl_url):
video_id = re.match(self._VALID_URL, pl_url).group('video_id')
return urljoin(pl_url, '/videos/%s/' % (video_id, ))
def _urls(self, html):
for m in re.finditer(r'''<a\b[^>]+\bhref\s*=\s*["'](?P<url>%s\b)[^>]+>''' % (self._VALID_URL, ), html):
yield self._get_video_url(m.group('url'))
def _real_extract(self, url):
pl_id = self._match_id(url)
if self._downloader.params.get('noplaylist'):
self.to_screen('Downloading just the featured video because of --no-playlist')
return self.url_result(self._get_video_url(url), 'ThisVid')
self.to_screen(
'Downloading playlist %s - add --no-playlist to download just the featured video' % (pl_id, ))
result = super(ThisVidPlaylistIE, self)._real_extract(url)
# rework title returned as `the title - the title`
title = result['title']
t_len = len(title)
if t_len > 5 and t_len % 2 != 0:
t_len = t_len // 2
if title[t_len] == '-':
title = [t.strip() for t in (title[:t_len], title[t_len + 1:])]
if title[0] and title[0] == title[1]:
result['title'] = title[0]
return result

17
youtube_dl/extractor/tv2dk.py
View File

@@ -41,8 +41,16 @@ class TV2DKIE(InfoExtractor):
'duration': 1347,
'view_count': int,
},
'params': {
'skip_download': True,
'add_ie': ['Kaltura'],
}, {
'url': 'https://www.tv2lorry.dk/gadekamp/gadekamp-6-hoejhuse-i-koebenhavn',
'info_dict': {
'id': '1_7iwll9n0',
'ext': 'mp4',
'upload_date': '20211027',
'title': 'Gadekamp #6 - Højhuse i København',
'uploader_id': 'tv2lorry',
'timestamp': 1635345229,
},
'add_ie': ['Kaltura'],
}, {
@@ -91,11 +99,14 @@ class TV2DKIE(InfoExtractor):
add_entry(partner_id, kaltura_id)
if not entries:
kaltura_id = self._search_regex(
r'entry_id\s*:\s*["\']([0-9a-z_]+)', webpage, 'kaltura id')
(r'entry_id\s*:\s*["\']([0-9a-z_]+)',
r'\\u002FentryId\\u002F(\w+)\\u002F'), webpage, 'kaltura id')
partner_id = self._search_regex(
(r'\\u002Fp\\u002F(\d+)\\u002F', r'/p/(\d+)/'), webpage,
'partner id')
add_entry(partner_id, kaltura_id)
if len(entries) == 1:
return entries[0]
return self.playlist_result(entries)

2
youtube_dl/extractor/uktvplay.py
View File

@@ -5,7 +5,7 @@ from .common import InfoExtractor
class UKTVPlayIE(InfoExtractor):
_VALID_URL = r'https?://uktvplay\.uktv\.co\.uk/(?:.+?\?.*?\bvideo=|([^/]+/)*watch-online/)(?P<id>\d+)'
_VALID_URL = r'https?://uktvplay\.(?:uktv\.)?co\.uk/(?:.+?\?.*?\bvideo=|([^/]+/)*watch-online/)(?P<id>\d+)'
_TESTS = [{
'url': 'https://uktvplay.uktv.co.uk/shows/world-at-war/c/200/watch-online/?video=2117008346001',
'info_dict': {

1
youtube_dl/extractor/uol.py
View File

@@ -95,7 +95,6 @@ class UOLIE(InfoExtractor):
if v:
query[k] = v
f_url = update_url_query(f_url, query)
format_id = format_id
if format_id == 'HLS':
m3u8_formats = self._extract_m3u8_formats(
f_url, media_id, 'mp4', 'm3u8_native',

52
youtube_dl/extractor/urplay.py
View File

@@ -4,7 +4,11 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
dict_get,
ExtractorError,
int_or_none,
ISO639Utils,
parse_age_limit,
try_get,
unified_timestamp,
)
@@ -23,9 +27,10 @@ class URPlayIE(InfoExtractor):
'upload_date': '20171214',
'series': 'UR Samtiden - Livet, universum och rymdens märkliga musik',
'duration': 2269,
'categories': ['Kultur & historia'],
'categories': ['Vetenskap & teknik'],
'tags': ['Kritiskt tänkande', 'Vetenskap', 'Vetenskaplig verksamhet'],
'episode': 'Om vetenskap, kritiskt tänkande och motstånd',
'age_limit': 15,
},
}, {
'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde',
@@ -50,11 +55,19 @@ class URPlayIE(InfoExtractor):
video_id = self._match_id(url)
url = url.replace('skola.se/Produkter', 'play.se/program')
webpage = self._download_webpage(url, video_id)
vid = int(video_id)
accessible_episodes = self._parse_json(self._html_search_regex(
r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"',
webpage, 'urplayer data'), video_id)['accessibleEpisodes']
urplayer_data = next(e for e in accessible_episodes if e.get('id') == vid)
urplayer_data = self._search_regex(
r'(?s)\bid\s*=\s*"__NEXT_DATA__"[^>]*>\s*({.+?})\s*</script',
webpage, 'urplayer next data', fatal=False) or {}
if urplayer_data:
urplayer_data = self._parse_json(urplayer_data, video_id, fatal=False)
urplayer_data = try_get(urplayer_data, lambda x: x['props']['pageProps']['program'], dict)
if not urplayer_data:
raise ExtractorError('Unable to parse __NEXT_DATA__')
else:
accessible_episodes = self._parse_json(self._html_search_regex(
r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"',
webpage, 'urplayer data'), video_id)['accessibleEpisodes']
urplayer_data = next(e for e in accessible_episodes if e.get('id') == int_or_none(video_id))
episode = urplayer_data['title']
raw_streaming_info = urplayer_data['streamingInfo']['raw']
host = self._download_json(
@@ -72,6 +85,30 @@ class URPlayIE(InfoExtractor):
video_id, skip_protocols=['f4m', 'rtmp', 'rtsp']))
self._sort_formats(formats)
subtitles = {}
def parse_lang_code(code):
"3-character language code or None (utils candidate)"
if code is None:
return
lang = code.lower()
if not ISO639Utils.long2short(lang):
lang = ISO639Utils.short2long(lang)
return lang or None
for k, v in (urplayer_data['streamingInfo'].get('sweComplete') or {}).items():
if (k in ('sd', 'hd') or not isinstance(v, dict)):
continue
lang, sttl_url = (v.get(kk) for kk in ('language', 'location', ))
if not sttl_url:
continue
lang = parse_lang_code(lang)
if not lang:
continue
sttl = subtitles.get(lang) or []
sttl.append({'ext': k, 'url': sttl_url, })
subtitles[lang] = sttl
image = urplayer_data.get('image') or {}
thumbnails = []
for k, v in image.items():
@@ -104,4 +141,7 @@ class URPlayIE(InfoExtractor):
'season': series.get('label'),
'episode': episode,
'episode_number': int_or_none(urplayer_data.get('episodeNumber')),
'age_limit': parse_age_limit(min(try_get(a, lambda x: x['from'], int) or 0
for a in urplayer_data.get('ageRanges', []))),
'subtitles': subtitles,
}

