from ..compat import compat_str
from ..utils import (
determine_ext,
+ float_or_none,
int_or_none,
+ join_nonempty,
+ merge_dicts,
NO_DEFAULT,
orderedSet,
parse_codecs,
qualities,
+ traverse_obj,
try_get,
unified_timestamp,
update_url_query,
class ZDFBaseIE(InfoExtractor):
- def _call_api(self, url, player, referrer, video_id, item):
- return self._download_json(
- url, video_id, 'Downloading JSON %s' % item,
- headers={
- 'Referer': referrer,
- 'Api-Auth': 'Bearer %s' % player['apiToken'],
- })
-
- 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)
-
-
-class ZDFIE(ZDFBaseIE):
- IE_NAME = "ZDF-3sat"
- _VALID_URL = r'https?://www\.(zdf|3sat)\.de/(?:[^/]+/)*(?P<id>[^/?]+)\.html'
- _QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh', 'hd')
_GEO_COUNTRIES = ['DE']
+ _QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh', 'hd')
- _TESTS = [{
- 'url': 'https://www.3sat.de/wissen/wissenschaftsdoku/luxusgut-lebensraum-100.html',
- 'info_dict': {
- 'id': 'luxusgut-lebensraum-100',
- 'ext': 'mp4',
- 'title': 'Luxusgut Lebensraum',
- 'description': 'md5:5c09b2f45ac3bc5233d1b50fc543d061',
- 'duration': 2601,
- 'timestamp': 1566497700,
- 'upload_date': '20190822',
- }
- }, {
- 'url': 'https://www.zdf.de/dokumentation/terra-x/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100.html',
- 'info_dict': {
- 'id': 'die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
- 'ext': 'mp4',
- 'title': 'Die Magie der Farben (2/2)',
- 'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
- 'duration': 2615,
- 'timestamp': 1465021200,
- 'upload_date': '20160604',
- },
- }, {
- 'url': 'https://www.zdf.de/service-und-hilfe/die-neue-zdf-mediathek/zdfmediathek-trailer-100.html',
- 'only_matching': True,
- }, {
- 'url': 'https://www.zdf.de/filme/taunuskrimi/die-lebenden-und-die-toten-1---ein-taunuskrimi-100.html',
- 'only_matching': True,
- }, {
- 'url': 'https://www.zdf.de/dokumentation/planet-e/planet-e-uebersichtsseite-weitere-dokumentationen-von-planet-e-100.html',
- 'only_matching': True,
- }]
+ def _call_api(self, url, video_id, item, api_token=None, referrer=None):
+ headers = {}
+ if api_token:
+ headers['Api-Auth'] = 'Bearer %s' % api_token
+ if referrer:
+ headers['Referer'] = referrer
+ return self._download_json(
+ url, video_id, 'Downloading JSON %s' % item, headers=headers)
@staticmethod
def _extract_subtitles(src):
def _extract_format(self, video_id, formats, format_urls, meta):
format_url = url_or_none(meta.get('url'))
- if not format_url:
- return
- if format_url in format_urls:
+ if not format_url or format_url in format_urls:
return
format_urls.add(format_url)
- mime_type = meta.get('mimeType')
- ext = determine_ext(format_url)
+
+ mime_type, ext = meta.get('mimeType'), determine_ext(format_url)
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'))
- format_id = ['http']
- for p in (meta.get('type'), meta.get('quality')):
- if p and isinstance(p, compat_str):
- format_id.append(p)
+ if not f and meta.get('type'):
+ data = meta['type'].split('_')
+ if try_get(data, lambda x: x[2]) == ext:
+ f = {'vcodec': data[0], 'acodec': data[1]}
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,
+ 'format_id': join_nonempty('http', meta.get('type'), meta.get('quality')),
})
- formats.append(f)
-
- def _extract_entry(self, url, player, content, video_id):
- title = content.get('title') or content['teaserHeadline']
-
- t = content['mainVideoContent']['http://zdf.de/rels/target']
-
- ptmd_path = t.get('http://zdf.de/rels/streams/ptmd')
-
- if not ptmd_path:
- ptmd_path = t[
- 'http://zdf.de/rels/streams/ptmd-template'].replace(
- '{playerId}', 'ngplayer_2_4')
-
+ new_formats = [f]
+ formats.extend(merge_dicts(f, {
+ 'format_note': join_nonempty('quality', 'class', from_dict=meta, delim=', '),
+ '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(
- urljoin(url, ptmd_path), player, url, video_id, 'metadata')
+ ptmd_url, video_id, 'metadata', api_token, referrer)
+
+ content_id = ptmd.get('basename') or ptmd_url.split('/')[-1]
formats = []
track_uris = set()
continue
for track in tracks:
self._extract_format(
- video_id, formats, track_uris, {
+ content_id, formats, track_uris, {
'url': track.get('uri'),
'type': f.get('type'),
'mimeType': f.get('mimeType'),
'quality': quality.get('quality'),
+ 'class': track.get('class'),
'language': track.get('language'),
})
- self._sort_formats(formats)
+ self._sort_formats(formats, ('hasaud', 'res', 'quality', 'language_preference'))
+
+ duration = float_or_none(try_get(
+ ptmd, lambda x: x['attributes']['duration']['value']), scale=1000)
+
+ return {
+ 'extractor_key': ZDFIE.ie_key(),
+ 'id': content_id,
+ 'duration': duration,
+ 'formats': formats,
+ 'subtitles': self._extract_subtitles(ptmd),
+ }
+
+ 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)
+
+
+class ZDFIE(ZDFBaseIE):
+ _VALID_URL = r'https?://www\.zdf\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)\.html'
+ _TESTS = [{
+ 'url': 'https://www.zdf.de/nachrichten/heute-journal/heute-journal-vom-30-12-2021-100.html',
+ 'info_dict': {
+ 'id': '211230_sendung_hjo',
+ 'ext': 'mp4',
+ 'description': 'md5:47dff85977bde9fb8cba9e9c9b929839',
+ 'duration': 1890.0,
+ 'upload_date': '20211230',
+ 'chapters': list,
+ 'thumbnail': 'md5:e65f459f741be5455c952cd820eb188e',
+ 'title': 'heute journal vom 30.12.2021',
+ 'timestamp': 1640897100,
+ }
+ }, {
+ 'url': 'https://www.zdf.de/dokumentation/terra-x/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100.html',
+ 'info_dict': {
+ 'id': '151025_magie_farben2_tex',
+ 'ext': 'mp4',
+ 'title': 'Die Magie der Farben (2/2)',
+ 'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
+ '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': '3d6f1049e9682178a11c54b91f3dd065',
+ '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
+ 'url': 'https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html',
+ 'only_matching': True,
+ }, {
+ # Same as https://www.3sat.de/film/spielfilm/der-hauptmann-100.html
+ 'url': 'https://www.zdf.de/filme/filme-sonstige/der-hauptmann-112.html',
+ 'only_matching': True,
+ }, {
+ # Same as https://www.3sat.de/wissen/nano/nano-21-mai-2019-102.html, equal media ids
+ 'url': 'https://www.zdf.de/wissen/nano/nano-21-mai-2019-102.html',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.zdf.de/service-und-hilfe/die-neue-zdf-mediathek/zdfmediathek-trailer-100.html',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.zdf.de/filme/taunuskrimi/die-lebenden-und-die-toten-1---ein-taunuskrimi-100.html',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.zdf.de/dokumentation/planet-e/planet-e-uebersichtsseite-weitere-dokumentationen-von-planet-e-100.html',
+ 'only_matching': True,
+ }, {
+ # 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
+ }]
+
+ def _extract_entry(self, url, player, content, video_id):
+ title = content.get('title') or content['teaserHeadline']
+
+ t = content['mainVideoContent']['http://zdf.de/rels/target']
+
+ ptmd_path = t.get('http://zdf.de/rels/streams/ptmd')
+
+ if not ptmd_path:
+ ptmd_path = traverse_obj(
+ t, ('streams', 'default', 'http://zdf.de/rels/streams/ptmd-template'),
+ 'http://zdf.de/rels/streams/ptmd-template').replace(
+ '{playerId}', 'ngplayer_2_4')
+
+ info = self._extract_ptmd(
+ urljoin(url, ptmd_path), video_id, player['apiToken'], url)
thumbnails = []
layouts = try_get(
})
thumbnails.append(thumbnail)
- return {
- 'id': video_id,
+ 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,
- 'subtitles': self._extract_subtitles(ptmd),
- 'formats': formats,
- }
+ 'chapters': chapters or None
+ })
def _extract_regular(self, url, player, video_id):
content = self._call_api(
- player['content'], player, url, video_id, 'content')
+ player['content'], video_id, 'content', player['apiToken'], url)
return self._extract_entry(player['content'], player, content, video_id)
def _extract_mobile(self, video_id):
- document = self._download_json(
+ video = self._download_json(
'https://zdf-cdn.live.cellular.de/mediathekV2/document/%s' % video_id,
- video_id)['document']
+ video_id)
+
+ document = video['document']
title = document['titel']
+ content_id = document['basename']
formats = []
format_urls = set()
for f in document['formitaeten']:
- self._extract_format(video_id, formats, format_urls, f)
+ self._extract_format(content_id, formats, format_urls, f)
self._sort_formats(formats)
thumbnails = []
})
return {
- 'id': video_id,
+ 'id': content_id,
'title': title,
'description': document.get('beschreibung'),
'duration': int_or_none(document.get('length')),
- 'timestamp': unified_timestamp(try_get(
- document, lambda x: x['meta']['editorialDate'], compat_str)),
+ 'timestamp': unified_timestamp(document.get('date')) or unified_timestamp(
+ try_get(video, lambda x: x['meta']['editorialDate'], compat_str)),
'thumbnails': thumbnails,
'subtitles': self._extract_subtitles(document),
'formats': formats,
projects / yt-dlp.git / blobdiff