artem/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-04-29 03:55:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

[ie/ZDF] Fix extractor after website redesign

Browse Source
This commit is contained in:
InvalidUsernameException 2025-03-29 20:30:15 +01:00
parent 6a6d97b2cb
commit 5b7b2e7cf4
4 changed files with 562 additions and 397 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
yt_dlp/extractor/_extractors.py
View File

@ -2601,7 +2601,7 @@ from .zattoo import (
) )
from .zdf import ( from .zdf import (
ZDFIE, ZDFIE,
ZDFChannelIE, ZDFCollectionIE,
) )
from .zee5 import ( from .zee5 import (
Zee5IE, Zee5IE,

121
yt_dlp/extractor/dreisat.py
View File

@ -1,4 +1,13 @@
from .zdf import ZDFBaseIE from .zdf import ZDFBaseIE
from ..utils import (
NO_DEFAULT,
ExtractorError,
int_or_none,
merge_dicts,
traverse_obj,
try_get,
unified_timestamp,
)
class DreiSatIE(ZDFBaseIE): class DreiSatIE(ZDFBaseIE):
@ -12,40 +21,42 @@ class DreiSatIE(ZDFBaseIE):
'title': 'Traumziele Südostasiens (1/2): Die Philippinen und Vietnam', 'title': 'Traumziele Südostasiens (1/2): Die Philippinen und Vietnam',
'description': 'md5:26329ce5197775b596773b939354079d', 'description': 'md5:26329ce5197775b596773b939354079d',
'duration': 2625.0, 'duration': 2625.0,
'thumbnail': 'https://www.3sat.de/assets/traumziele-suedostasiens-die-philippinen-und-vietnam-100~2400x1350?cb=1699870351148', 'thumbnail': 'https://www.3sat.de/assets/traumziele-suedostasiens-die-philippinen-und-vietnam-100~original?cb=1699870351148',
'episode': 'Traumziele Südostasiens (1/2): Die Philippinen und Vietnam', 'episode': 'Traumziele Südostasiens (1/2): Die Philippinen und Vietnam',
'episode_id': 'POS_cc7ff51c-98cf-4d12-b99d-f7a551de1c95', 'episode_id': 'POS_cc7ff51c-98cf-4d12-b99d-f7a551de1c95',
'timestamp': 1738593000, 'timestamp': 1738593000,
'upload_date': '20250203', 'upload_date': '20250203',
}, },
}, { }, {
# Same as https://www.zdf.de/dokumentation/ab-18/10-wochen-sommer-102.html 'url': 'https://www.3sat.de/film/ab-18/ab-18---mein-fremdes-ich-100.html',
'url': 'https://www.3sat.de/film/ab-18/10-wochen-sommer-108.html', 'md5': '66cb9013ce37f6e008dc99bfcf1356bc',
'md5': '0aff3e7bc72c8813f5e0fae333316a1d',
'info_dict': { 'info_dict': {
'id': '141007_ab18_10wochensommer_film', 'id': '221128_mein_fremdes_ich2_ab18',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Ab 18! - 10 Wochen Sommer', 'title': 'Ab 18! - Mein fremdes Ich',
'description': 'md5:8253f41dc99ce2c3ff892dac2d65fe26', 'description': 'md5:cae0c0b27b7426d62ca0dda181738bf0',
'duration': 2660, 'duration': 2625.0,
'timestamp': 1608604200, 'thumbnail': 'https://www.3sat.de/assets/ab-18---mein-fremdes-ich-106~original?cb=1666081865812',
'upload_date': '20201222', 'episode': 'Ab 18! - Mein fremdes Ich',
'episode_id': 'POS_6225d1ca-a0d5-45e3-870b-e783ee6c8a3f',
'timestamp': 1695081600,
'upload_date': '20230919',
}, },
'skip': '410 Gone',
}, { }, {
'url': 'https://www.3sat.de/gesellschaft/schweizweit/waidmannsheil-100.html', 'url': 'https://www.3sat.de/gesellschaft/37-grad-leben/aus-dem-leben-gerissen-102.html',
'md5': '69f276184c9a24147e4baae728fbc3c4',
'info_dict': { 'info_dict': {
'id': '140913_sendung_schweizweit', 'id': '250323_0903_sendung_sgl',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Waidmannsheil', 'title': 'Plötzlich ohne dich',
'description': 'md5:cce00ca1d70e21425e72c86a98a56817', 'description': 'md5:380cc10659289dd91510ad8fa717c66b',
'timestamp': 1410623100, 'duration': 1620.0,
'upload_date': '20140913', 'thumbnail': 'https://www.3sat.de/assets/37-grad-leben-106~original?cb=1645537156810',
'episode': 'Plötzlich ohne dich',
'episode_id': 'POS_faa7a93c-c0f2-4d51-823f-ce2ac3ee191b',
'timestamp': 1743162540,
'upload_date': '20250328',
}, },
'params': {
'skip_download': True,
},
'skip': '404 Not Found',
}, { }, {
# Same as https://www.zdf.de/filme/filme-sonstige/der-hauptmann-112.html # Same as https://www.zdf.de/filme/filme-sonstige/der-hauptmann-112.html
'url': 'https://www.3sat.de/film/spielfilm/der-hauptmann-100.html', 'url': 'https://www.3sat.de/film/spielfilm/der-hauptmann-100.html',
@ -56,13 +67,67 @@ class DreiSatIE(ZDFBaseIE):
'only_matching': True, 'only_matching': True,
}] }]
def _extract_player(self, webpage, video_id, fatal=True):
return self._parse_json(
self._search_regex(
r'(?s)data-zdfplayer-jsb=(["\'])(?P<json>{.+?})\1', webpage,
'player JSON', default='{}' if not fatal else NO_DEFAULT,
group='json'),
video_id)
def _extract_regular(self, url, player, video_id):
player_url = player['content']
api_token = f'Bearer {player["apiToken"]}'
content = self._call_api(player_url, video_id, 'video metadata', api_token)
return self._extract_entry(player_url, api_token, content, video_id)
def _extract_entry(self, url, api_token, content, video_id):
title = content.get('title') or content['teaserHeadline']
t = content['mainVideoContent']['http://zdf.de/rels/target']
ptmd_path = traverse_obj(t, (
(('streams', 'default'), None),
('http://zdf.de/rels/streams/ptmd', 'http://zdf.de/rels/streams/ptmd-template'),
), get_all=False)
if not ptmd_path:
raise ExtractorError('Could not extract ptmd_path')
info = self._extract_ptmd(url, ptmd_path, video_id, api_token)
layouts = try_get(
content, lambda x: x['teaserImageRef']['layouts'], dict)
thumbnails = self._extract_thumbnails(layouts)
chapter_marks = t.get('streamAnchorTag') or []
chapter_marks.append({'anchorOffset': int_or_none(t.get('duration'))})
chapters = [{
