- _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>[^/?#&]+)'
Rapsys Git / youtubedl / blobdiff