diff options
| -rw-r--r-- | test/test_youtube_lists.py | 8 | ||||
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/youtube.py | 18 | 
3 files changed, 24 insertions, 4 deletions
| diff --git a/test/test_youtube_lists.py b/test/test_youtube_lists.py index 4486b7eb0..dd9e292b0 100644 --- a/test/test_youtube_lists.py +++ b/test/test_youtube_lists.py @@ -8,7 +8,7 @@ import json  import os  sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from youtube_dl.extractor import YoutubeUserIE, YoutubePlaylistIE, YoutubeIE, YoutubeChannelIE +from youtube_dl.extractor import YoutubeUserIE, YoutubePlaylistIE, YoutubeIE, YoutubeChannelIE, YoutubeShowIE  from youtube_dl.utils import *  from helper import FakeYDL @@ -88,5 +88,11 @@ class TestYoutubeLists(unittest.TestCase):          result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl')[0]          self.assertEqual(len(result['entries']), 2) +    def test_youtube_show(self): +        dl = FakeYDL() +        ie = YoutubeShowIE(dl) +        result = ie.extract('http://www.youtube.com/show/airdisasters') +        self.assertTrue(len(result) >= 4) +  if __name__ == '__main__':      unittest.main() diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index ba0e86713..ac2e5f0e7 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -67,7 +67,7 @@ from .yahoo import YahooIE, YahooSearchIE  from .youjizz import YouJizzIE  from .youku import YoukuIE  from .youporn import YouPornIE -from .youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE +from .youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE, YoutubeShowIE  from .zdf import ZDFIE diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 109c8a93f..76b297ea5 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -34,7 +34,7 @@ class YoutubeIE(InfoExtractor):                           (?:                                                  # the various things that can precede the ID:                               (?:(?:v|embed|e)/)                               # v/ or embed/ or e/                               |(?:                                             # or the v= param in all its forms -                                 (?:watch(?:_popup)?(?:\.php)?)?              # preceding watch(_popup|.php) or nothing (like /?v=xxxx) +                                 (?:watch|movie(?:_popup)?(?:\.php)?)?              # preceding watch(_popup|.php) or nothing (like /?v=xxxx)                                   (?:\?|\#!?)                                  # the params delimiter ? or # or #!                                   (?:.*?&)?                                    # any other preceding param (like /?s=tuff&v=xxxx)                                   v= @@ -586,7 +586,7 @@ class YoutubeIE(InfoExtractor):              if req_format is None or req_format == 'best':                  video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality              elif req_format == 'worst': -                video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality +                video_url_list = [(existing_formats[-1], url_map[existing_formats[-1]])] # worst quality              elif req_format in ('-1', 'all'):                  video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats              else: @@ -853,3 +853,17 @@ class YoutubeSearchIE(SearchInfoExtractor):              video_ids = video_ids[:n]          videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids]          return self.playlist_result(videos, query) + + +class YoutubeShowIE(InfoExtractor): +    _VALID_URL = r'https?://www\.youtube\.com/show/(.*)' +    IE_NAME = u'youtube:show' + +    def _real_extract(self, url): +        mobj = re.match(self._VALID_URL, url) +        show_name = mobj.group(1) +        webpage = self._download_webpage(url, show_name, u'Downloading show webpage') +        # There's one playlist for each season of the show +        m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage)) +        self.to_screen(u'%s: Found %s seasons' % (show_name, len(m_seasons))) +        return [self.url_result('https://www.youtube.com' + season.group(1), 'YoutubePlaylist') for season in m_seasons] | 
