gitlab-com-dstftw/youtube-dl
1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
Code Issues Releases Wiki Activity

[ceskatelevize] Fix video availability check and add geo unrestricted test

Browse source
This commit is contained in:
Sergey M․ 2014-03-01 22:54:37 +07:00
parent f00fc78674
commit 7d78f0cc48
1 changed files with 40 additions and 25 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

65
youtube_dl/extractor/ceskatelevize.py
View file

@ -16,31 +16,46 @@ from ..utils import (
class CeskaTelevizeIE(InfoExtractor): class CeskaTelevizeIE(InfoExtractor):
_VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)' _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
_TESTS = [{ _TESTS = [
'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka', {
'info_dict': { 'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka',
'id': '213512120230004', 'info_dict': {
'ext': 'flv', 'id': '213512120230004',
'title': 'První republika: Španělská chřipka', 'ext': 'flv',
'duration': 3107.4, 'title': 'První republika: Španělská chřipka',
'duration': 3107.4,
},
'params': {
'skip_download': True, # requires rtmpdump
},
'skip': 'Works only from Czech Republic.',
}, },
'params': { {
'skip_download': True, # requires rtmpdump 'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt',
'info_dict': {
'id': '20138143440',
'ext': 'flv',
'title': 'Tsatsiki, maminka a policajt',
'duration': 6754.1,
},
'params': {
'skip_download': True, # requires rtmpdump
},
'skip': 'Works only from Czech Republic.',
}, },
'skip': 'Works only from Czech Republic.', {
}, { 'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt', 'info_dict': {
'info_dict': { 'id': '14716',
'id': '20138143440', 'ext': 'flv',
'ext': 'flv', 'title': 'První republika: Zpěvačka z Dupárny Bobina',
'title': 'Tsatsiki, maminka a policajt', 'duration': 90,
'duration': 6754.1, },
'params': {
'skip_download': True, # requires rtmpdump
},
}, },
'params': { ]
'skip_download': True, # requires rtmpdump
},
'skip': 'Works only from Czech Republic.',
}]
def _real_extract(self, url): def _real_extract(self, url):
url = url.replace('/porady/', '/ivysilani/').replace('/video/', '') url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
@ -50,9 +65,9 @@ class CeskaTelevizeIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
if '<p class="title">Chyba konfigurace prohlížeče.</p>' not in webpage: NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
msg = self._html_search_regex(r'<p class="title">(.+?)</p>', webpage, 'error-message') if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
raise ExtractorError(msg.replace('<br />', ' ')) raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type') typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id') episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')