Add support for the Dailymotion

Based slightly (idea and one regular expression) on the old anonymous
dailymotion-dl.pl, but with fixes (more robust regular expression,
extracting author, support for domains other than .com). Simpler
due to the fact that youtube-dl provides all needed functionalities.

diff --git a/youtube-dl b/youtube-dl
index fba11fab03d6d1ef7f8eaece0a03a64ff22ae64c..b94fe4ce2d772a606aa83dab147528e624b59626 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -1085,6 +1085,123 @@ class MetacafeIE(InfoExtractor):
                        self._downloader.trouble(u'ERROR: format not available for video')
 
 
+class DailymotionIE(InfoExtractor):
+       """Information Extractor for Dailymotion"""
+
+       _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
+       _DISCLAIMER = ''
+       _FILTER_POST = ''
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+
+       @staticmethod
+       def suitable(url):
+               return (re.match(DailymotionIE._VALID_URL, url) is not None)
+
+       def report_disclaimer(self):
+               """Report disclaimer retrieval."""
+               self._downloader.to_stdout(u'[dailymotion] Retrieving disclaimer')
+
+       def report_age_confirmation(self):
+               """Report attempt to confirm age."""
+               self._downloader.to_stdout(u'[dailymotion] Confirming age')
+       
+       def report_download_webpage(self, video_id):
+               """Report webpage download."""
+               self._downloader.to_stdout(u'[dailymotion] %s: Downloading webpage' % video_id)
+       
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_stdout(u'[dailymotion] %s: Extracting information' % video_id)
+
+       def _real_initialize(self):
+               return
+
+               # Retrieve disclaimer
+               request = urllib2.Request(self._DISCLAIMER, None, std_headers)
+               try:
+                       self.report_disclaimer()
+                       disclaimer = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
+                       return
+
+               # Confirm age
+               disclaimer_form = {
+                       'filters': '0',
+                       'submit': "Continue - I'm over 18",
+                       }
+               request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
+               try:
+                       self.report_age_confirmation()
+                       disclaimer = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
+                       return
+       
+       def _real_extract(self, url):
+               # Extract id and simplified title from URL
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+
+               video_id = mobj.group(1)
+
+               simple_title = mobj.group(2).decode('utf-8')
+               video_extension = 'flv'
+
+               # Retrieve video webpage to extract further information
+               request = urllib2.Request(url)
+               try:
+                       self.report_download_webpage(video_id)
+                       webpage = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
+                       return
+
+               # Extract URL, uploader and title from webpage
+               self.report_extraction(video_id)
+               mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract media URL')
+                       return
+               mediaURL = urllib.unquote(mobj.group(1))
+
+               # 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)
+               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)<div class="dmco_html owner"><a class="name" href="/.+">(.+?)</a></div>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+                       return
+               video_uploader = mobj.group(1)
+
+               try:
+                       # Process video information
+                       self._downloader.process_info({
+                               'id':           video_id.decode('utf-8'),
+                               'url':          video_url.decode('utf-8'),
+                               'uploader':     video_uploader.decode('utf-8'),
+                               'title':        video_title,
+                               'stitle':       simple_title,
+                               'ext':          video_extension.decode('utf-8'),
+                               'format':       u'NA',
+                               'player_url':   None,
+                       })
+               except UnavailableFormatError:
+                       self._downloader.trouble(u'ERROR: format not available for video')
+
 class GoogleIE(InfoExtractor):
        """Information extractor for video.google.com."""
 
@@ -2101,6 +2218,7 @@ if __name__ == '__main__':
                # Information extractors
                youtube_ie = YoutubeIE()
                metacafe_ie = MetacafeIE(youtube_ie)
+               dailymotion_ie = DailymotionIE()
                youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
                youtube_user_ie = YoutubeUserIE(youtube_ie)
                youtube_search_ie = YoutubeSearchIE(youtube_ie)
@@ -2141,6 +2259,7 @@ if __name__ == '__main__':
                fd.add_info_extractor(youtube_pl_ie)
                fd.add_info_extractor(youtube_user_ie)
                fd.add_info_extractor(metacafe_ie)
+               fd.add_info_extractor(dailymotion_ie)
                fd.add_info_extractor(youtube_ie)
                fd.add_info_extractor(google_ie)
                fd.add_info_extractor(google_search_ie)