57
youtube_dl/extractor/videa.py
View File

@@ -12,6 +12,7 @@ from ..utils import (
mimetype2ext,
parse_codecs,
update_url_query,
urljoin,
xpath_element,
xpath_text,
)
@@ -19,6 +20,7 @@ from ..compat import (
compat_b64decode,
compat_ord,
compat_struct_pack,
compat_urlparse,
)
@@ -45,10 +47,24 @@ class VideaIE(InfoExtractor):
},
}, {
'url': 'http://videa.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
'only_matching': True,
'md5': 'd57ccd8812c7fd491d33b1eab8c99975',
'info_dict': {
'id': 'jAHDWfWSJH5XuFhH',
'ext': 'mp4',
'title': 'Supercars előzés',
'thumbnail': r're:^https?://.*',
'duration': 64,
},
}, {
'url': 'http://videa.hu/player?v=8YfIAjxwWGwT8HVQ',
'only_matching': True,
'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
'info_dict': {
'id': '8YfIAjxwWGwT8HVQ',
'ext': 'mp4',
'title': 'Az őrült kígyász 285 kígyót enged szabadon',
'thumbnail': r're:^https?://.*',
'duration': 21,
},
}, {
'url': 'http://videa.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
'only_matching': True,
@@ -91,13 +107,20 @@ class VideaIE(InfoExtractor):
k = S[(S[i] + S[j]) % 256]
res += compat_struct_pack('B', k ^ compat_ord(cipher_text[m]))
return res.decode()
return res.decode('utf-8')
def _real_extract(self, url):
video_id = self._match_id(url)
query = {'v': video_id}
player_page = self._download_webpage(
'https://videa.hu/player', video_id, query=query)
video_page = self._download_webpage(url, video_id)
if 'videa.hu/player' in url:
player_url = url
player_page = video_page
else:
player_url = self._search_regex(
r'<iframe.*?src="(/player\?[^"]+)"', video_page, 'player url')
player_url = urljoin(url, player_url)
player_page = self._download_webpage(player_url, video_id)
nonce = self._search_regex(
r'_xt\s*=\s*"([^"]+)"', player_page, 'nonce')
@@ -107,6 +130,7 @@ class VideaIE(InfoExtractor):
for i in range(0, 32):
result += s[i - (self._STATIC_SECRET.index(l[i]) - 31)]
query = compat_urlparse.parse_qs(compat_urlparse.urlparse(player_url).query)
random_seed = ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(8))
query['_s'] = random_seed
query['_t'] = result[:16]
@@ -121,13 +145,13 @@ class VideaIE(InfoExtractor):
compat_b64decode(b64_info), key), video_id)
video = xpath_element(info, './video', 'video')
if not video:
if video is None:
raise ExtractorError(xpath_element(
info, './error', fatal=True), expected=True)
sources = xpath_element(
info, './video_sources', 'sources', fatal=True)
hash_values = xpath_element(
info, './hash_values', 'hash values', fatal=True)
info, './hash_values', 'hash values', fatal=False)
title = xpath_text(video, './title', fatal=True)
@@ -136,15 +160,16 @@ class VideaIE(InfoExtractor):
source_url = source.text
source_name = source.get('name')
source_exp = source.get('exp')
if not (source_url and source_name and source_exp):
if not (source_url and source_name):
continue
hash_value = xpath_text(hash_values, 'hash_value_' + source_name)
if not hash_value:
continue
source_url = update_url_query(source_url, {
'md5': hash_value,
'expires': source_exp,
})
hash_value = (
xpath_text(hash_values, 'hash_value_' + source_name)
if hash_values is not None else None)
if hash_value and source_exp:
source_url = update_url_query(source_url, {
'md5': hash_value,
'expires': source_exp,
})
f = parse_codecs(source.get('codecs'))
f.update({
'url': self._proto_relative_url(source_url),

