Compare commits

...

8 Commits

Author SHA1 Message Date
dirkf
4343d76f61
Merge da90df06c3b8e7e6cc66a124c196aef4eb856a89 into 4e714f9df1ed2cccd51df60d45ff5504abe827b7 2025-03-29 23:54:47 +08:00
dirkf
4e714f9df1 [Misc] Correct [_]IE_DESC/NAME in a few IEs
* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`
2025-03-26 12:47:19 +00:00
dirkf
c1ea7f5a24 [ITV] Mark ITVX not working
* update old shim
* correct [_]IE_DESC
2025-03-26 12:17:49 +00:00
dirkf
da90df06c3
Linty 2024-11-29 14:27:29 +00:00
dirkf
98e6231a25
Further small improvements 2024-11-29 14:17:10 +00:00
dirkf
ab9ad567d8
Incorporate changes from PR #32979
* update tests
* send `Referer` when fetching media link

Co-authored-by: mp3butcher <julienvalentin51@gmail.com>
2024-11-29 14:11:41 +00:00
dirkf
9dd91758ae [DoodStream] Support more TLDs
* also fix title extraction
2022-06-04 09:26:41 +01:00
dirkf
3687a4f9bd [DoodStream] Add extractor from yt-dlp back-port and improve 2022-06-04 08:19:09 +01:00
7 changed files with 143 additions and 15 deletions

View File

@ -32,7 +32,7 @@ class BokeCCBaseIE(InfoExtractor):
class BokeCCIE(BokeCCBaseIE): class BokeCCIE(BokeCCBaseIE):
_IE_DESC = 'CC视频' IE_DESC = 'CC视频'
_VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)' _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
_TESTS = [{ _TESTS = [{

View File

@ -9,7 +9,7 @@ from ..utils import (
class CloudyIE(InfoExtractor): class CloudyIE(InfoExtractor):
_IE_DESC = 'cloudy.ec' IE_DESC = 'cloudy.ec'
_VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)' _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://www.cloudy.ec/v/af511e2527aac', 'url': 'https://www.cloudy.ec/v/af511e2527aac',

View File

@ -422,6 +422,8 @@ class InfoExtractor(object):
_GEO_COUNTRIES = None _GEO_COUNTRIES = None
_GEO_IP_BLOCKS = None _GEO_IP_BLOCKS = None
_WORKING = True _WORKING = True
# supply this in public subclasses: used in supported sites list, etc
# IE_DESC = 'short description of IE'
def __init__(self, downloader=None): def __init__(self, downloader=None):
"""Constructor. Receives an optional downloader.""" """Constructor. Receives an optional downloader."""

