adding second vimeo url

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 1575a3434d3258d0ff743c1275b4edf96f2bfab2..6e59ba8fd740c789435c3ada8ba0a13dcb2297a8 100644 (file)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -102,6 +102,7 @@ class YoutubeIE(InfoExtractor):
                             (?:https?://)?                                       # http(s):// (optional)
                             (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
                                tube\.majestyc\.net/)                             # the various hostnames, with wildcard subdomains
+                            (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
                             (?!view_play_list|my_playlists|artist|playlist)      # ignore playlist URLs
                             (?:                                                  # the various things that can precede the ID:
                                 (?:(?:v|embed|e)/)                               # v/ or embed/ or e/
@@ -413,6 +414,12 @@ class YoutubeIE(InfoExtractor):
                        except Trouble as trouble:
                                self._downloader.trouble(trouble[0])
 
+               if 'length_seconds' not in video_info:
+                       self._downloader.trouble(u'WARNING: unable to extract video duration')
+                       video_duration = ''
+               else:
+                       video_duration = urllib.unquote_plus(video_info['length_seconds'][0])
+
                # token
                video_token = urllib.unquote_plus(video_info['token'][0])
 
@@ -479,7 +486,8 @@ class YoutubeIE(InfoExtractor):
                                'thumbnail':    video_thumbnail.decode('utf-8'),
                                'description':  video_description,
                                'player_url':   player_url,
-                               'subtitles':    video_subtitles
+                               'subtitles':    video_subtitles,
+                               'duration':             video_duration
                        })
                return results
 
@@ -1508,7 +1516,7 @@ class YahooSearchIE(InfoExtractor):
 class YoutubePlaylistIE(InfoExtractor):
        """Information Extractor for YouTube playlists."""
 
-       _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+       _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
        _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
        _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s'
        _MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
@@ -1578,6 +1586,56 @@ class YoutubePlaylistIE(InfoExtractor):
                return
 
 
+class YoutubeChannelIE(InfoExtractor):
+       """Information Extractor for YouTube channels."""
+
+       _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$"
+       _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
+       _MORE_PAGES_INDICATOR = r'yt-uix-button-content">Next' # TODO
+       IE_NAME = u'youtube:channel'
+
+       def report_download_page(self, channel_id, pagenum):
+               """Report attempt to download channel page with given number."""
+               self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
+
+       def _real_extract(self, url):
+               # Extract channel id
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+                       return
+
+               # Download channel pages
+               channel_id = mobj.group(1)
+               video_ids = []
+               pagenum = 1
+
+               while True:
+                       self.report_download_page(channel_id, pagenum)
+                       url = self._TEMPLATE_URL % (channel_id, pagenum)
+                       request = urllib2.Request(url)
+                       try:
+                               page = urllib2.urlopen(request).read()
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+                               return
+
+                       # Extract video identifiers
+                       ids_in_page = []
+                       for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page):
+                               if mobj.group(1) not in ids_in_page:
+                                       ids_in_page.append(mobj.group(1))
+                       video_ids.extend(ids_in_page)
+
+                       if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+                               break
+                       pagenum = pagenum + 1
+
+               for id in video_ids:
+                       self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
+               return
+
+
 class YoutubeUserIE(InfoExtractor):
        """Information Extractor for YouTube users."""