335
youtube_dl/extractor/viki.py
View File

@@ -1,38 +1,29 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import hashlib
import hmac
import itertools
import json
import re
import time
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
ExtractorError,
int_or_none,
parse_age_limit,
parse_iso8601,
sanitized_Request,
std_headers,
try_get,
)
class VikiBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.)?viki\.(?:com|net|mx|jp|fr)/'
_API_QUERY_TEMPLATE = '/v4/%sapp=%s&t=%s&site=www.viki.com'
_API_URL_TEMPLATE = 'https://api.viki.io%s&sig=%s'
_API_URL_TEMPLATE = 'https://api.viki.io%s'
_DEVICE_ID = '112395910d'
_APP = '100005a'
_APP_VERSION = '6.0.0'
_APP_SECRET = 'MM_d*yP@`&1@]@!AVrXf_o-HVEnoTnm$O-ti4[G~$JDI/Dc-&piU&z&5.;:}95=Iad'
_APP_VERSION = '6.11.3'
_APP_SECRET = 'd96704b180208dbb2efa30fe44c48bd8690441af9f567ba8fd710a72badc85198f7472'
_GEO_BYPASS = False
_NETRC_MACHINE = 'viki'
@@ -45,43 +36,60 @@ class VikiBaseIE(InfoExtractor):
'paywall': 'Sorry, this content is only available to Viki Pass Plus subscribers',
}
def _prepare_call(self, path, timestamp=None, post_data=None):
def _stream_headers(self, timestamp, sig):
return {
'X-Viki-manufacturer': 'vivo',
'X-Viki-device-model': 'vivo 1606',
'X-Viki-device-os-ver': '6.0.1',
'X-Viki-connection-type': 'WIFI',
'X-Viki-carrier': '',
'X-Viki-as-id': '100005a-1625321982-3932',
'timestamp': str(timestamp),
'signature': str(sig),
'x-viki-app-ver': self._APP_VERSION
}
def _api_query(self, path, version=4, **kwargs):
path += '?' if '?' not in path else '&'
if not timestamp:
timestamp = int(time.time())
query = self._API_QUERY_TEMPLATE % (path, self._APP, timestamp)
app = self._APP
query = '/v{version}/{path}app={app}'.format(**locals())
if self._token:
query += '&token=%s' % self._token
return query + ''.join('&{name}={val}.format(**locals())' for name, val in kwargs.items())
def _sign_query(self, path):
timestamp = int(time.time())
query = self._api_query(path, version=5)
sig = hmac.new(
self._APP_SECRET.encode('ascii'),
query.encode('ascii'),
hashlib.sha1
).hexdigest()
url = self._API_URL_TEMPLATE % (query, sig)
return sanitized_Request(
url, json.dumps(post_data).encode('utf-8')) if post_data else url
'{query}&t={timestamp}'.format(**locals()).encode('ascii'),
hashlib.sha1).hexdigest()
return timestamp, sig, self._API_URL_TEMPLATE % query
def _call_api(self, path, video_id, note, timestamp=None, post_data=None):
def _call_api(
self, path, video_id, note='Downloading JSON metadata', data=None, query=None, fatal=True):
if query is None:
timestamp, sig, url = self._sign_query(path)
else:
url = self._API_URL_TEMPLATE % self._api_query(path, version=4)
resp = self._download_json(
self._prepare_call(path, timestamp, post_data), video_id, note,
headers={'x-viki-app-ver': self._APP_VERSION})
error = resp.get('error')
if error:
if error == 'invalid timestamp':
resp = self._download_json(
self._prepare_call(path, int(resp['current_timestamp']), post_data),
video_id, '%s (retry)' % note)
error = resp.get('error')
if error:
self._raise_error(resp['error'])
url, video_id, note, fatal=fatal, query=query,
data=json.dumps(data).encode('utf-8') if data else None,
headers=({'x-viki-app-ver': self._APP_VERSION} if data
else self._stream_headers(timestamp, sig) if query is None
else None), expected_status=400) or {}
self._raise_error(resp.get('error'), fatal)
return resp
def _raise_error(self, error):
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error),
expected=True)
def _raise_error(self, error, fatal=True):
if error is None:
return
msg = '%s said: %s' % (self.IE_NAME, error)
if fatal:
raise ExtractorError(msg, expected=True)
else:
self.report_warning(msg)
def _check_errors(self, data):
for reason, status in (data.get('blocking') or {}).items():
@@ -90,9 +98,10 @@ class VikiBaseIE(InfoExtractor):
if reason == 'geo':
self.raise_geo_restricted(msg=message)
elif reason == 'paywall':
if try_get(data, lambda x: x['paywallable']['tvod']):
self._raise_error('This video is for rent only or TVOD (Transactional Video On demand)')
self.raise_login_required(message)
raise ExtractorError('%s said: %s' % (
self.IE_NAME, message), expected=True)
self._raise_error(message)
def _real_initialize(self):
self._login()
@@ -102,35 +111,39 @@ class VikiBaseIE(InfoExtractor):
if username is None:
return
login_form = {
'login_id': username,
'password': password,
}
login = self._call_api(
'sessions.json', None,
'Logging in', post_data=login_form)
self._token = login.get('token')
self._token = self._call_api(
'sessions.json', None, 'Logging in', fatal=False,
data={'username': username, 'password': password}).get('token')
if not self._token:
self.report_warning('Unable to get session token, login has probably failed')
self.report_warning('Login Failed: Unable to get session token')
@staticmethod
def dict_selection(dict_obj, preferred_key, allow_fallback=True):
def dict_selection(dict_obj, preferred_key):
if preferred_key in dict_obj:
return dict_obj.get(preferred_key)
if not allow_fallback:
return
filtered_dict = list(filter(None, [dict_obj.get(k) for k in dict_obj.keys()]))
return filtered_dict[0] if filtered_dict else None
return dict_obj[preferred_key]
return (list(filter(None, dict_obj.values())) or [None])[0]
class VikiIE(VikiBaseIE):
IE_NAME = 'viki'
_VALID_URL = r'%s(?:videos|player)/(?P<id>[0-9]+v)' % VikiBaseIE._VALID_URL_BASE
_TESTS = [{
'note': 'Free non-DRM video with storyboards in MPD',
'url': 'https://www.viki.com/videos/1175236v-choosing-spouse-by-lottery-episode-1',
'info_dict': {
'id': '1175236v',
'ext': 'mp4',
'title': 'Choosing Spouse by Lottery - Episode 1',
'timestamp': 1606463239,
'age_limit': 12,
'uploader': 'FCC',
'upload_date': '20201127',
},
'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
'params': {
'format': 'bestvideo',
},
}, {
'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14',
'info_dict': {
'id': '1023585v',
@@ -146,7 +159,7 @@ class VikiIE(VikiBaseIE):
'params': {
'format': 'bestvideo',
},
'skip': 'Blocked in the US',
'skip': 'Content is only available to Viki Pass Plus subscribers',
'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
}, {
# clip
@@ -178,11 +191,11 @@ class VikiIE(VikiBaseIE):
'like_count': int,
'age_limit': 13,
},
'skip': 'Blocked in the US',
'skip': 'Page not found!',
}, {
# episode
'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1',
'md5': '0a53dc252e6e690feccd756861495a8c',
'md5': '670440c79f7109ca6564d4c7f24e3e81',
'info_dict': {
'id': '44699v',
'ext': 'mp4',
@@ -193,7 +206,7 @@ class VikiIE(VikiBaseIE):
'upload_date': '20100405',
'uploader': 'group8',
'like_count': int,
'age_limit': 13,
'age_limit': 15,
'episode_number': 1,
},
'params': {
@@ -224,7 +237,7 @@ class VikiIE(VikiBaseIE):
}, {
# non-English description
'url': 'http://www.viki.com/videos/158036v-love-in-magic',
'md5': '41faaba0de90483fb4848952af7c7d0d',
'md5': '78bf49fdaa51f9e7f9150262a9ef9bdf',
'info_dict': {
'id': '158036v',
'ext': 'mp4',
@@ -232,8 +245,8 @@ class VikiIE(VikiBaseIE):
'upload_date': '20111122',
'timestamp': 1321985454,
'description': 'md5:44b1e46619df3a072294645c770cef36',
'title': 'Love In Magic',
'age_limit': 13,
'title': 'Love in Magic',
'age_limit': 15,
},
'params': {
'format': 'bestvideo',
@@ -244,45 +257,53 @@ class VikiIE(VikiBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
resp = self._download_json(