'start_time': chap.get('anchorOffset'),
'end_time': next_chap.get('anchorOffset'),
'title': chap.get('anchorLabel'),
} for chap, next_chap in zip(chapter_marks, chapter_marks[1:])]
return merge_dicts(info, {
'title': title,
'description': content.get('leadParagraph') or content.get('teasertext'),
'duration': int_or_none(t.get('duration')),
'timestamp': unified_timestamp(content.get('editorialDate')),
'thumbnails': thumbnails,
'chapters': chapters or None,
'episode': title,
**traverse_obj(content, ('programmeItem', 0, 'http://zdf.de/rels/target', {
'series_id': ('http://zdf.de/rels/cmdm/series', 'seriesUuid', {str}),
'series': ('http://zdf.de/rels/cmdm/series', 'seriesTitle', {str}),
'season': ('http://zdf.de/rels/cmdm/season', 'seasonTitle', {str}),
'season_number': ('http://zdf.de/rels/cmdm/season', 'seasonNumber', {int_or_none}),
'season_id': ('http://zdf.de/rels/cmdm/season', 'seasonUuid', {str}),
'episode_number': ('episodeNumber', {int_or_none}),
'episode_id': ('contentId', {str}),
})),
})
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id, fatal=False) webpage = self._download_webpage(url, video_id)
if webpage: player = self._extract_player(webpage, url)
player = self._extract_player(webpage, url, fatal=False) return self._extract_regular(url, player, video_id)
if player:
return self._extract_regular(url, player, video_id)
return self._extract_mobile(video_id)

60
yt_dlp/extractor/phoenix.py
View File

@ -1,5 +1,3 @@
import re
from .youtube import YoutubeIE from .youtube import YoutubeIE
from .zdf import ZDFBaseIE from .zdf import ZDFBaseIE
from ..utils import ( from ..utils import (
@ -7,7 +5,6 @@ from ..utils import (
merge_dicts, merge_dicts,
try_get, try_get,
unified_timestamp, unified_timestamp,
urljoin,
) )
@ -15,36 +12,20 @@ class PhoenixIE(ZDFBaseIE):
IE_NAME = 'phoenix.de' IE_NAME = 'phoenix.de'
_VALID_URL = r'https?://(?:www\.)?phoenix\.de/(?:[^/]+/)*[^/?#&]*-a-(?P<id>\d+)\.html' _VALID_URL = r'https?://(?:www\.)?phoenix\.de/(?:[^/]+/)*[^/?#&]*-a-(?P<id>\d+)\.html'
_TESTS = [{ _TESTS = [{
# Same as https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html 'url': 'https://www.phoenix.de/sendungen/dokumentationen/spitzbergen-a-893349.html',
'url': 'https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html', 'md5': '768bbcd67a51fbfb22263ecdbc49146d',
'md5': '34ec321e7eb34231fd88616c65c92db0',
'info_dict': { 'info_dict': {
'id': '210222_phx_nachgehakt_corona_protest', 'id': '221215_phx_spitzbergen',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Wohin führt der Protest in der Pandemie?', 'title': 'Spitzbergen',
'description': 'md5:7d643fe7f565e53a24aac036b2122fbd', 'description': 'Film von Tilmann Bünz',
'duration': 1691, 'duration': 728.0,
'timestamp': 1613902500, 'timestamp': 1555600500,
'upload_date': '20210221', 'upload_date': '20190418',
'uploader': 'Phoenix', 'uploader': 'Phoenix',
'series': 'corona nachgehakt', 'thumbnail': 'https://www.phoenix.de/sixcms/media.php/21/Bergspitzen1.png',
'episode': 'Wohin führt der Protest in der Pandemie?', 'series': 'Dokumentationen',
}, 'episode': 'Spitzbergen',
}, {
# Youtube embed
'url': 'https://www.phoenix.de/sendungen/gespraeche/phoenix-streitgut-brennglas-corona-a-1965505.html',
'info_dict': {
'id': 'hMQtqFYjomk',
'ext': 'mp4',
'title': 'phoenix streitgut: Brennglas Corona - Wie gerecht ist unsere Gesellschaft?',
'description': 'md5:ac7a02e2eb3cb17600bc372e4ab28fdd',
'duration': 3509,
'upload_date': '20201219',
'uploader': 'phoenix',
'uploader_id': 'phoenix',
},
'params': {
'skip_download': True,
}, },
}, { }, {
'url': 'https://www.phoenix.de/entwicklungen-in-russland-a-2044720.html', 'url': 'https://www.phoenix.de/entwicklungen-in-russland-a-2044720.html',
@ -90,8 +71,9 @@ class PhoenixIE(ZDFBaseIE):
content_id = details['tracking']['nielsen']['content']['assetid'] content_id = details['tracking']['nielsen']['content']['assetid']
info = self._extract_ptmd( info = self._extract_ptmd(
f'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/{content_id}', 'https://tmd.phoenix.de',
content_id, None, url) f'tmd/2/{{playerId}}/vod/ptmd/phoenix/{content_id}',
content_id)
duration = int_or_none(try_get( duration = int_or_none(try_get(
details, lambda x: x['tracking']['nielsen']['content']['length'])) details, lambda x: x['tracking']['nielsen']['content']['length']))
@ -101,20 +83,8 @@ class PhoenixIE(ZDFBaseIE):
str) str)
episode = title if details.get('contentType') == 'episode' else None episode = title if details.get('contentType') == 'episode' else None
thumbnails = []
teaser_images = try_get(details, lambda x: x['teaserImageRef']['layouts'], dict) or {} teaser_images = try_get(details, lambda x: x['teaserImageRef']['layouts'], dict) or {}
for thumbnail_key, thumbnail_url in teaser_images.items(): thumbnails = self._extract_thumbnails(teaser_images)
thumbnail_url = urljoin(url, thumbnail_url)
if not thumbnail_url:
continue
thumbnail = {
'url': thumbnail_url,
}
m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
if m:
thumbnail['width'] = int(m.group(1))
thumbnail['height'] = int(m.group(2))
thumbnails.append(thumbnail)
return merge_dicts(info, { return merge_dicts(info, {
'id': content_id, 'id': content_id,

776
yt_dlp/extractor/zdf.py
View File

@ -1,8 +1,9 @@
import json
import re import re
import time
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
NO_DEFAULT,
ExtractorError, ExtractorError,
determine_ext, determine_ext,
float_or_none, float_or_none,
@ -10,13 +11,15 @@ from ..utils import (
