Merge remote-tracking branch 'knagano/master'

[youtube-dl.git] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 017a461..781dff7 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -15,7 +15,7 @@ __author__  = (
        )
 
 __license__ = 'Public Domain'
-__version__ = '2011.09.06-phihag'
+__version__ = '2011.09.13'
 
 UPDATE_URL = 'https://raw.github.com/phihag/youtube-dl/master/youtube-dl'
 
@@ -1523,6 +1523,7 @@ class DailymotionIE(InfoExtractor):
 
                # Retrieve video webpage to extract further information
                request = urllib2.Request(url)
+               request.add_header('Cookie', 'family_filter=off')
                try:
                        self.report_download_webpage(video_id)
                        webpage = urllib2.urlopen(request).read()
@@ -1532,25 +1533,29 @@ class DailymotionIE(InfoExtractor):
 
                # Extract URL, uploader and title from webpage
                self.report_extraction(video_id)
-               mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
+               mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract media URL')
                        return
-               mediaURL = urllib.unquote(mobj.group(1))
+               sequence = urllib.unquote(mobj.group(1))
+               mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract media URL')
+                       return
+               mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')
 
                # if needed add http://www.dailymotion.com/ if relative URL
 
                video_url = mediaURL
 
-               # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
-               mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
+               mobj = re.search(r'(?im)<title>Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?</title>', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract title')
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
 
-               mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', webpage)
+               mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
                        return
@@ -1917,7 +1922,6 @@ class YahooIE(InfoExtractor):
                                'thumbnail':    video_thumbnail.decode('utf-8'),
                                'description':  video_description,
                                'thumbnail':    video_thumbnail,
-                               'description':  video_description,
                                'player_url':   None,
                        })
                except UnavailableVideoError:
@@ -3037,9 +3041,9 @@ class MyVideoIE(InfoExtractor):
                        self._downloader.trouble(u'\nERROR: Unable to download video')
 
 class ComedyCentralIE(InfoExtractor):
-       """Information extractor for blip.tv"""
+       """Information extractor for The Daily Show and Colbert Report """
 
-       _VALID_URL = r'^(?:https?://)?(www\.)?(thedailyshow|colbertnation)\.com/full-episodes/(.*)$'
+       _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
 
        @staticmethod
        def suitable(url):
@@ -3064,15 +3068,39 @@ class ComedyCentralIE(InfoExtractor):
                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
                        return
-               epTitle = mobj.group(3)
+
+               if mobj.group('shortname'):
+                       if mobj.group('shortname') in ('tds', 'thedailyshow'):
+                               url = 'http://www.thedailyshow.com/full-episodes/'
+                       else:
+                               url = 'http://www.colbertnation.com/full-episodes/'
+                       mobj = re.match(self._VALID_URL, url)
+                       assert mobj is not None
+
+               dlNewest = not mobj.group('episode')
+               if dlNewest:
+                       epTitle = mobj.group('showname')
+               else:
+                       epTitle = mobj.group('episode')
 
                req = urllib2.Request(url)
                self.report_extraction(epTitle)
                try:
-                       html = urllib2.urlopen(req).read()
+                       htmlHandle = urllib2.urlopen(req)
+                       html = htmlHandle.read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
                        return
+               if dlNewest:
+                       url = htmlHandle.geturl()
+                       mobj = re.match(self._VALID_URL, url)
+                       if mobj is None:
+                               self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
+                               return
+                       if mobj.group('episode') == '':
+                               self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
+                               return
+                       epTitle = mobj.group('episode')
 
                mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/(.*?:episode:([^:]*):)(.*?))"/>', html)
                if len(mMovieParams) == 0:
@@ -3084,9 +3112,9 @@ class ComedyCentralIE(InfoExtractor):
                        'colbertnation.com': 3,
                }.get(show_id, 4)
                OFFSET = {
-                       'thedailyshow.com': -ACT_COUNT,
+                       'thedailyshow.com': 1,
                        'colbertnation.com': 1,
-               }.get(show_id, -ACT_COUNT)
+               }.get(show_id, 1)
 
                first_player_url = mMovieParams[0][0]
                startMediaNum = int(mMovieParams[0][3]) + OFFSET