'https://www.viki.com/api/videos/' + video_id,
video_id, 'Downloading video JSON', headers={
'x-client-user-agent': std_headers['User-Agent'],
'x-viki-app-ver': '3.0.0',
})
video = resp['video']
video = self._call_api('videos/{0}.json'.format(video_id), video_id, 'Downloading video JSON', query={})
self._check_errors(video)
title = self.dict_selection(video.get('titles', {}), 'en', allow_fallback=False)
title = try_get(video, lambda x: x['titles']['en'], str)
episode_number = int_or_none(video.get('number'))
if not title:
title = 'Episode %d' % episode_number if video.get('type') == 'episode' else video.get('id') or video_id
container_titles = try_get(video, lambda x: x['container']['titles'], dict) or {}
container_title = self.dict_selection(container_titles, 'en')
title = '%s - %s' % (container_title, title)
if container_title and title == video_id:
title = container_title
else:
title = '%s - %s' % (container_title, title)
resp = self._call_api(
'playback_streams/%s.json?drms=dt3&device_id=%s' % (video_id, self._DEVICE_ID),
video_id, 'Downloading video streams JSON')['main'][0]
mpd_url = resp['url']
# 720p is hidden in another MPD which can be found in the current manifest content
mpd_content = self._download_webpage(mpd_url, video_id, note='Downloading initial MPD manifest')
mpd_url = self._search_regex(
r'(?mi)<BaseURL>(http.+.mpd)', mpd_content, 'new manifest', default=mpd_url)
if 'mpdhd_high' not in mpd_url:
# Modify the URL to get 1080p
mpd_url = mpd_url.replace('mpdhd', 'mpdhd_high')
formats = self._extract_mpd_formats(mpd_url, video_id)
self._sort_formats(formats)
description = self.dict_selection(video.get('descriptions', {}), 'en')
thumbnails = [{
'id': thumbnail_id,
'url': thumbnail['url'],
} for thumbnail_id, thumbnail in (video.get('images') or {}).items() if thumbnail.get('url')]
like_count = int_or_none(try_get(video, lambda x: x['likes']['count']))
thumbnails = []
for thumbnail_id, thumbnail in (video.get('images') or {}).items():
thumbnails.append({
'id': thumbnail_id,
'url': thumbnail.get('url'),
})
stream_id = try_get(resp, lambda x: x['properties']['track']['stream_id'])
subtitles = dict((lang, [{
'ext': ext,
'url': self._API_URL_TEMPLATE % self._api_query(
'videos/{0}/auth_subtitles/{1}.{2}'.format(video_id, lang, ext), stream_id=stream_id)
} for ext in ('srt', 'vtt')]) for lang in (video.get('subtitle_completions') or {}).keys())
subtitles = {}
for subtitle_lang, _ in (video.get('subtitle_completions') or {}).items():
subtitles[subtitle_lang] = [{
'ext': subtitles_format,
'url': self._prepare_call(
'videos/%s/subtitles/%s.%s' % (video_id, subtitle_lang, subtitles_format)),
} for subtitles_format in ('srt', 'vtt')]
result = {
return {
'id': video_id,
'formats': formats,
'title': title,
'description': description,
'duration': int_or_none(video.get('duration')),
@@ -296,79 +317,6 @@ class VikiIE(VikiBaseIE):
'episode_number': episode_number,
}
formats = []
def add_format(format_id, format_dict, protocol='http'):
# rtmps URLs does not seem to work
if protocol == 'rtmps':
return
format_url = format_dict.get('url')
if not format_url:
return
qs = compat_parse_qs(compat_urllib_parse_urlparse(format_url).query)
stream = qs.get('stream', [None])[0]
if stream:
format_url = base64.b64decode(stream).decode()
if format_id in ('m3u8', 'hls'):
m3u8_formats = self._extract_m3u8_formats(
format_url, video_id, 'mp4',
entry_protocol='m3u8_native',
m3u8_id='m3u8-%s' % protocol, fatal=False)
# Despite CODECS metadata in m3u8 all video-only formats
# are actually video+audio
for f in m3u8_formats:
if '_drm/index_' in f['url']:
continue
if f.get('acodec') == 'none' and f.get('vcodec') != 'none':
f['acodec'] = None
formats.append(f)
elif format_id in ('mpd', 'dash'):
formats.extend(self._extract_mpd_formats(
format_url, video_id, 'mpd-%s' % protocol, fatal=False))
elif format_url.startswith('rtmp'):
mobj = re.search(
r'^(?P<url>rtmp://[^/]+/(?P<app>.+?))/(?P<playpath>mp4:.+)$',
format_url)
if not mobj:
return
formats.append({
'format_id': 'rtmp-%s' % format_id,
'ext': 'flv',
'url': mobj.group('url'),
'play_path': mobj.group('playpath'),
'app': mobj.group('app'),
'page_url': url,
})
else:
formats.append({
'url': format_url,
'format_id': '%s-%s' % (format_id, protocol),
'height': int_or_none(self._search_regex(
r'^(\d+)[pP]$', format_id, 'height', default=None)),
})
for format_id, format_dict in (resp.get('streams') or {}).items():
add_format(format_id, format_dict)
if not formats:
streams = self._call_api(
'videos/%s/streams.json' % video_id, video_id,
'Downloading video streams JSON')
if 'external' in streams:
result.update({
'_type': 'url_transparent',
'url': streams['external']['url'],
})
return result
for format_id, stream_dict in streams.items():
for protocol, format_dict in stream_dict.items():
add_format(format_id, format_dict, protocol)
self._sort_formats(formats)
result['formats'] = formats
return result
class VikiChannelIE(VikiBaseIE):
IE_NAME = 'viki:channel'
@@ -378,9 +326,9 @@ class VikiChannelIE(VikiBaseIE):
'info_dict': {
'id': '50c',
'title': 'Boys Over Flowers',
'description': 'md5:804ce6e7837e1fd527ad2f25420f4d59',
'description': 'md5:f08b679c200e1a273c695fe9986f21d7',
},
'playlist_mincount': 71,
'playlist_mincount': 51,
}, {
'url': 'http://www.viki.com/tv/1354c-poor-nastya-complete',
'info_dict': {
@@ -401,33 +349,38 @@ class VikiChannelIE(VikiBaseIE):
'only_matching': True,
}]
_PER_PAGE = 25
_video_types = ('episodes', 'movies', 'clips', 'trailers')
def _entries(self, channel_id):
params = {
'app': self._APP, 'token': self._token, 'only_ids': 'true',
'direction': 'asc', 'sort': 'number', 'per_page': 30
}
video_types = self._video_types
for video_type in video_types:
if video_type not in self._video_types:
self.report_warning('Unknown video_type: ' + video_type)
page_num = 0
while True:
page_num += 1
params['page'] = page_num
res = self._call_api(
'containers/{channel_id}/{video_type}.json'.format(**locals()), channel_id, query=params, fatal=False,
note='Downloading %s JSON page %d' % (video_type.title(), page_num))
for video_id in res.get('response') or []:
yield self.url_result('https://www.viki.com/videos/' + video_id, VikiIE.ie_key(), video_id)
if not res.get('more'):
break
def _real_extract(self, url):
channel_id = self._match_id(url)
channel = self._call_api(
'containers/%s.json' % channel_id, channel_id,
'Downloading channel JSON')
channel = self._call_api('containers/%s.json' % channel_id, channel_id, 'Downloading channel JSON')
self._check_errors(channel)
title = self.dict_selection(channel['titles'], 'en')
description = self.dict_selection(channel['descriptions'], 'en')
entries = []
for video_type in ('episodes', 'clips', 'movies'):
for page_num in itertools.count(1):
page = self._call_api(
'containers/%s/%s.json?per_page=%d&sort=number&direction=asc&with_paging=true&page=%d'
% (channel_id, video_type, self._PER_PAGE, page_num), channel_id,
'Downloading %s JSON page #%d' % (video_type, page_num))
for video in page['response']:
video_id = video['id']
entries.append(self.url_result(
'https://www.viki.com/videos/%s' % video_id, 'Viki'))
if not page['pagination']['next']:
break
return self.playlist_result(entries, channel_id, title, description)
return self.playlist_result(
self._entries(channel_id), channel_id,
self.dict_selection(channel['titles'], 'en'),
self.dict_selection(channel['descriptions'], 'en'))