join_nonempty, join_nonempty,
merge_dicts, merge_dicts,
parse_codecs, parse_codecs,
parse_iso8601,
parse_qs,
qualities, qualities,
traverse_obj, traverse_obj,
try_get, try_get,
unified_timestamp,
update_url_query, update_url_query,
url_or_none, url_or_none,
urljoin, urljoin,
variadic,
) )
@ -24,30 +27,25 @@ class ZDFBaseIE(InfoExtractor):
_GEO_COUNTRIES = ['DE'] _GEO_COUNTRIES = ['DE']
_QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh', 'hd', 'fhd', 'uhd') _QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh', 'hd', 'fhd', 'uhd')
def _download_v2_doc(self, document_id): def _call_api(self, url, video_id, item, api_token=None):
headers = {'Api-Auth': api_token} if api_token else {}
return self._download_json( return self._download_json(
f'https://zdf-prod-futura.zdf.de/mediathekV2/document/{document_id}', url, video_id, note=f'Downloading {item}',
document_id) errnote=f'Failed to download {item}', headers=headers)
def _call_api(self, url, video_id, item, api_token=None, referrer=None):
headers = {}
if api_token:
headers['Api-Auth'] = f'Bearer {api_token}'
if referrer:
headers['Referer'] = referrer
return self._download_json(
url, video_id, f'Downloading JSON {item}', headers=headers)
@staticmethod @staticmethod
def _extract_subtitles(src): def _extract_subtitles(src):
seen_urls = set()
subtitles = {} subtitles = {}
for caption in try_get(src, lambda x: x['captions'], list) or []: for caption in src:
subtitle_url = url_or_none(caption.get('uri')) subtitle_url = url_or_none(caption.get('uri'))
if subtitle_url: if not subtitle_url or subtitle_url in seen_urls:
lang = caption.get('language', 'deu') continue
subtitles.setdefault(lang, []).append({ seen_urls.add(subtitle_url)
'url': subtitle_url, lang = caption.get('language', 'deu')
}) subtitles.setdefault(lang, []).append({
'url': subtitle_url,
})
return subtitles return subtitles
def _extract_format(self, video_id, formats, format_urls, meta): def _extract_format(self, video_id, formats, format_urls, meta):
@ -86,246 +84,308 @@ class ZDFBaseIE(InfoExtractor):
'quality': qualities(self._QUALITIES)(meta.get('quality')), 'quality': qualities(self._QUALITIES)(meta.get('quality')),
}) for f in new_formats) }) for f in new_formats)
def _extract_ptmd(self, ptmd_url, video_id, api_token, referrer): def _extract_ptmd(self, api_base_url, templates, video_id, api_token=None):
ptmd = self._call_api( # TODO: HTTPS formats are extracted without resolution information
ptmd_url, video_id, 'metadata', api_token, referrer) # However, we know vertical resolution and the caller often knows apsect ratio.
# So we could calculate the correct resulution from those two data points.
content_id = ptmd.get('basename') or ptmd_url.split('/')[-1] templates = variadic(templates)
src_captions = []
content_id = None
duration = None
formats = [] formats = []
track_uris = set() track_uris = set()
for p in ptmd['priorityList']: for template in templates:
formitaeten = p.get('formitaeten') ptmd_url = urljoin(api_base_url, template.replace(
if not isinstance(formitaeten, list): '{playerId}', 'android_native_6'))
continue ptmd = self._call_api(ptmd_url, video_id, 'PTMD data', api_token)
for f in formitaeten: content_id = content_id or ptmd.get('basename') or ptmd_url.split('/')[-1]
f_qualities = f.get('qualities') duration = (duration or float_or_none(try_get(
if not isinstance(f_qualities, list): ptmd, lambda x: x['attributes']['duration']['value']), scale=1000))
src_captions += ptmd.get('captions') or []
for p in ptmd['priorityList']:
formitaeten = p.get('formitaeten')
if not isinstance(formitaeten, list):
continue continue
for quality in f_qualities: for f in formitaeten:
tracks = try_get(quality, lambda x: x['audio']['tracks'], list) f_qualities = f.get('qualities')
if not tracks: if not isinstance(f_qualities, list):
continue continue
for track in tracks: for quality in f_qualities:
self._extract_format( tracks = try_get(quality, lambda x: x['audio']['tracks'], list)
content_id, formats, track_uris, { if not tracks:
'url': track.get('uri'), continue
'type': f.get('type'), for track in tracks:
'mimeType': f.get('mimeType'), self._extract_format(
'quality': quality.get('quality'), content_id, formats, track_uris, {
'class': track.get('class'), 'url': track.get('uri'),
'language': track.get('language'), 'type': f.get('type'),
}) 'mimeType': f.get('mimeType'),
'quality': quality.get('quality'),
duration = float_or_none(try_get( 'class': track.get('class'),
ptmd, lambda x: x['attributes']['duration']['value']), scale=1000) 'language': track.get('language'),
})
return { return {
'extractor_key': ZDFIE.ie_key(), 'extractor_key': ZDFIE.ie_key(),
'id': content_id, 'id': content_id,
'duration': duration, 'duration': duration,
'formats': formats, 'formats': formats,
'subtitles': self._extract_subtitles(ptmd), 'subtitles': self._extract_subtitles(src_captions),
'_format_sort_fields': ('tbr', 'res', 'quality', 'language_preference'), '_format_sort_fields': ('tbr', 'res', 'quality', 'language_preference'),
} }
def _extract_player(self, webpage, video_id, fatal=True): def _get_api_token(self, video_id):
return self._parse_json( # As of 2025-03, this API is used by the Android app for getting tokens.
self._search_regex( # An equivalent token could be extracted from the webpage should the API become unavailable.
r'(?s)data-zdfplayer-jsb=(["\'])(?P<json>{.+?})\1', webpage, # For now this allows the extractor to avoid dealing with Next.js hydration data.