View File

@ -0,0 +1,132 @@
# coding: utf-8
from __future__ import unicode_literals
from random import choice as random_choice
from string import ascii_letters, digits
from time import time as time_time
from ..compat import compat_filter as filter
from ..utils import (
clean_html,
ExtractorError,
get_element_by_class,
parse_duration,
parse_filesize,
update_url_query,
unified_strdate,
url_or_none,
)
from .common import InfoExtractor
class DoodStreamIE(InfoExtractor):
# dood.* redirects
# .watch -> .re (but HEAD request fails in GenericIE)
# .so -> .li
_VALID_URL = r'https?://(?:www\.)?(?P<host>dood\.(?:to|la|li|pm|re|sh|watch|ws|one)|ds2play\.com)/[ed]/(?P<id>[a-z\d]+)'
_TESTS = [{
'url': 'https://dood.li/e/h7ecgw5oqn8k',
'md5': '90f2af170551c17fc78bee7426890054',
'info_dict': {
'id': 'h7ecgw5oqn8k',
'ext': 'mp4',
'title': 'Free-Slow-Music',
'upload_date': '20230814',
'thumbnail': 'https://img.doodcdn.co/splash/7mbnwydhb6kb7xyk.jpg',
},
}, {
'url': 'https://dood.to/d/is34uy8wvaet',
'md5': '04740d3ba93bcd638aa7a097d9226710',
'info_dict': {
'id': 'is34uy8wvaet',
'ext': 'mp4',
'title': 'Akhanda (2021) Telugu DVDScr MP3 700MB',
'upload_date': '20211202',
'thumbnail': r're:https?://img\.doodcdn\.com?/[\w/]+\.jpg',
'filesize_approx': int,
'duration': 9886,
},
'skip': 'Video not found',
}, {
'url': 'https://dood.sh/d/wlihoael8uog',
'md5': '2c14444c89788cc309738c1560abe278',
'info_dict': {
'id': 'wlihoael8uog',
'ext': 'mp4',
'title': 'VID 20220319 161659',
'thumbnail': r're:https?://img\.doodcdn\.com?/splash/rmpnhb8ckkk79cge\.jpg',
'upload_date': '20220319',
'filesize_approx': int,
'duration': 12.0,
},
}, {
'url': 'http://dood.ws/d/h7ecgw5oqn8k',
'only_matching': True,
}, {
'url': 'https://dood.li/d/wlihoael8uog',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
host = 'dood.li'
url = 'https://%s/e/%s' % (host, video_id)
webpage = self._download_webpage(url, video_id, note='Downloading "/e/" webpage')
def get_title(html, fatal=False):
return self._html_search_regex(r'<title\b[^>]*>([^<]+?)(?:[|-]\s+DoodStream\s*)?</title', html, 'title', fatal=fatal)
title = get_title(webpage)
if title == 'Video not found' or (
title == '' and 'Not Found' == self._html_search_regex(r'<h1\b[^>]*>([^<]+?)</h1', webpage, 'heading1', default=None)):
raise ExtractorError(title, expected=True)
pass_md5, token = self._search_regex(
r'["\']/(?P<pm>pass_md5/[\da-f-]+/(?P<tok>[\da-z]+))', webpage, 'tokens',
group=('pm', 'tok'))
headers = {
'Referer': url,
}
# construct the media link
final_url = self._download_webpage(
'https://%s/%s' % (host, pass_md5), video_id, headers={
'Referer': url,
}, note='Downloading authpage URL')
final_url += ''.join((random_choice(ascii_letters + digits)
for _ in range(10)))
final_url = update_url_query(final_url, {
'token': token,
'expiry': int(time_time() * 1000),
})
# get additional metadata
thumb = next(filter(None, (url_or_none(self._html_search_meta(x, webpage, default=None))
for x in ('og:image', 'twitter:image'))), None)
description = self._html_search_meta(
('og:description', 'description', 'twitter:description'), webpage, default=None)
webpage = self._download_webpage(
'https://%s/d/%s' % (host, video_id), video_id, fatal=False,
note='Downloading alternative "/d/" page') or ''
title = (
self._html_search_meta(('og:title', 'twitter:title'), webpage, default=None)
or get_title(webpage, fatal=(title is not None))
or title)
def get_class_text(x):
return clean_html(get_element_by_class(x, webpage))
return {
'id': video_id,
'title': title,
'url': final_url,
'http_headers': headers,
'ext': 'mp4',
'upload_date': unified_strdate(get_class_text('uploadate')),
'duration': parse_duration(get_class_text('length')),
'filesize_approx': parse_filesize(get_class_text('size')),
'description': description,
'thumbnail': thumb,
}

View File

@ -304,6 +304,7 @@ from .dlf import (
from .dfb import DFBIE from .dfb import DFBIE
from .dhm import DHMIE from .dhm import DHMIE
from .digg import DiggIE from .digg import DiggIE
from .doodstream import DoodStreamIE
from .dotsub import DotsubIE from .dotsub import DotsubIE
from .douyutv import ( from .douyutv import (
DouyuShowIE, DouyuShowIE,

View File

@ -35,15 +35,6 @@ from ..utils import (
class ITVBaseIE(InfoExtractor): 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): def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
if errnote is False: if errnote is False:
return False return False
@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
class ITVIE(ITVBaseIE): class ITVIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)' _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
_IE_DESC = 'ITVX' IE_DESC = 'ITVX'
_WORKING = False
_TESTS = [{ _TESTS = [{
'note': 'Hub URLs redirect to ITVX', 'note': 'Hub URLs redirect to ITVX',
'url': 'https://www.itv.com/hub/liar/2a4547a0012', 'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
'ext': determine_ext(href, 'vtt'), 'ext': determine_ext(href, 'vtt'),
}) })
next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}') 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 {}) video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
title = traverse_obj(video_data, 'headerTitle', 'episodeTitle') title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
info = self._og_extract(webpage, require_title=not title) info = self._og_extract(webpage, require_title=not title)
@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
class ITVBTCCIE(ITVBaseIE): class ITVBTCCIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
_IE_DESC = 'ITV articles: News, British Touring Car Championship' IE_DESC = 'ITV articles: News, British Touring Car Championship'
_TESTS = [{ _TESTS = [{
'note': 'British Touring Car Championship', 'note': 'British Touring Car Championship',
'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch', 'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

View File

@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
['vetaff', '76462', 'http://vetaff-f.akamaihd.net'], ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
['arch', '', 'http://ussenate-f.akamaihd.net/'] ['arch', '', 'http://ussenate-f.akamaihd.net/']
] ]
_IE_NAME = 'senate.gov' IE_NAME = 'senate.gov'
_VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)' _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png', 'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',