79
youtube_dl/extractor/vimeo.py
View File

@@ -261,27 +261,33 @@ class VimeoIE(VimeoBaseInfoExtractor):
# _VALID_URL matches Vimeo URLs
_VALID_URL = r'''(?x)
https?://
(?:
(?:
www|
player
)
\.
)?
vimeo(?:pro)?\.com/
(?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
(?:.*?/)?
(?:
(?:
play_redirect_hls|
moogaloop\.swf)\?clip_id=
)?
(?:videos?/)?
(?P<id>[0-9]+)
(?:/(?P<unlisted_hash>[\da-f]{10}))?
/?(?:[?&].*)?(?:[#].*)?$
'''
https?://
(?:
(?:
www|
player
)
\.
)?
vimeo(?:pro)?\.com/
(?:
(?P<u>user)|
(?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
(?:.*?/)??
(?P<q>
(?:
play_redirect_hls|
moogaloop\.swf)\?clip_id=
)?
(?:videos?/)?
)
(?P<id>[0-9]+)
(?(u)
/(?!videos|likes)[^/?#]+/?|
(?(q)|/(?P<unlisted_hash>[\da-f]{10}))?
)
(?:(?(q)[&]|(?(u)|/?)[?]).*?)?(?:[#].*)?$
'''
IE_NAME = 'vimeo'
_TESTS = [
{
@@ -517,15 +523,34 @@ class VimeoIE(VimeoBaseInfoExtractor):
'url': 'https://vimeo.com/7809605',
'only_matching': True,
},
{
'url': 'https://vimeo.com/160743502/abd0e13fb4',
'only_matching': True,
},
{
# requires passing unlisted_hash(a52724358e) to load_download_config request
'url': 'https://vimeo.com/392479337/a52724358e',
'only_matching': True,
}
},
{
# similar, but all numeric: ID must be 581039021, not 9603038895
# issue #29690
'url': 'https://vimeo.com/581039021/9603038895',
'info_dict': {
'id': '581039021',
# these have to be provided but we don't care
'ext': 'mp4',
'timestamp': 1627621014,
'title': 're:.+',
'uploader_id': 're:.+',
'uploader': 're:.+',
'upload_date': r're:\d+',
},
'params': {
'skip_download': True,
},
},
{
# user playlist alias -> https://vimeo.com/258705797
'url': 'https://vimeo.com/user26785108/newspiritualguide',
'only_matching': True,
},
# https://gettingthingsdone.com/workflowmap/
# vimeo embed with check-password page protected by Referer header
]
@@ -649,7 +674,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
if '//player.vimeo.com/video/' in url:
config = self._parse_json(self._search_regex(
r'\bconfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
r'(?s)\b(?:playerC|c)onfig\s*=\s*({.+?})\s*[;\n]', webpage, 'info section'), video_id)
if config.get('view') == 4:
config = self._verify_player_video_password(
redirect_url, video_id, headers)

15
youtube_dl/extractor/vvvvid.py
View File

@@ -64,6 +64,18 @@ class VVVVIDIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
# video_type == 'video/dash'
'url': 'https://www.vvvvid.it/show/683/made-in-abyss/1542/693786/nanachi',
'info_dict': {
'id': '693786',
'ext': 'mp4',
'title': 'Nanachi',
},
'params': {
'skip_download': True,
'format': 'mp4',
},
}, {
'url': 'https://www.vvvvid.it/show/434/perche-dovrei-guardarlo-di-dario-moccia/437/489048',
'only_matching': True
@@ -205,6 +217,9 @@ class VVVVIDIE(InfoExtractor):
})
is_youtube = True
break
elif video_type == 'video/dash':
formats.extend(self._extract_m3u8_formats(
embed_code, video_id, 'mp4', m3u8_id='hls', fatal=False))
else:
formats.extend(self._extract_wowza_formats(
'http://sb.top-ix.org/videomg/_definst_/mp4:%s/playlist.m3u8' % embed_code, video_id))

2
youtube_dl/extractor/wat.py
View File

@@ -57,7 +57,7 @@ class WatIE(InfoExtractor):
# 'http://www.wat.tv/interface/contentv4s/' + video_id, video_id)
video_data = self._download_json(
'https://mediainfo.tf1.fr/mediainfocombo/' + video_id,
video_id, query={'context': 'MYTF1'})
video_id, query={'context': 'MYTF1', 'pver': '4001000'})
video_info = video_data['media']
error_desc = video_info.get('error_desc')