'player JSON', default='{}' if not fatal else NO_DEFAULT, TOKEN_CACHE_SECTION = 'zdf'
group='json'), TOKEN_CACHE_KEY = 'api-token'
video_id) token_data = self.cache.load(TOKEN_CACHE_SECTION, TOKEN_CACHE_KEY)
if traverse_obj(token_data, ('expires', {int_or_none}), default=0) < int(time.time()):
token_data = self._download_json(
'https://zdf-prod-futura.zdf.de/mediathekV2/token', video_id,
note='Downloading API token')
self.cache.store(TOKEN_CACHE_SECTION, TOKEN_CACHE_KEY, token_data)
return f'{token_data["type"]} {token_data["token"]}'
def _extract_entry(self, url, player, content, video_id): def _download_graphql(self, item_id, data_desc, query=None, body=None):
title = content.get('title') or content['teaserHeadline'] if not query and not body:
raise ExtractorError(
'GraphQL API requires either query parameters or a body',
video_id=item_id)
t = content['mainVideoContent']['http://zdf.de/rels/target'] return self._download_json(
ptmd_path = traverse_obj(t, ( 'https://api.zdf.de/graphql', item_id, note=f'Downloading {data_desc}',
(('streams', 'default'), None), errnote=f'Failed to download {data_desc}', query=query,
('http://zdf.de/rels/streams/ptmd', 'http://zdf.de/rels/streams/ptmd-template'), data=json.dumps(body).encode() if body else None, headers={
), get_all=False) 'Api-Auth': self._get_api_token(item_id),
if not ptmd_path: 'Apollo-Require-Preflight': True,
raise ExtractorError('Could not extract ptmd_path') 'Content-Type': 'application/json' if body else None,
})
info = self._extract_ptmd( @staticmethod
urljoin(url, ptmd_path.replace('{playerId}', 'android_native_5')), video_id, player['apiToken'], url) def _extract_thumbnails(source):
return [{
thumbnails = [] 'id': format_id,
layouts = try_get( 'url': url,
content, lambda x: x['teaserImageRef']['layouts'], dict) 'preference': 1 if format_id == 'original' else 0,
if layouts: **traverse_obj(re.search(r'(?P<width>\d+|auto)[Xx](?P<height>\d+|auto)', format_id), {
for layout_key, layout_url in layouts.items(): 'width': ('width', {int_or_none}),
layout_url = url_or_none(layout_url) 'height': ('height', {int_or_none}),
if not layout_url: }),
continue } for format_id, url in (source or {}).items() if url]
thumbnail = {
'url': layout_url,
'format_id': layout_key,
}
mobj = re.search(r'(?P<width>\d+)x(?P<height>\d+)', layout_key)
if mobj:
thumbnail.update({
'width': int(mobj.group('width')),
'height': int(mobj.group('height')),
})
thumbnails.append(thumbnail)
chapter_marks = t.get('streamAnchorTag') or []
chapter_marks.append({'anchorOffset': int_or_none(t.get('duration'))})
chapters = [{
'start_time': chap.get('anchorOffset'),
'end_time': next_chap.get('anchorOffset'),
'title': chap.get('anchorLabel'),
} for chap, next_chap in zip(chapter_marks, chapter_marks[1:])]
return merge_dicts(info, {
'title': title,
'description': content.get('leadParagraph') or content.get('teasertext'),
'duration': int_or_none(t.get('duration')),
'timestamp': unified_timestamp(content.get('editorialDate')),
'thumbnails': thumbnails,
'chapters': chapters or None,
'episode': title,
**traverse_obj(content, ('programmeItem', 0, 'http://zdf.de/rels/target', {
'series_id': ('http://zdf.de/rels/cmdm/series', 'seriesUuid', {str}),
'series': ('http://zdf.de/rels/cmdm/series', 'seriesTitle', {str}),
'season': ('http://zdf.de/rels/cmdm/season', 'seasonTitle', {str}),
'season_number': ('http://zdf.de/rels/cmdm/season', 'seasonNumber', {int_or_none}),
'season_id': ('http://zdf.de/rels/cmdm/season', 'seasonUuid', {str}),
'episode_number': ('episodeNumber', {int_or_none}),
'episode_id': ('contentId', {str}),
})),
})
def _extract_regular(self, url, player, video_id, query=None):
player_url = player['content']
content = self._call_api(
update_url_query(player_url, query),
video_id, 'content', player['apiToken'], url)
return self._extract_entry(player_url, player, content, video_id)
def _extract_mobile(self, video_id):
video = self._download_v2_doc(video_id)
formats = []
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)
thumbnails = []
teaser_bild = document.get('teaserBild')
if isinstance(teaser_bild, dict):
for thumbnail_key, thumbnail in teaser_bild.items():
thumbnail_url = try_get(
thumbnail, lambda x: x['url'], str)
if thumbnail_url:
thumbnails.append({
'url': thumbnail_url,
'id': thumbnail_key,
'width': int_or_none(thumbnail.get('width')),
'height': int_or_none(thumbnail.get('height')),
})
return {
'id': content_id,
'title': title,
'description': document.get('beschreibung'),
'duration': int_or_none(document.get('length')),
'timestamp': unified_timestamp(document.get('date')) or unified_timestamp(
try_get(video, lambda x: x['meta']['editorialDate'], str)),
'thumbnails': thumbnails,
'subtitles': self._extract_subtitles(document),
'formats': formats,
}
class ZDFIE(ZDFBaseIE): class ZDFIE(ZDFBaseIE):
_VALID_URL = r'https?://www\.zdf\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)\.html' _VALID_URL = [
# Legacy URLs end in .html and redirect
r'https?://(?:www\.)?zdf\.de/(?:[^/?#]+/)*(?P<id>[^/?#]+)\.html',
r'https?://(?:www\.)?zdf\.de/(?:video|play)/(?:[^/?#]+/)*(?P<id>[^/?#]+)/?',
]
_TESTS = [{ _TESTS = [{
# Same as https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html # Standalone video (i.e. not part of a playlist), video URL
'url': 'https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html', 'url': 'https://www.zdf.de/video/dokus/sylt---deutschlands-edles-nordlicht-movie-100/sylt-deutschlands-edles-nordlicht-100',
'md5': '34ec321e7eb34231fd88616c65c92db0',
'info_dict': { 'info_dict': {
