w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Merge branch 'master' of github.com:rg3/youtube-dl

Browse source
This commit is contained in:
Philipp Hagemeister 2013-07-01 18:21:36 +02:00
commit 2db67bc0f4
3 changed files with 24 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
test/test_youtube_lists.py
View file

@ -8,7 +8,7 @@ import json
import os import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) 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 youtube_dl.utils import *
from helper import FakeYDL from helper import FakeYDL
@ -88,5 +88,11 @@ class TestYoutubeLists(unittest.TestCase):
result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl')[0] result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl')[0]
self.assertEqual(len(result['entries']), 2) 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__': if __name__ == '__main__':
unittest.main() unittest.main()

2
youtube_dl/extractor/__init__.py
View file

@ -67,7 +67,7 @@ from .yahoo import YahooIE, YahooSearchIE
from .youjizz import YouJizzIE from .youjizz import YouJizzIE
from .youku import YoukuIE from .youku import YoukuIE
from .youporn import YouPornIE 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 from .zdf import ZDFIE

18
youtube_dl/extractor/youtube.py
View file

@ -34,7 +34,7 @@ class YoutubeIE(InfoExtractor):
(?: # the various things that can precede the ID: (?: # the various things that can precede the ID:
(?:(?:v|embed|e)/) # v/ or embed/ or e/ (?:(?:v|embed|e)/) # v/ or embed/ or e/
|(?: # or the v= param in all its forms |(?: # 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 #! (?:\?|\#!?) # the params delimiter ? or # or #!
(?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx) (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
v= v=
@ -586,7 +586,7 @@ class YoutubeIE(InfoExtractor):
if req_format is None or req_format == 'best': if req_format is None or req_format == 'best':
video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
elif req_format == 'worst': 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'): elif req_format in ('-1', 'all'):
video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
else: else:
@ -853,3 +853,17 @@ class YoutubeSearchIE(SearchInfoExtractor):
video_ids = video_ids[:n] video_ids = video_ids[:n]
videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids] videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids]
return self.playlist_result(videos, query) 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]