60
youtube_dl/extractor/wdr.py
View File

@@ -10,6 +10,7 @@ from ..compat import (
)
from ..utils import (
determine_ext,
dict_get,
ExtractorError,
js_to_json,
strip_jsonp,
@@ -22,9 +23,10 @@ from ..utils import (
class WDRIE(InfoExtractor):
_VALID_URL = r'https?://deviceids-medp\.wdr\.de/ondemand/\d+/(?P<id>\d+)\.js'
__API_URL_TPL = '//deviceids-medp.wdr.de/ondemand/%s/%s'
_VALID_URL = (r'(?:https?:' + __API_URL_TPL) % (r'\d+', r'(?=\d+\.js)|wdr:)(?P<id>\d{6,})')
_GEO_COUNTRIES = ['DE']
_TEST = {
_TESTS = [{
'url': 'http://deviceids-medp.wdr.de/ondemand/155/1557833.js',
'info_dict': {
'id': 'mdb-1557833',
@@ -32,11 +34,20 @@ class WDRIE(InfoExtractor):
'title': 'Biathlon-Staffel verpasst Podest bei Olympia-Generalprobe',
'upload_date': '20180112',
},
}
},
]
def _asset_url(self, wdr_id):
id_len = max(len(wdr_id), 5)
return ''.join(('https:', self.__API_URL_TPL % (wdr_id[:id_len - 4], wdr_id, ), '.js'))
def _real_extract(self, url):
video_id = self._match_id(url)
if url.startswith('wdr:'):
video_id = url[4:]
url = self._asset_url(video_id)
metadata = self._download_json(
url, video_id, transform_source=strip_jsonp)
@@ -115,10 +126,10 @@ class WDRIE(InfoExtractor):
}
class WDRPageIE(InfoExtractor):
_CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
class WDRPageIE(WDRIE):
_MAUS_REGEX = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/)*?(?P<maus_id>[^/?#.]+)(?:/?|/index\.php5|\.php5)$'
_PAGE_REGEX = r'/(?:mediathek/)?(?:[^/]+/)*(?P<display_id>[^/]+)\.html'
_VALID_URL = r'https?://(?:www\d?\.)?(?:(?:kinder\.)?wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
_VALID_URL = r'https?://(?:www\d?\.)?(?:(?:kinder\.)?wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _MAUS_REGEX
_TESTS = [
{
@@ -159,11 +170,11 @@ class WDRPageIE(InfoExtractor):
{
'url': 'http://www1.wdr.de/mediathek/video/live/index.html',
'info_dict': {
'id': 'mdb-1406149',
'id': 'mdb-2296252',
'ext': 'mp4',
'title': r're:^WDR Fernsehen im Livestream \(nur in Deutschland erreichbar\) [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'title': r're:^WDR Fernsehen im Livestream (?:\(nur in Deutschland erreichbar\) )?[0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'alt_title': 'WDR Fernsehen Live',
'upload_date': '20150101',
'upload_date': '20201112',
'is_live': True,
},
'params': {
@@ -172,7 +183,7 @@ class WDRPageIE(InfoExtractor):
},
{
'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html',
'playlist_mincount': 7,
'playlist_mincount': 6,
'info_dict': {
'id': 'aktuelle-stunde-120',
},
@@ -180,10 +191,10 @@ class WDRPageIE(InfoExtractor):
{
'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
'info_dict': {
'id': 'mdb-1552552',
'id': 'mdb-2627637',
'ext': 'mp4',
'upload_date': 're:^[0-9]{8}$',
'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$',
'title': 're:^Die Sendung (?:mit der Maus )?vom [0-9.]{10}$',
},
'skip': 'The id changes from week to week because of the new episode'
},
@@ -196,6 +207,7 @@ class WDRPageIE(InfoExtractor):
'upload_date': '20130919',
'title': 'Sachgeschichte - Achterbahn ',
},
'skip': 'HTTP Error 404: Not Found',
},
{
'url': 'http://www1.wdr.de/radio/player/radioplayer116~_layout-popupVersion.html',
@@ -221,6 +233,7 @@ class WDRPageIE(InfoExtractor):
'params': {
'skip_download': True,
},
'skip': 'HTTP Error 404: Not Found',
},
{
'url': 'http://www.sportschau.de/handballem2018/audio-vorschau---die-handball-em-startet-mit-grossem-favoritenfeld-100.html',
@@ -234,7 +247,7 @@ class WDRPageIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('display_id')
display_id = dict_get(mobj.groupdict(), ('display_id', 'maus_id'), 'wdrmaus')
webpage = self._download_webpage(url, display_id)
entries = []
@@ -260,6 +273,14 @@ class WDRPageIE(InfoExtractor):
jsonp_url = try_get(
media_link_obj, lambda x: x['mediaObj']['url'], compat_str)
if jsonp_url:
# metadata, or player JS with ['ref'] giving WDR id, or just media, perhaps
clip_id = media_link_obj['mediaObj'].get('ref')
if jsonp_url.endswith('.assetjsonp'):
asset = self._download_json(
jsonp_url, display_id, fatal=False, transform_source=strip_jsonp)
clip_id = try_get(asset, lambda x: x['trackerData']['trackerClipId'], compat_str)
if clip_id:
jsonp_url = self._asset_url(clip_id[4:])
entries.append(self.url_result(jsonp_url, ie=WDRIE.ie_key()))
# Playlist (e.g. https://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html)
@@ -279,16 +300,14 @@ class WDRPageIE(InfoExtractor):
class WDRElefantIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)wdrmaus\.de/elefantenseite/#(?P<id>.+)'
_TEST = {
'url': 'http://www.wdrmaus.de/elefantenseite/#folge_ostern_2015',
'url': 'http://www.wdrmaus.de/elefantenseite/#elefantenkino_wippe',
# adaptive stream: unstable file MD5
'info_dict': {
'title': 'Folge Oster-Spezial 2015',
'id': 'mdb-1088195',
'title': 'Wippe',
'id': 'mdb-1198320',
'ext': 'mp4',
'age_limit': None,
'upload_date': '20150406'
},
'params': {
'skip_download': True,
'upload_date': '20071003'
},
}
@@ -323,6 +342,7 @@ class WDRMobileIE(InfoExtractor):
/[0-9]+/[0-9]+/
(?P<id>[0-9]+)_(?P<title>[0-9]+)'''
IE_NAME = 'wdr:mobile'
_WORKING = False # no such domain
_TEST = {
'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
'info_dict': {

25
youtube_dl/extractor/xhamster.py
View File

@@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import itertools
@@ -23,7 +24,7 @@ from ..utils import (
class XHamsterIE(InfoExtractor):
_DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com)'
_DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com|xhday\.com|xhvid\.com)'
_VALID_URL = r'''(?x)
https?://
(?:.+?\.)?%s/
@@ -34,7 +35,7 @@ class XHamsterIE(InfoExtractor):
''' % _DOMAINS
_TESTS = [{
'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
'md5': '98b4687efb1ffd331c4197854dc09e8f',
'md5': '34e1ab926db5dc2750fed9e1f34304bb',
'info_dict': {
'id': '1509445',
'display_id': 'femaleagent-shy-beauty-takes-the-bait',
@@ -43,6 +44,7 @@ class XHamsterIE(InfoExtractor):
'timestamp': 1350194821,
'upload_date': '20121014',
'uploader': 'Ruseful2011',
'uploader_id': 'ruseful2011',
'duration': 893,
'age_limit': 18,
},
@@ -72,6 +74,7 @@ class XHamsterIE(InfoExtractor):
'timestamp': 1454948101,
'upload_date': '20160208',
'uploader': 'parejafree',
'uploader_id': 'parejafree',
'duration': 72,
'age_limit': 18,
},
@@ -117,6 +120,12 @@ class XHamsterIE(InfoExtractor):
}, {
'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
'only_matching': True,
}, {
'url': 'https://xhday.com/videos/strapless-threesome-xhh7yVf',
'only_matching': True,
}, {
'url': 'https://xhvid.com/videos/lk-mm-xhc6wn6',
'only_matching': True,
}]
def _real_extract(self, url):
@@ -245,6 +254,7 @@ class XHamsterIE(InfoExtractor):
else:
categories = None
uploader_url = url_or_none(try_get(video, lambda x: x['author']['pageURL']))
return {
'id': video_id,
'display_id': display_id,
@@ -253,6 +263,8 @@ class XHamsterIE(InfoExtractor):
'timestamp': int_or_none(video.get('created')),
'uploader': try_get(
video, lambda x: x['author']['name'], compat_str),
'uploader_url': uploader_url,
'uploader_id': uploader_url.split('/')[-1] if uploader_url else None,
'thumbnail': video.get('thumbURL'),
'duration': int_or_none(video.get('duration')),
'view_count': int_or_none(video.get('views')),
@@ -261,7 +273,7 @@ class XHamsterIE(InfoExtractor):
'dislike_count': int_or_none(try_get(
video, lambda x: x['rating']['dislikes'], int)),
'comment_count': int_or_none(video.get('views')),
'age_limit': age_limit,
'age_limit': age_limit if age_limit is not None else 18,
'categories': categories,
'formats': formats,
}
@@ -352,6 +364,7 @@ class XHamsterIE(InfoExtractor):
'description': description,
'upload_date': upload_date,
'uploader': uploader,
'uploader_id': uploader.lower() if uploader else None,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
@@ -420,6 +433,12 @@ class XHamsterUserIE(InfoExtractor):
'id': 'firatkaan',
},
'playlist_mincount': 1,
}, {
'url': 'https://xhday.com/users/mobhunter',
'only_matching': True,
}, {
'url': 'https://xhvid.com/users/pelushe21',
'only_matching': True,
}]
def _entries(self, user_id):