'id': '210222_phx_nachgehakt_corona_protest', 'id': 'sylt-deutschlands-edles-nordlicht-100',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Wohin führt der Protest in der Pandemie?', 'title': 'Sylt - Deutschlands edles Nordlicht',
'description': 'md5:7d643fe7f565e53a24aac036b2122fbd', 'description': 'md5:35407b810c2e1e33efbe15ef6e4c06c3',
'duration': 1691, 'duration': 810.0,
'timestamp': 1613948400, 'thumbnail': 'https://www.zdf.de/assets/sylt-118~original?cb=1613992485011',
'upload_date': '20210221', 'series': 'Sylt - Deutschlands edles Nordlicht',
'series_id': 'sylt---deutschlands-edles-nordlicht-movie-100',
'timestamp': 1612462500,
'upload_date': '20210204',
'_old_archive_ids': ['210402_1915_sendung_dok'],
}, },
'skip': 'No longer available: "Diese Seite wurde leider nicht gefunden"',
}, { }, {
# Same as https://www.3sat.de/film/ab-18/10-wochen-sommer-108.html # Standalone video (i.e. not part of a playlist), play URL
'url': 'https://www.zdf.de/dokumentation/ab-18/10-wochen-sommer-102.html', 'url': 'https://www.zdf.de/play/dokus/sylt---deutschlands-edles-nordlicht-movie-100/sylt-deutschlands-edles-nordlicht-100',
'md5': '0aff3e7bc72c8813f5e0fae333316a1d',
'info_dict': { 'info_dict': {
'id': '141007_ab18_10wochensommer_film', 'id': 'sylt-deutschlands-edles-nordlicht-100',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Ab 18! - 10 Wochen Sommer', 'title': 'Sylt - Deutschlands edles Nordlicht',
'description': 'md5:8253f41dc99ce2c3ff892dac2d65fe26', 'description': 'md5:35407b810c2e1e33efbe15ef6e4c06c3',
'duration': 2660, 'duration': 810.0,
'timestamp': 1608604200, 'thumbnail': 'https://www.zdf.de/assets/sylt-118~original?cb=1613992485011',
'upload_date': '20201222', 'series': 'Sylt - Deutschlands edles Nordlicht',
'series_id': 'sylt---deutschlands-edles-nordlicht-movie-100',
'timestamp': 1612462500,
'upload_date': '20210204',
'_old_archive_ids': ['210402_1915_sendung_dok'],
}, },
'skip': 'No longer available: "Diese Seite wurde leider nicht gefunden"', 'params': {'skip_download': True},
}, { }, {
'url': 'https://www.zdf.de/nachrichten/heute-journal/heute-journal-vom-30-12-2021-100.html', # Standalone video (i.e. not part of a playlist), legacy URL before website redesign in 2025-03
'url': 'https://www.zdf.de/dokumentation/dokumentation-sonstige/sylt-deutschlands-edles-nordlicht-100.html',
'info_dict': { 'info_dict': {
'id': '211230_sendung_hjo', 'id': 'sylt-deutschlands-edles-nordlicht-100',
'ext': 'mp4', 'ext': 'mp4',
'description': 'md5:47dff85977bde9fb8cba9e9c9b929839', 'title': 'Sylt - Deutschlands edles Nordlicht',
'duration': 1890.0, 'description': 'md5:35407b810c2e1e33efbe15ef6e4c06c3',
'upload_date': '20211230', 'duration': 810.0,
'chapters': list, 'thumbnail': 'https://www.zdf.de/assets/sylt-118~original?cb=1613992485011',
'thumbnail': 'md5:e65f459f741be5455c952cd820eb188e', 'series': 'Sylt - Deutschlands edles Nordlicht',
'title': 'heute journal vom 30.12.2021', 'series_id': 'sylt---deutschlands-edles-nordlicht-movie-100',
'timestamp': 1640897100, 'timestamp': 1612462500,
'upload_date': '20210204',
'_old_archive_ids': ['210402_1915_sendung_dok'],
}, },
'skip': 'No longer available: "Diese Seite wurde leider nicht gefunden"', 'params': {'skip_download': True},
}, { }, {
'url': 'https://www.zdf.de/dokumentation/terra-x/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100.html', # Video belongs to a playlist, video URL
'url': 'https://www.zdf.de/video/dokus/die-magie-der-farben-116/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
'md5': '1eda17eb40a9ead3046326e10b9c5973',
'info_dict': { 'info_dict': {
'id': '151025_magie_farben2_tex', 'id': 'die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
'ext': 'mp4', 'ext': 'mp4',
'duration': 2615.0, 'title': 'Von Königspurpur bis Jeansblau',
'title': 'Die Magie der Farben (2/2)',
'description': 'md5:a89da10c928c6235401066b60a6d5c1a', 'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
'timestamp': 1465021200, 'duration': 2615.0,
'thumbnail': 'https://www.zdf.de/assets/mauve-im-labor-100~768x432?cb=1464909117806', 'thumbnail': 'https://www.zdf.de/assets/koenigspurpur-bis-jeansblau-100~original?cb=1741857765971',
'upload_date': '20160604',
'episode': 'Die Magie der Farben (2/2)',
'episode_id': 'POS_954f4170-36a5-4a41-a6cf-78f1f3b1f127',
'season': 'Staffel 1',
'series': 'Die Magie der Farben', 'series': 'Die Magie der Farben',
'series_id': 'die-magie-der-farben-116',
'season': 'Season 1',
'season_number': 1, 'season_number': 1,
'series_id': 'a39900dd-cdbd-4a6a-a413-44e8c6ae18bc', 'episode': 'Episode 2',
'season_id': '5a92e619-8a0f-4410-a3d5-19c76fbebb37',
'episode_number': 2, 'episode_number': 2,
'timestamp': 1445797800,
'upload_date': '20151025',
'_old_archive_ids': ['151025_magie_farben2_tex'],
},
}, {
# Video belongs to a playlist, play URL
'url': 'https://www.zdf.de/play/dokus/die-magie-der-farben-116/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
'md5': '1eda17eb40a9ead3046326e10b9c5973',
'info_dict': {
'id': 'die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
'ext': 'mp4',
'title': 'Von Königspurpur bis Jeansblau',
'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
'duration': 2615.0,
'thumbnail': 'https://www.zdf.de/assets/koenigspurpur-bis-jeansblau-100~original?cb=1741857765971',
'series': 'Die Magie der Farben',
'series_id': 'die-magie-der-farben-116',
'season': 'Season 1',
'season_number': 1,
'episode': 'Episode 2',
'episode_number': 2,
'timestamp': 1445797800,
'upload_date': '20151025',
