Compare commits

...

5 Commits

Author SHA1 Message Date
cypheron
17f78a1467
Merge a66ef4baaceb9f3104dfb031e96269ffc72ae70c into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6 2025-04-01 11:17:35 +02:00
dirkf
3eb8d22ddb
[JSInterp] Temporary fix for #33102 2025-03-31 04:21:09 +01:00
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
cypheron
a66ef4baac [hse24] Add new extractor 2020-11-19 13:48:47 +01:00
8 changed files with 108 additions and 15 deletions

View File

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

View File

@ -9,7 +9,7 @@ from ..utils import (
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]+)'
_TESTS = [{
'url': 'https://www.cloudy.ec/v/af511e2527aac',

View File

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

View File

@ -499,6 +499,7 @@ from .hrti import (
HRTiIE,
HRTiPlaylistIE,
)
from .hse24 import HSE24IE
from .huajiao import HuajiaoIE
from .huffpost import HuffPostIE
from .hungama import (

View File

@ -0,0 +1,95 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from time import mktime, strptime
class HSE24IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hse24\.de/dpl/(?:p/product|c/tv-shows)?/(?P<id>[0-9]+)'
_GEO_COUNTRIES = ['DE']
_TESTS = [{
'url': 'https://www.hse24.de/dpl/c/tv-shows/476357',
'info_dict': {
'id': '476357',
'ext': 'mp4',
'title': 'Jürgen Hirsch Schuhe zum Wohlfühlen',
'timestamp': 1604926800,
'upload_date': '20201109',
'channel': 'HSE24EXTRA',
'uploader': 'Daniela Elger'
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.hse24.de/dpl/p/product/408630',
'info_dict': {
'id': '408630',
'ext': 'mp4',
'title': 'Hose im Ponte-Mix',
'timestamp': 1603058400,
'upload_date': '20201018',
'channel': 'HSE24',
'uploader': 'Judith Williams'
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
json_str = self._html_search_regex(r'window\.__REDUX_DATA__ = ({.*});?', webpage, 'json_str')
json_str = json_str.replace('\n', '')
json_data = self._parse_json(json_str, video_id)
formats = []
if 'tvShow' in json_data: # /dpl/c/tv-shows
show = json_data['tvShow']['tvShow']
title, date, hour, uploader = show['title'], show['date'], show['hour'], show['presenter']
channel = self._search_regex(r'tvShow \| ([A-Z0-9]+)_', show['actionFieldText'], video_id)
timestamp = mktime(strptime(' '.join((date, hour)), '%Y-%m-%d %H'))
video = json_data['tvShow']['tvShowVideo']
thumbnail = video['poster']
sources = video['sources']
for src in sources:
if src['mimetype'] == 'application/x-mpegURL':
formats.extend(self._extract_m3u8_formats(src['url'], video_id, ext='mp4'))
elif 'productDetail' in json_data: # /dpl/p/product
product = json_data['productDetail']['product']
title, uploader = product['name']['short'], product['brand']['brandName']
channel = 'HSE24'
default_time = '2001-01-01T01:01:01+0100'
time = product['variants'][0]['price']['validFrom'] if len(product['variants']) > 0 else default_time
# python2 compatibility (no %z directive support)
time = strptime(time[:-6], '%Y-%m-%dT%H:%M:%S')
if time[-6] == '+':
time += strptime(time[-6:], '%H:%M')
elif time[-6] == '-':
time -= strptime(time[-6:], '%H:%M')
timestamp = mktime(time)
for video in json_data['productContent']['productContent']['videos']:
thumbnail = video['poster']
sources = video['sources']
for src in sources:
if src['mimetype'] == 'application/x-mpegURL':
formats.extend(self._extract_m3u8_formats(src['url'], video_id, ext='mp4'))
# elif src['mimetype'] == 'video/mp4':
# formats.append({'url': src['url']})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'formats': formats,
'timestamp': int(timestamp),
'thumbnail': thumbnail,
'channel': channel,
'uploader': uploader
}

View File

@ -35,15 +35,6 @@ from ..utils import (
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
@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
class ITVIE(ITVBaseIE):
_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 = [{
'note': 'Hub URLs redirect to ITVX',
'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
'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 {})
title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
info = self._og_extract(webpage, require_title=not title)
@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
class ITVBTCCIE(ITVBaseIE):
_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 = [{
'note': 'British Touring Car Championship',
'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'],
['arch', '', 'http://ussenate-f.akamaihd.net/']
]
_IE_NAME = 'senate.gov'
IE_NAME = 'senate.gov'
_VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
_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',

View File

@ -686,6 +686,8 @@ class JSInterpreter(object):
raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
def _dump(self, obj, namespace):
if obj is JS_Undefined:
return 'undefined'
try:
return json.dumps(obj)
except TypeError: