+ # This is not a real id, it can be for example AJT for the news
+ # http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
+ video_id = mobj.group('id')
+ return video_id, lang
+
+ def _extract_from_json_url(self, json_url, video_id, lang, title=None):
+ info = self._download_json(json_url, video_id)
+ player_info = info['videoJsonPlayer']
+
+ vsr = player_info['VSR']
+
+ if not vsr:
+ raise ExtractorError(
+ 'Video %s is not available' % player_info.get('VID') or video_id,
+ expected=True)
+
+ upload_date_str = player_info.get('shootingDate')
+ if not upload_date_str:
+ upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0]
+
+ title = (player_info.get('VTI') or title or player_info['VID']).strip()
+ subtitle = player_info.get('VSU', '').strip()
+ if subtitle:
+ title += ' - %s' % subtitle
+
+ info_dict = {
+ 'id': player_info['VID'],
+ 'title': title,
+ 'description': player_info.get('VDE'),
+ 'upload_date': unified_strdate(upload_date_str),
+ 'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
+ }
+ qfunc = qualities(['HQ', 'MQ', 'EQ', 'SQ'])
+
+ LANGS = {
+ 'fr': 'F',
+ 'de': 'A',
+ 'en': 'E[ANG]',
+ 'es': 'E[ESP]',
+ }
+
+ langcode = LANGS.get(lang, lang)
+
+ formats = []
+ for format_id, format_dict in vsr.items():
+ f = dict(format_dict)
+ versionCode = f.get('versionCode')
+ l = re.escape(langcode)
+
+ # Language preference from most to least priority
+ # Reference: section 5.6.3 of
+ # http://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-05.pdf
+ PREFERENCES = (
+ # original version in requested language, without subtitles
+ r'VO{0}$'.format(l),
+ # original version in requested language, with partial subtitles in requested language
+ r'VO{0}-ST{0}$'.format(l),
+ # original version in requested language, with subtitles for the deaf and hard-of-hearing in requested language
+ r'VO{0}-STM{0}$'.format(l),
+ # non-original (dubbed) version in requested language, without subtitles
+ r'V{0}$'.format(l),
+ # non-original (dubbed) version in requested language, with subtitles partial subtitles in requested language
+ r'V{0}-ST{0}$'.format(l),
+ # non-original (dubbed) version in requested language, with subtitles for the deaf and hard-of-hearing in requested language
+ r'V{0}-STM{0}$'.format(l),
+ # original version in requested language, with partial subtitles in different language
+ r'VO{0}-ST(?!{0}).+?$'.format(l),
+ # original version in requested language, with subtitles for the deaf and hard-of-hearing in different language
+ r'VO{0}-STM(?!{0}).+?$'.format(l),
+ # original version in different language, with partial subtitles in requested language
+ r'VO(?:(?!{0}).+?)?-ST{0}$'.format(l),
+ # original version in different language, with subtitles for the deaf and hard-of-hearing in requested language
+ r'VO(?:(?!{0}).+?)?-STM{0}$'.format(l),
+ # original version in different language, without subtitles
+ r'VO(?:(?!{0}))?$'.format(l),
+ # original version in different language, with partial subtitles in different language
+ r'VO(?:(?!{0}).+?)?-ST(?!{0}).+?$'.format(l),
+ # original version in different language, with subtitles for the deaf and hard-of-hearing in different language
+ r'VO(?:(?!{0}).+?)?-STM(?!{0}).+?$'.format(l),
+ )
+
+ for pref, p in enumerate(PREFERENCES):
+ if re.match(p, versionCode):
+ lang_pref = len(PREFERENCES) - pref
+ break
+ else:
+ lang_pref = -1
+
+ format = {
+ 'format_id': format_id,
+ 'preference': -10 if f.get('videoFormat') == 'M3U8' else None,
+ 'language_preference': lang_pref,
+ 'format_note': '%s, %s' % (f.get('versionCode'), f.get('versionLibelle')),
+ 'width': int_or_none(f.get('width')),
+ 'height': int_or_none(f.get('height')),
+ 'tbr': int_or_none(f.get('bitrate')),
+ 'quality': qfunc(f.get('quality')),
+ }
+
+ if f.get('mediaType') == 'rtmp':
+ format['url'] = f['streamer']
+ format['play_path'] = 'mp4:' + f['url']
+ format['ext'] = 'flv'
+ else:
+ format['url'] = f['url']
+
+ formats.append(format)
+
+ self._check_formats(formats, video_id)
+ self._sort_formats(formats)
+
+ info_dict['formats'] = formats
+ return info_dict
+
+
+class ArteTVPlus7IE(ArteTVBaseIE):
+ IE_NAME = 'arte.tv:+7'
+ _VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/(?:[^/]+/)?(?P<lang>fr|de|en|es)/(?:videos/)?(?:[^/]+/)*(?P<id>[^/?#&]+)'
+
+ _TESTS = [{
+ 'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.arte.tv/de/videos/048696-000-A/der-kluge-bauch-unser-zweites-gehirn',
+ 'only_matching': True,
+ }]
+
+ @classmethod
+ def suitable(cls, url):
+ return False if ArteTVPlaylistIE.suitable(url) else super(ArteTVPlus7IE, cls).suitable(url)
+
+ def _real_extract(self, url):
+ video_id, lang = self._extract_url_info(url)
+ webpage = self._download_webpage(url, video_id)
+ return self._extract_from_webpage(webpage, video_id, lang)
+
+ def _extract_from_webpage(self, webpage, video_id, lang):
+ patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']')
+ ids = (video_id, '')
+ # some pages contain multiple videos (like
+ # http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D),
+ # so we first try to look for json URLs that contain the video id from
+ # the 'vid' parameter.
+ patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates]
+ json_url = self._html_search_regex(
+ patterns, webpage, 'json vp url', default=None)
+ if not json_url:
+ def find_iframe_url(webpage, default=NO_DEFAULT):
+ return self._html_search_regex(
+ r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
+ webpage, 'iframe url', group='url', default=default)
+
+ iframe_url = find_iframe_url(webpage, None)
+ if not iframe_url:
+ embed_url = self._html_search_regex(
+ r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None)
+ if embed_url:
+ player = self._download_json(
+ embed_url, video_id, 'Downloading player page')
+ iframe_url = find_iframe_url(player['html'])
+ # en and es URLs produce react-based pages with different layout (e.g.
+ # http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world)
+ if not iframe_url:
+ program = self._search_regex(
+ r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n',
+ webpage, 'program', default=None)
+ if program:
+ embed_html = self._parse_json(program, video_id)
+ if embed_html:
+ iframe_url = find_iframe_url(embed_html['embed_html'])
+ if iframe_url:
+ json_url = compat_parse_qs(
+ compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
+ if json_url:
+ title = self._search_regex(
+ r'<h3[^>]+title=(["\'])(?P<title>.+?)\1',
+ webpage, 'title', default=None, group='title')
+ return self._extract_from_json_url(json_url, video_id, lang, title=title)
+ # Different kind of embed URL (e.g.
+ # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium)
+ entries = [
+ self.url_result(url)
+ for _, url in re.findall(r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', webpage)]
+ return self.playlist_result(entries)
+
+
+# It also uses the arte_vp_url url from the webpage to extract the information
+class ArteTVCreativeIE(ArteTVPlus7IE):
+ IE_NAME = 'arte.tv:creative'
+ _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+
+ _TESTS = [{
+ 'url': 'http://creative.arte.tv/fr/episode/osmosis-episode-1',
+ 'info_dict': {
+ 'id': '057405-001-A',
+ 'ext': 'mp4',
+ 'title': 'OSMOSIS - N\'AYEZ PLUS PEUR D\'AIMER (1)',
+ 'upload_date': '20150716',
+ },
+ }, {
+ 'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion',
+ 'playlist_count': 11,
+ 'add_ie': ['Youtube'],
+ }, {
+ 'url': 'http://creative.arte.tv/de/episode/agentur-amateur-4-der-erste-kunde',
+ 'only_matching': True,
+ }]
+
+
+class ArteTVInfoIE(ArteTVPlus7IE):
+ IE_NAME = 'arte.tv:info'
+ _VALID_URL = r'https?://info\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+
+ _TESTS = [{
+ 'url': 'http://info.arte.tv/fr/service-civique-un-cache-misere',
+ 'info_dict': {
+ 'id': '067528-000-A',
+ 'ext': 'mp4',
+ 'title': 'Service civique, un cache misère ?',
+ 'upload_date': '20160403',
+ },
+ }]
+
+
+class ArteTVFutureIE(ArteTVPlus7IE):
+ IE_NAME = 'arte.tv:future'
+ _VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
+
+ _TESTS = [{
+ 'url': 'http://future.arte.tv/fr/info-sciences/les-ecrevisses-aussi-sont-anxieuses',
+ 'info_dict': {
+ 'id': '050940-028-A',
+ 'ext': 'mp4',
+ 'title': 'Les écrevisses aussi peuvent être anxieuses',
+ 'upload_date': '20140902',
+ },
+ }, {
+ 'url': 'http://future.arte.tv/fr/la-science-est-elle-responsable',
+ 'only_matching': True,
+ }]
+
+
+class ArteTVDDCIE(ArteTVPlus7IE):
+ IE_NAME = 'arte.tv:ddc'
+ _VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>[^/?#&]+)'
+
+ _TESTS = []
+
+ def _real_extract(self, url):
+ video_id, lang = self._extract_url_info(url)
+ if lang == 'folge':
+ lang = 'de'
+ elif lang == 'emission':
+ lang = 'fr'
+ webpage = self._download_webpage(url, video_id)
+ scriptElement = get_element_by_attribute('class', 'visu_video_block', webpage)
+ script_url = self._html_search_regex(r'src="(.*?)"', scriptElement, 'script url')
+ javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator')
+ json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, 'json url')
+ return self._extract_from_json_url(json_url, video_id, lang)
+
+
+class ArteTVConcertIE(ArteTVPlus7IE):
+ IE_NAME = 'arte.tv:concert'
+ _VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
+
+ _TESTS = [{
+ 'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde',
+ 'md5': '9ea035b7bd69696b67aa2ccaaa218161',
+ 'info_dict': {
+ 'id': '186',
+ 'ext': 'mp4',
+ 'title': 'The Notwist im Pariser Konzertclub "Divan du Monde"',
+ 'upload_date': '20140128',
+ 'description': 'md5:486eb08f991552ade77439fe6d82c305',
+ },
+ }]
Rapsys Git / youtubedl / blobdiff