'_old_archive_ids': ['151025_magie_farben2_tex'],
},
'params': {'skip_download': True},
}, {
# Video belongs to a playlist, legacy URL before website redesign in 2025-03
'url': 'https://www.zdf.de/dokumentation/terra-x/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100.html',
'md5': '1eda17eb40a9ead3046326e10b9c5973',
'info_dict': {
'id': 'die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
'ext': 'mp4',
'title': 'Von Königspurpur bis Jeansblau',
'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
'duration': 2615.0,
'thumbnail': 'https://www.zdf.de/assets/koenigspurpur-bis-jeansblau-100~original?cb=1741857765971',
'series': 'Die Magie der Farben',
'series_id': 'die-magie-der-farben-116',
'season': 'Season 1',
'season_number': 1,
'episode': 'Episode 2',
'episode_number': 2,
'timestamp': 1445797800,
'upload_date': '20151025',
'_old_archive_ids': ['151025_magie_farben2_tex'],
},
'params': {'skip_download': True},
}, {
# Video with chapters
'url': 'https://www.zdf.de/video/magazine/heute-journal-104/heute-journal-vom-19-12-2021-100',
'md5': '1175003f28507bd27b266181c4de9f56',
'info_dict': {
'id': 'heute-journal-vom-19-12-2021-100',
'ext': 'mp4',
'title': 'heute journal vom 19.12.2021',
'description': 'md5:02504cf3b03777ff32fcc927d260c5dd',
'duration': 1770.0,
'thumbnail': 'https://epg-image.zdf.de/fotobase-webdelivery/images/273e5545-16e7-4ca3-898e-52fe9e06d964?layout=1920x1080',
'chapters': 'count:11',
'series': 'heute journal',
'series_id': 'heute-journal-104',
'season': 'Season 2021',
'season_number': 2021,
'episode': 'Episode 370',
'episode_number': 370,
'timestamp': 1639946700,
'upload_date': '20211219',
'_old_archive_ids': ['211219_sendung_hjo_dgs'],
}, },
}, { }, {
'url': 'https://www.zdf.de/funk/druck-11790/funk-alles-ist-verzaubert-102.html', 'url': 'https://www.zdf.de/funk/druck-11790/funk-alles-ist-verzaubert-102.html',
'md5': '57af4423db0455a3975d2dc4578536bc', 'md5': '57af4423db0455a3975d2dc4578536bc',
'info_dict': { 'info_dict': {
'id': 'funk-alles-ist-verzaubert-102',
'ext': 'mp4', 'ext': 'mp4',
'id': 'video_funk_1770473',
'duration': 1278.0,
'title': 'Alles ist verzaubert', 'title': 'Alles ist verzaubert',
'description': 'Die Neue an der Schule verdreht Ismail den Kopf.', 'description': 'Die Neue an der Schule verdreht Ismail den Kopf.',
'duration': 1278.0,
'thumbnail': 'https://www.zdf.de/assets/teaser-funk-alles-ist-verzaubert-102~original?cb=1663848412907',
'series': 'DRUCK',
'series_id': 'funk-collection-funk-11790-1590',
'season': 'Season 7',
'season_number': 7,
'episode': 'Episode 1',
'episode_number': 1,
'timestamp': 1635520560, 'timestamp': 1635520560,
'thumbnail': 'https://www.zdf.de/assets/teaser-funk-alles-ist-verzaubert-102~1920x1080?cb=1663848412907',
'upload_date': '20211029', 'upload_date': '20211029',
'episode': 'Alles ist verzaubert', '_old_archive_ids': ['video_funk_1770473'],
}, },
}, {
'url': 'https://www.zdf.de/serien/soko-stuttgart/das-geld-anderer-leute-100.html',
'info_dict': {
'id': 'das-geld-anderer-leute-100',
'ext': 'mp4',
'title': 'Das Geld anderer Leute',
'description': 'md5:cb6f660850dc5eb7d1ab776ea094959d',
'duration': 2581.0,
'thumbnail': 'https://epg-image.zdf.de/fotobase-webdelivery/images/e2d7e55a-09f0-424e-ac73-6cac4dd65f35?layout=1920x1080',
'series': 'SOKO Stuttgart',
'series_id': 'soko-stuttgart-104',
'season': 'Season 11',
'season_number': 11,
'episode': 'Episode 10',
'episode_number': 10,
'timestamp': 1728983700,
'upload_date': '20241015',
'_old_archive_ids': ['191205_1800_sendung_sok8'],
},
}, {
'url': 'https://www.zdf.de/serien/northern-lights/begegnung-auf-der-bruecke-100.html',
'info_dict': {
'id': 'begegnung-auf-der-bruecke-100',
'ext': 'mp4',
'title': 'Begegnung auf der Brücke',
'description': 'md5:e53a555da87447f7f1207f10353f8e45',
'duration': 3083.0,
'thumbnail': 'https://epg-image.zdf.de/fotobase-webdelivery/images/c5ff1d1f-f5c8-4468-86ac-1b2f1dbecc76?layout=1920x1080',
'series': 'Northern Lights',
'series_id': 'northern-lights-100',
'season': 'Season 1',
'season_number': 1,
'episode': 'Episode 1',
'episode_number': 1,
'timestamp': 1738546500,
'upload_date': '20250203',
'_old_archive_ids': ['240319_2310_sendung_not'],
},
}, {
# Same as https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html
'url': 'https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html',
'only_matching': True,
}, {
# 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',
'only_matching': True,
}, { }, {
# Same as https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche # Same as https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche
'url': 'https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html', 'url': 'https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html',
@ -349,108 +409,156 @@ class ZDFIE(ZDFBaseIE):
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://www.zdf.de/arte/todliche-flucht/page-video-artede-toedliche-flucht-16-100.html', 'url': 'https://www.zdf.de/arte/todliche-flucht/page-video-artede-toedliche-flucht-16-100.html',
'info_dict': { 'only_matching': True,
'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': 1728983700,
'upload_date': '20241015',
'thumbnail': 'https://epg-image.zdf.de/fotobase-webdelivery/images/e2d7e55a-09f0-424e-ac73-6cac4dd65f35?layout=2400x1350',
'series': 'SOKO Stuttgart',
'series_id': 'f862ce9a-6dd1-4388-a698-22b36ac4c9e9',
'season': 'Staffel 11',
'season_number': 11,
'season_id': 'ae1b4990-6d87-4970-a571-caccf1ba2879',
'episode': 'Das Geld anderer Leute',
'episode_number': 10,
'episode_id': 'POS_7f367934-f2f0-45cb-9081-736781ff2d23',
},
}, { }, {
'url': 'https://www.zdf.de/dokumentation/terra-x/unser-gruener-planet-wuesten-doku-100.html', 'url': 'https://www.zdf.de/dokumentation/terra-x/unser-gruener-planet-wuesten-doku-100.html',
'info_dict': { 'only_matching': True,
'id': '220525_green_planet_makingof_1_tropen_tex',
'ext': 'mp4',
'title': 'Making-of Unser grüner Planet - Tropen',
'description': 'md5:d7c6949dc7c75c73c4ad51c785fb0b79',
'duration': 435.0,
'timestamp': 1653811200,
'upload_date': '20220529',
'format_note': 'hd, main',
'thumbnail': 'https://www.zdf.de/assets/unser-gruener-planet-making-of-1-tropen-100~3840x2160?cb=1653493335577',
'episode': 'Making-of Unser grüner Planet - Tropen',
},
'skip': 'No longer available: "Leider kein Video verfügbar"',
}, {
'url': 'https://www.zdf.de/serien/northern-lights/begegnung-auf-der-bruecke-100.html',
'info_dict': {
'id': '240319_2310_sendung_not',
'ext': 'mp4',
'title': 'Begegnung auf der Brücke',
'description': 'md5:e53a555da87447f7f1207f10353f8e45',
'thumbnail': 'https://epg-image.zdf.de/fotobase-webdelivery/images/c5ff1d1f-f5c8-4468-86ac-1b2f1dbecc76?layout=2400x1350',
'upload_date': '20250203',
'duration': 3083.0,
'timestamp': 1738546500,
'series_id': '1d7a1879-01ee-4468-8237-c6b4ecd633c7',
'series': 'Northern Lights',
'season': 'Staffel 1',
'season_number': 1,
'season_id': '22ac26a2-4ea2-4055-ac0b-98b755cdf718',
'episode': 'Begegnung auf der Brücke',
'episode_number': 1,
'episode_id': 'POS_71049438-024b-471f-b472-4fe2e490d1fb',
},
}] }]
_GRAPHQL_QUERY = '''
query VideoByCanonical($canonical: String!) {
videoByCanonical(canonical: $canonical) {
canonical
title
leadParagraph
editorialDate
teaser {
description
image {
list
}
}
episodeInfo {
episodeNumber
seasonNumber
}
smartCollection {
canonical
title
}
currentMedia {
nodes {
ptmdTemplate
... on VodMedia {
duration
aspectRatio
streamAnchorTags {
nodes {
anchorOffset
anchorLabel
}
}
vodMediaType
label
}
... on LiveMedia {
start
stop
encryption
liveMediaType
label
}
id
}
}
}
}
'''
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
video_data = self._download_graphql(video_id, 'video metadata', body={
'operationName': 'VideoByCanonical',
'query': self._GRAPHQL_QUERY,
'variables': {'canonical': video_id},
})
# TODO: If there are multiple PTMD templates,
# usually one of them is a sign-language variant of the video.
# The format order works out fine as is and prefers the "normal" video,
# but this should probably be made more explicit.
ptmd_templates = traverse_obj(
video_data,
('data', 'videoByCanonical', 'currentMedia', 'nodes', ..., 'ptmdTemplate'))
ptmd_data = self._extract_ptmd(
'https://api.zdf.de', ptmd_templates, video_id,
self._get_api_token(video_id))
# We can't use the ID from PTMD extraction as the video ID
# because it is not available during playlist extraction.
# We fix it here manually instead of inside the method
# because other extractors do rely on using it as their ID.
ptmd_data['_old_archive_ids'] = [ptmd_data['id']]
del ptmd_data['id']
webpage = self._download_webpage(url, video_id, fatal=False) return {
if webpage: 'id': video_id,
player = self._extract_player(webpage, url, fatal=False) **ptmd_data,
if player: **traverse_obj(video_data, ('data', 'videoByCanonical', {
return self._extract_regular(url, player, video_id, query={'profile': 'player-3'}) 'title': ('title', {str}),
'description': (('leadParagraph', ('teaser', 'description')), any, {str}),
'timestamp': ('editorialDate', {parse_iso8601}),
'thumbnails': ('teaser', 'image', 'list', {self._extract_thumbnails}),
'episode_number': ('episodeInfo', 'episodeNumber', {int_or_none}),
'season_number': ('episodeInfo', 'seasonNumber', {int_or_none}),
'series': ('smartCollection', 'title', {str}),
'series_id': ('smartCollection', 'canonical', {str}),
'chapters': ('currentMedia', 'nodes', 0, {self._extract_chapters}),
})),
}
return self._extract_mobile(video_id) def _extract_chapters(self, data):
chapter_marks = traverse_obj(data, ('streamAnchorTags', 'nodes'))
chapter_marks.append({'anchorOffset': float_or_none(data.get('duration'))})
return [{
'start_time': chap.get('anchorOffset'),
'end_time': next_chap.get('anchorOffset'),
'title': chap.get('anchorLabel'),
} for chap, next_chap in zip(chapter_marks, chapter_marks[1:])] or None
class ZDFChannelIE(ZDFBaseIE): class ZDFCollectionIE(ZDFBaseIE):
_VALID_URL = r'https?://www\.zdf\.de/(?:[^/?#]+/)*(?P<id>[^/?#&]+)' _VALID_URL = r'https?://www\.zdf\.de/(?:[^/?#]+/)*(?P<id>[^/?#]+)'
_TESTS = [{ _TESTS = [{
# Playlist, legacy URL before website redesign in 2025-03
'url': 'https://www.zdf.de/sport/das-aktuelle-sportstudio', 'url': 'https://www.zdf.de/sport/das-aktuelle-sportstudio',
'info_dict': { 'info_dict': {
'id': 'das-aktuelle-sportstudio', 'id': 'das-aktuelle-sportstudio-220',
'title': 'das aktuelle sportstudio', 'title': 'das aktuelle sportstudio',
'description': 'md5:e46c785324238a03edcf8b301c5fd5dc',
}, },
'playlist_mincount': 18, 'playlist_mincount': 18,
}, { }, {
'url': 'https://www.zdf.de/dokumentation/planet-e', # Playlist, current URL
'url': 'https://www.zdf.de/sport/das-aktuelle-sportstudio-220',
'info_dict': { 'info_dict': {
'id': 'planet-e', 'id': 'das-aktuelle-sportstudio-220',
'title': 'planet e.', 'title': 'das aktuelle sportstudio',
'description': 'md5:87e3b9c66a63cf1407ee443d2c4eb88e', 'description': 'md5:e46c785324238a03edcf8b301c5fd5dc',
}, },
'playlist_mincount': 50, 'playlist_mincount': 18,
}, {
# Standalone video (i.e. not part of a playlist), collection URL
'add_ie': [ZDFIE.ie_key()],
