Support downloading Youtube videos via tube.majestyc.net

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 0835c447c1cf6955f17d246a461948be25bfa3fd..d95423f7db63985742c44fb43869f668011c9fae 100644 (file)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -95,7 +95,7 @@ class InfoExtractor(object):
 class YoutubeIE(InfoExtractor):
        """Information extractor for youtube.com."""
 
-       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
+       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|tube.majestyc.net/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
        _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
        _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
        _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
@@ -1622,6 +1622,98 @@ class YoutubeUserIE(InfoExtractor):
                        self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id])
 
 
+class BlipTVUserIE(InfoExtractor):
+       """Information Extractor for blip.tv users."""
+
+       _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
+       _PAGE_SIZE = 12
+       IE_NAME = u'blip.tv:user'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+
+       def report_download_page(self, username, pagenum):
+               """Report attempt to download user page."""
+               self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' %
+                               (self.IE_NAME, username, pagenum))
+
+       def _real_extract(self, url):
+               # Extract username
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+                       return
+
+               username = mobj.group(1)
+
+               page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
+
+               request = urllib2.Request(url)
+
+               try:
+                       page = urllib2.urlopen(request).read().decode('utf-8')
+                       mobj = re.search(r'data-users-id="([^"]+)"', page)
+                       page_base = page_base % mobj.group(1)
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+                       return
+
+
+               # Download video ids using BlipTV Ajax calls. Result size per
+               # query is limited (currently to 12 videos) so we need to query
+               # page by page until there are no video ids - it means we got
+               # all of them.
+
+               video_ids = []
+               pagenum = 1
+
+               while True:
+                       self.report_download_page(username, pagenum)
+
+                       request = urllib2.Request( page_base + "&page=" + str(pagenum) )
+
+                       try:
+                               page = urllib2.urlopen(request).read().decode('utf-8')
+                       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="/([^"]+)"', page):
+                               if mobj.group(1) not in ids_in_page:
+                                       ids_in_page.append(unescapeHTML(mobj.group(1)))
+
+                       video_ids.extend(ids_in_page)
+
+                       # A little optimization - if current page is not
+                       # "full", ie. does not contain PAGE_SIZE video ids then
+                       # we can assume that this page is the last one - there
+                       # are no more ids on further pages - no need to query
+                       # again.
+
+                       if len(ids_in_page) < self._PAGE_SIZE:
+                               break
+
+                       pagenum += 1
+
+               all_ids_count = len(video_ids)
+               playliststart = self._downloader.params.get('playliststart', 1) - 1
+               playlistend = self._downloader.params.get('playlistend', -1)
+
+               if playlistend == -1:
+                       video_ids = video_ids[playliststart:]
+               else:
+                       video_ids = video_ids[playliststart:playlistend]
+
+               self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" %
+                               (self.IE_NAME, username, all_ids_count, len(video_ids)))
+
+               for video_id in video_ids:
+                       self._downloader.download([u'http://blip.tv/'+video_id])
+
+
 class DepositFilesIE(InfoExtractor):
        """Information extractor for depositfiles.com"""
 
@@ -1920,7 +2012,7 @@ class BlipTVIE(InfoExtractor):
                else:
                        cchar = '?'
                json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
-               request = urllib2.Request(json_url)
+               request = urllib2.Request(json_url.encode('utf-8'))
                self.report_extraction(mobj.group(1))
                info = None
                try:
@@ -1978,6 +2070,7 @@ class BlipTVIE(InfoExtractor):
                                self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
                                return
 
+               std_headers['User-Agent'] = 'iTunes/10.6.1'
                return [info]