[tvp] extract video id from the webpage(fixes #7799)

This commit is contained in:
Remita Amine 2016-08-05 09:44:15 +01:00
parent f65dc41b72
commit fdd0b8f8e0

View File

@ -24,6 +24,7 @@ class TVPIE(InfoExtractor):
'id': '194536', 'id': '194536',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Czas honoru, I seria odc. 13', 'title': 'Czas honoru, I seria odc. 13',
'description': 'md5:76649d2014f65c99477be17f23a4dead',
}, },
}, { }, {
'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176', 'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176',
@ -32,6 +33,16 @@ class TVPIE(InfoExtractor):
'id': '17916176', 'id': '17916176',
'ext': 'mp4', 'ext': 'mp4',
'title': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata', 'title': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata',
'description': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata',
},
}, {
# page id is not the same as video id(#7799)
'url': 'http://vod.tvp.pl/22704887/08122015-1500',
'md5': 'cf6a4705dfd1489aef8deb168d6ba742',
'info_dict': {
'id': '22680786',
'ext': 'mp4',
'title': 'Wiadomości, 08.12.2015, 15:00',
}, },
}, { }, {
'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272', 'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272',
@ -53,6 +64,39 @@ class TVPIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
video_id = self._search_regex([
r'<iframe[^>]+src="[^"]*?object_id=(\d+)',
"object_id\s*:\s*'(\d+)'"], webpage, 'video id')
return {
'_type': 'url_transparent',
'url': 'tvp:' + video_id,
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage),
'ie_key': 'TVPEmbed',
}
class TVPEmbedIE(InfoExtractor):
IE_NAME = 'tvp:embed'
IE_DESC = 'Telewizja Polska'
_VALID_URL = r'(?:tvp:|https?://[^/]+\.tvp\.(?:pl|info)/sess/tvplayer\.php\?.*?object_id=)(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.tvp.pl/sess/tvplayer.php?object_id=22670268',
'md5': '8c9cd59d16edabf39331f93bf8a766c7',
'info_dict': {
'id': '22670268',
'ext': 'mp4',
'title': 'Panorama, 07.12.2015, 15:40',
},
}, {
'url': 'tvp:22670268',
'only_matching': True,
}]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)