'url': 'https://www.zdf.de/dokus/sylt---deutschlands-edles-nordlicht-movie-100',
'info_dict': {
'id': 'sylt-deutschlands-edles-nordlicht-100',
'ext': 'mp4',
'title': 'Sylt - Deutschlands edles Nordlicht',
'description': 'md5:35407b810c2e1e33efbe15ef6e4c06c3',
'duration': 810.0,
'thumbnail': 'https://www.zdf.de/assets/sylt-118~original?cb=1613992485011',
'series': 'Sylt - Deutschlands edles Nordlicht',
'series_id': 'sylt---deutschlands-edles-nordlicht-movie-100',
'timestamp': 1612462500,
'upload_date': '20210204',
'_old_archive_ids': ['210402_1915_sendung_dok'],
},
'params': {'skip_download': True},
}, { }, {
'url': 'https://www.zdf.de/gesellschaft/aktenzeichen-xy-ungeloest', 'url': 'https://www.zdf.de/gesellschaft/aktenzeichen-xy-ungeloest',
'info_dict': { 'info_dict': {
'id': 'aktenzeichen-xy-ungeloest', 'id': 'aktenzeichen-xy-ungeloest-110',
'title': 'Aktenzeichen XY... Ungelöst', 'title': 'Aktenzeichen XY... Ungelöst',
'description': 'md5:623ede5819c400c6d04943fa8100e6e7', 'description': 'md5:b79ac0d64b979e53cbe510c0ca9cb7be',
}, },
'playlist_mincount': 2, 'playlist_mincount': 2,
}, { }, {
@ -462,42 +570,64 @@ class ZDFChannelIE(ZDFBaseIE):
def suitable(cls, url): def suitable(cls, url):
return False if ZDFIE.suitable(url) else super().suitable(url) return False if ZDFIE.suitable(url) else super().suitable(url)
def _extract_entry(self, entry):
return self.url_result(
entry['sharingUrl'], ZDFIE, **traverse_obj(entry, {
'id': ('basename', {str}),
'title': ('titel', {str}),
'description': ('beschreibung', {str}),
'duration': ('length', {float_or_none}),
'season_number': ('seasonNumber', {int_or_none}),
'episode_number': ('episodeNumber', {int_or_none}),
}))
def _entries(self, data, document_id):
for entry in traverse_obj(data, (
'cluster', lambda _, v: v['type'] == 'teaser',
# If 'brandId' differs, it is a 'You might also like' video. Filter these out
'teaser', lambda _, v: v['type'] == 'video' and v['brandId'] == document_id and v['sharingUrl'],
)):
yield self._extract_entry(entry)
def _real_extract(self, url): def _real_extract(self, url):
channel_id = self._match_id(url) channel_id = self._match_id(url)
webpage = self._download_webpage(url, channel_id) webpage, urlh = self._download_webpage_handle(url, channel_id)
document_id = self._search_regex( # Make sure to get the correct ID in case of redirects
r'docId\s*:\s*(["\'])(?P<doc_id>(?:(?!\1).)+)\1', webpage, 'document id', group='doc_id') channel_id = self._search_regex(self._VALID_URL, urlh.url, 'channel id', group='id')
data = self._download_v2_doc(document_id)
main_video = traverse_obj(data, ( collection_data = self._download_graphql(
'cluster', lambda _, v: v['type'] == 'teaserContent', channel_id, 'smart collection data', query={
'teaser', lambda _, v: v['type'] == 'video' and v['basename'] and v['sharingUrl'], any)) or {} 'operationName': 'GetSmartCollectionByCanonical',
'variables': json.dumps({
'canonical': channel_id,
'videoPageSize': 100,
}),
'extensions': json.dumps({
'persistedQuery': {
'version': 1,
'sha256Hash': 'cb49420e133bd668ad895a8cea0e65cba6aa11ac1cacb02341ff5cf32a17cd02',
},
}),
})
if not self._yes_playlist(channel_id, main_video.get('basename')): video_data = traverse_obj(
return self._extract_entry(main_video) collection_data, ('data', 'smartCollectionByCanonical', 'video'))
season_data = traverse_obj(
collection_data, ('data', 'smartCollectionByCanonical', 'seasons'))
return self.playlist_result( if not self._yes_playlist(
self._entries(data, document_id), channel_id, channel_id if season_data else None,
re.split(r'\s+[-|]\s+ZDF(?:mediathek)?$', self._og_search_title(webpage) or '')[0] or None, traverse_obj(video_data, ('canonical', {str}))):
join_nonempty( return self.url_result(video_data['sharingUrl'], ie=ZDFIE)
'headline', 'text', delim='\n\n',
from_dict=traverse_obj(data, ('shortText', {dict}), default={})) or None) title = (traverse_obj(collection_data, ('data', 'smartCollectionByCanonical', 'title'))
or self._html_search_meta(
['og:title', 'title', 'twitter:title'], webpage, 'title', fatal=False))
needs_pagination = traverse_obj(season_data, (
'seasons', ..., 'episodes', 'pageInfo', 'hasNextPage',
lambda _, v: v is True, any), default=False)
if needs_pagination:
# TODO: Implement pagination for collections with long seasons
# e.g. https://www.zdf.de/magazine/heute-journal-104
self.report_warning('This collections contains seasons with more than 100 episodes, some episodes are missing from the result.')
videos = traverse_obj(season_data, ('seasons', ..., 'episodes', 'videos', ...))
season_id = parse_qs(url).get('staffel', [None])[-1]
videos = [v for v in videos
if not season_id or season_id == str(traverse_obj(v, ('episodeInfo', 'seasonNumber')))]
entries = [self.url_result(video['sharingUrl'], ZDFIE, **traverse_obj(video, {
'id': ('canonical', {str}),
'title': ('teaser', 'title', {str}),
'description': (('leadParagraph', ('teaser', 'description')), any, {str}),
'timestamp': ('editorialDate', {parse_iso8601}),
'thumbnails': ('teaser', 'imageWithoutLogo', 'layouts', {self._extract_thumbnails}),
'episode_number': ('episodeInfo', 'episodeNumber', {int_or_none}),
'season_number': ('episodeInfo', 'seasonNumber', {int_or_none}),
'series_id': {lambda _: channel_id},
'series': {lambda _: title},
})) for video in videos or [] if video.get('currentMediaType') != 'NOVIDEO']
return self.playlist_result(entries, channel_id, title, traverse_obj(
collection_data, ('data', 'smartCollectionByCanonical', 'infoText', {str})))