2
youtube_dl/extractor/xvideos.py
View File

@@ -82,7 +82,7 @@ class XVideosIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://www.xvideos.com/video%s/' % video_id, video_id)
'https://www.xvideos.com/video%s/0' % video_id, video_id)
mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
if mobj:

6
youtube_dl/extractor/youporn.py
View File

@@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import re
@@ -137,9 +138,10 @@ class YouPornIE(InfoExtractor):
r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
webpage, 'uploader', fatal=False)
upload_date = unified_strdate(self._html_search_regex(
[r'UPLOADED:\s*<span>([^<]+)',
(r'UPLOADED:\s*<span>([^<]+)',
r'Date\s+[Aa]dded:\s*<span>([^<]+)',
r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>'],
r'''(?s)<div[^>]+class=["']videoInfo(?:Date|Time)\b[^>]*>(.+?)</div>''',
r'(?s)<label\b[^>]*>Uploaded[^<]*</label>\s*<span\b[^>]*>(.+?)</span>'),
webpage, 'upload date', fatal=False))
age_limit = self._rta_search(webpage)

699
youtube_dl/extractor/youtube.py
View File

File diff suppressed because it is too large Load Diff

197
youtube_dl/extractor/zdf.py
View File

@@ -7,13 +7,15 @@ from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
ExtractorError,
extract_attributes,
float_or_none,
int_or_none,
merge_dicts,
NO_DEFAULT,
orderedSet,
parse_codecs,
qualities,
str_or_none,
try_get,
unified_timestamp,
update_url_query,
@@ -56,28 +58,39 @@ class ZDFBaseIE(InfoExtractor):
format_urls.add(format_url)
mime_type = meta.get('mimeType')
ext = determine_ext(format_url)
join_nonempty = lambda s, l: s.join(filter(None, l))
meta_map = lambda t: map(lambda x: str_or_none(meta.get(x)), t)
if mime_type == 'application/x-mpegURL' or ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
new_formats = self._extract_m3u8_formats(
format_url, video_id, 'mp4', m3u8_id='hls',
entry_protocol='m3u8_native', fatal=False))
entry_protocol='m3u8_native', fatal=False)
elif mime_type == 'application/f4m+xml' or ext == 'f4m':
formats.extend(self._extract_f4m_formats(
update_url_query(format_url, {'hdcore': '3.7.0'}), video_id, f4m_id='hds', fatal=False))
new_formats = self._extract_f4m_formats(
update_url_query(format_url, {'hdcore': '3.7.0'}), video_id, f4m_id='hds', fatal=False)
else:
f = parse_codecs(meta.get('mimeCodec'))
if not f:
data = meta.get('type', '').split('_')
if try_get(data, lambda x: x[2]) == ext:
f = dict(zip(('vcodec', 'acodec'), data[1]))
format_id = ['http']
for p in (meta.get('type'), meta.get('quality')):
if p and isinstance(p, compat_str):
format_id.append(p)
format_id.extend(join_nonempty('-', meta_map(('type', 'quality'))))
f.update({
'url': format_url,
'format_id': '-'.join(format_id),
'format_note': meta.get('quality'),
'language': meta.get('language'),
'quality': qualities(self._QUALITIES)(meta.get('quality')),
'preference': -10,
'tbr': int_or_none(self._search_regex(r'_(\d+)k_', format_url, 'tbr', default=None))
})
formats.append(f)
new_formats = [f]
formats.extend(merge_dicts(f, {
'format_note': join_nonempty(',', meta_map(('quality', 'class'))),
'language': meta.get('language'),
'language_preference': 10 if meta.get('class') == 'main' else -10 if meta.get('class') == 'ad' else -1,
'quality': qualities(self._QUALITIES)(meta.get('quality')),
}) for f in new_formats)
def _extract_ptmd(self, ptmd_url, video_id, api_token, referrer):
ptmd = self._call_api(
@@ -106,6 +119,7 @@ class ZDFBaseIE(InfoExtractor):
'type': f.get('type'),
'mimeType': f.get('mimeType'),
'quality': quality.get('quality'),
'class': track.get('class'),
'language': track.get('language'),
})
self._sort_formats(formats)
@@ -145,6 +159,7 @@ class ZDFIE(ZDFBaseIE):
'timestamp': 1613948400,
'upload_date': '20210221',
},
'skip': 'No longer available: "Diese Seite wurde leider nicht gefunden"',
}, {
# Same as https://www.3sat.de/film/ab-18/10-wochen-sommer-108.html
'url': 'https://www.zdf.de/dokumentation/ab-18/10-wochen-sommer-102.html',
@@ -158,6 +173,7 @@ class ZDFIE(ZDFBaseIE):
'timestamp': 1608604200,
'upload_date': '20201222',
},
'skip': 'No longer available: "Diese Seite wurde leider nicht gefunden"',
}, {
'url': 'https://www.zdf.de/dokumentation/terra-x/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100.html',
'info_dict': {
@@ -168,6 +184,20 @@ class ZDFIE(ZDFBaseIE):
'duration': 2615,
'timestamp': 1465021200,
'upload_date': '20160604',
'thumbnail': 'https://www.zdf.de/assets/mauve-im-labor-100~768x432?cb=1464909117806',
},
}, {
'url': 'https://www.zdf.de/funk/druck-11790/funk-alles-ist-verzaubert-102.html',
'md5': '1b93bdec7d02fc0b703c5e7687461628',
'info_dict': {
'ext': 'mp4',
'id': 'video_funk_1770473',
'duration': 1278,
'description': 'Die Neue an der Schule verdreht Ismail den Kopf.',
'title': 'Alles ist verzaubert',
'timestamp': 1635520560,
'upload_date': '20211029',
'thumbnail': 'https://www.zdf.de/assets/teaser-funk-alles-ist-verzaubert-100~1920x1080?cb=1636466431799',
},
}, {
# Same as https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche
@@ -190,6 +220,30 @@ class ZDFIE(ZDFBaseIE):
}, {
'url': 'https://www.zdf.de/dokumentation/planet-e/planet-e-uebersichtsseite-weitere-dokumentationen-von-planet-e-100.html',
'only_matching': True,
}, {
'url': 'https://www.zdf.de/arte/todliche-flucht/page-video-artede-toedliche-flucht-16-100.html',
'info_dict': {
'id': 'video_artede_083871-001-A',
'ext': 'mp4',
'title': 'Tödliche Flucht (1/6)',
'description': 'md5:e34f96a9a5f8abd839ccfcebad3d5315',
'duration': 3193.0,
'timestamp': 1641355200,
'upload_date': '20220105',
},
'skip': 'No longer available "Diese Seite wurde leider nicht gefunden"'
