- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
- video_id = mobj.group('video_id')
-
- if mobj.group('hash'):
- url = url.replace(u'#', u'', 1)
-
- html = self._download_webpage(url, video_id)
- streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
- if streams is None:
- raise ExtractorError(u'No media url found.')
-
- # s['media_type'] == 'wstreaming' -> use 'Windows Media Player' and mms url
- # s['media_type'] == 'hstreaming' -> use 'Quicktime' and rtsp url
- # choose first/default media type and highest quality for now
- def stream_pref(s):
- TYPE_ORDER = ['ostreaming', 'hstreaming', 'wstreaming']
- try:
- type_pref = TYPE_ORDER.index(s['media_type'])
- except ValueError:
- type_pref = 999
-
- QUALITY_ORDER = ['veryhigh', '300']
- try:
- quality_pref = QUALITY_ORDER.index(s['quality'])
- except ValueError:
- quality_pref = 999
-
- return (type_pref, quality_pref)
-
- sorted_streams = sorted(streams, key=stream_pref)
- if not sorted_streams:
- raise ExtractorError(u'No stream found.')
- stream = sorted_streams[0]
-
- media_link = self._download_webpage(
- stream['video_url'],
- video_id,
- u'Get stream URL')
-
- MMS_STREAM = r'href="(?P<video_url>mms://[^"]*)"'
- RTSP_STREAM = r'(?P<video_url>rtsp://[^"]*.mp4)'
-
- mobj = re.search(self._MEDIA_STREAM, media_link)
- if mobj is None:
- mobj = re.search(RTSP_STREAM, media_link)
- if mobj is None:
- raise ExtractorError(u'Cannot extract mms:// or rtsp:// URL')
- video_url = mobj.group('video_url')
-
- title = self._html_search_regex(
- r'<h1(?: class="beitragHeadline")?>(.*?)</h1>',
- html, u'title')
+ 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'
+ _QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh')
+
+ _TESTS = [{
+ 'url': 'https://www.zdf.de/service-und-hilfe/die-neue-zdf-mediathek/zdfmediathek-trailer-100.html',
+ 'info_dict': {
+ 'id': 'zdfmediathek-trailer-100',
+ 'ext': 'mp4',
+ 'title': 'Die neue ZDFmediathek',
+ 'description': 'md5:3003d36487fb9a5ea2d1ff60beb55e8d',
+ 'duration': 30,
+ 'timestamp': 1477627200,
+ 'upload_date': '20161028',
+ }
+ }, {
+ '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,
+ }]
+
+ @staticmethod
+ def _extract_subtitles(src):
+ subtitles = {}
+ for caption in try_get(src, lambda x: x['captions'], list) or []:
+ subtitle_url = caption.get('uri')
+ if subtitle_url and isinstance(subtitle_url, compat_str):
+ lang = caption.get('language', 'deu')
+ subtitles.setdefault(lang, []).append({
+ 'url': subtitle_url,
+ })
+ return subtitles
+
+ def _extract_format(self, video_id, formats, format_urls, meta):
+ format_url = meta.get('url')
+ if not format_url or not isinstance(format_url, compat_str):
+ return
+ if format_url in format_urls:
+ return
+ format_urls.add(format_url)
+ mime_type = meta.get('mimeType')
+ ext = determine_ext(format_url)
+ if mime_type == 'application/x-mpegURL' or ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ format_url, video_id, 'mp4', m3u8_id='hls',
+ 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))
+ 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)
+ 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,
+ })
+ 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}', 'portal')
+
+ ptmd = self._call_api(
+ urljoin(url, ptmd_path), player, url, video_id, 'metadata')
+
+ formats = []
+ track_uris = set()
+ for p in ptmd['priorityList']:
+ formitaeten = p.get('formitaeten')
+ if not isinstance(formitaeten, list):
+ continue
+ for f in formitaeten:
+ f_qualities = f.get('qualities')
+ if not isinstance(f_qualities, list):
+ continue
+ for quality in f_qualities:
+ tracks = try_get(quality, lambda x: x['audio']['tracks'], list)
+ if not tracks:
+ continue
+ for track in tracks:
+ self._extract_format(
+ video_id, formats, track_uris, {
+ 'url': track.get('uri'),
+ 'type': f.get('type'),
+ 'mimeType': f.get('mimeType'),
+ 'quality': quality.get('quality'),
+ 'language': track.get('language'),
+ })
+ self._sort_formats(formats)
+
+ thumbnails = []
+ layouts = try_get(
+ content, lambda x: x['teaserImageRef']['layouts'], dict)
+ if layouts:
+ for layout_key, layout_url in layouts.items():
+ if not isinstance(layout_url, compat_str):
+ continue
+ 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)
Rapsys Git / youtubedl / blobdiff