}, {
'url': 'https://www.zdf.de/serien/soko-stuttgart/das-geld-anderer-leute-100.html',
'info_dict': {
'id': '191205_1800_sendung_sok8',
'ext': 'mp4',
'title': 'Das Geld anderer Leute',
'description': 'md5:cb6f660850dc5eb7d1ab776ea094959d',
'duration': 2581.0,
'timestamp': 1654790700,
'upload_date': '20220609',
'thumbnail': 'https://epg-image.zdf.de/fotobase-webdelivery/images/e2d7e55a-09f0-424e-ac73-6cac4dd65f35?layout=2400x1350',
},
}]
def _extract_entry(self, url, player, content, video_id):
@@ -197,12 +251,18 @@ class ZDFIE(ZDFBaseIE):
t = content['mainVideoContent']['http://zdf.de/rels/target']
ptmd_path = t.get('http://zdf.de/rels/streams/ptmd')
def get_ptmd_path(d):
return (
d.get('http://zdf.de/rels/streams/ptmd')
or d.get('http://zdf.de/rels/streams/ptmd-template',
'').replace('{playerId}', 'ngplayer_2_4'))
ptmd_path = get_ptmd_path(try_get(t, lambda x: x['streams']['default'], dict) or {})
if not ptmd_path:
ptmd_path = get_ptmd_path(t)
if not ptmd_path:
ptmd_path = t[
'http://zdf.de/rels/streams/ptmd-template'].replace(
'{playerId}', 'ngplayer_2_4')
raise ExtractorError('Could not extract ptmd_path')
info = self._extract_ptmd(
urljoin(url, ptmd_path), video_id, player['apiToken'], url)
@@ -245,15 +305,16 @@ class ZDFIE(ZDFBaseIE):
'https://zdf-cdn.live.cellular.de/mediathekV2/document/%s' % video_id,
video_id)
document = video['document']
title = document['titel']
content_id = document['basename']
formats = []
format_urls = set()
for f in document['formitaeten']:
self._extract_format(content_id, formats, format_urls, f)
formitaeten = try_get(video, lambda x: x['document']['formitaeten'], list)
document = formitaeten and video['document']
if formitaeten:
title = document['titel']
content_id = document['basename']
format_urls = set()
for f in formitaeten or []:
self._extract_format(content_id, formats, format_urls, f)
self._sort_formats(formats)
thumbnails = []
@@ -300,9 +361,9 @@ class ZDFChannelIE(ZDFBaseIE):
'url': 'https://www.zdf.de/sport/das-aktuelle-sportstudio',
'info_dict': {
'id': 'das-aktuelle-sportstudio',
'title': 'das aktuelle sportstudio | ZDF',
'title': 'das aktuelle sportstudio',
},
'playlist_mincount': 23,
'playlist_mincount': 18,
}, {
'url': 'https://www.zdf.de/dokumentation/planet-e',
'info_dict': {
@@ -310,6 +371,14 @@ class ZDFChannelIE(ZDFBaseIE):
'title': 'planet e.',
},
'playlist_mincount': 50,
}, {
'url': 'https://www.zdf.de/gesellschaft/aktenzeichen-xy-ungeloest',
'info_dict': {
'id': 'aktenzeichen-xy-ungeloest',
'title': 'Aktenzeichen XY... ungelöst',
'entries': "lambda x: not any('xy580-fall1-kindermoerder-gesucht-100' in e['url'] for e in x)",
},
'playlist_mincount': 2,
}, {
'url': 'https://www.zdf.de/filme/taunuskrimi/',
'only_matching': True,
@@ -319,60 +388,36 @@ class ZDFChannelIE(ZDFBaseIE):
def suitable(cls, url):
return False if ZDFIE.suitable(url) else super(ZDFChannelIE, cls).suitable(url)
def _og_search_title(self, webpage, fatal=False):
title = super(ZDFChannelIE, self)._og_search_title(webpage, fatal=fatal)
return re.split(r'\s+[-|]\s+ZDF(?:mediathek)?$', title or '')[0] or None
def _real_extract(self, url):
channel_id = self._match_id(url)
webpage = self._download_webpage(url, channel_id)
entries = [
self.url_result(item_url, ie=ZDFIE.ie_key())
for item_url in orderedSet(re.findall(
r'data-plusbar-url=["\'](http.+?\.html)', webpage))]
matches = re.finditer(
r'''<div\b[^>]*?\sdata-plusbar-id\s*=\s*(["'])(?P<p_id>[\w-]+)\1[^>]*?\sdata-plusbar-url=\1(?P<url>%s)\1''' % ZDFIE._VALID_URL,
webpage)
return self.playlist_result(
entries, channel_id, self._og_search_title(webpage, fatal=False))
if self._downloader.params.get('noplaylist', False):
entry = next(
(self.url_result(m.group('url'), ie=ZDFIE.ie_key()) for m in matches),
None)
self.to_screen('Downloading just the main video because of --no-playlist')
if entry:
return entry
else:
self.to_screen('Downloading playlist %s - add --no-playlist to download just the main video' % (channel_id, ))
r"""
player = self._extract_player(webpage, channel_id)
def check_video(m):
v_ref = self._search_regex(
r'''(<a\b[^>]*?\shref\s*=[^>]+?\sdata-target-id\s*=\s*(["'])%s\2[^>]*>)''' % (m.group('p_id'), ),
webpage, 'check id', default='')
v_ref = extract_attributes(v_ref)
return v_ref.get('data-target-video-type') != 'novideo'
channel_id = self._search_regex(
r'docId\s*:\s*(["\'])(?P<id>(?!\1).+?)\1', webpage,
'channel id', group='id')
channel = self._call_api(
'https://api.zdf.de/content/documents/%s.json' % channel_id,
player, url, channel_id)
items = []
for module in channel['module']:
for teaser in try_get(module, lambda x: x['teaser'], list) or []:
t = try_get(
teaser, lambda x: x['http://zdf.de/rels/target'], dict)
if not t:
continue
items.extend(try_get(
t,
lambda x: x['resultsWithVideo']['http://zdf.de/rels/search/results'],
list) or [])
items.extend(try_get(
module,
lambda x: x['filterRef']['resultsWithVideo']['http://zdf.de/rels/search/results'],
list) or [])
entries = []
entry_urls = set()
for item in items:
t = try_get(item, lambda x: x['http://zdf.de/rels/target'], dict)
if not t:
continue
sharing_url = t.get('http://zdf.de/rels/sharing-url')
if not sharing_url or not isinstance(sharing_url, compat_str):
continue
if sharing_url in entry_urls:
continue
entry_urls.add(sharing_url)
entries.append(self.url_result(
sharing_url, ie=ZDFIE.ie_key(), video_id=t.get('id')))
return self.playlist_result(entries, channel_id, channel.get('title'))
"""
return self.playlist_from_matches(
(m.group('url') for m in matches if check_video(m)),
channel_id, self._og_search_title(webpage, fatal=False))