patched to add Google Video and Photobucket support

diff --git a/LATEST_VERSION b/LATEST_VERSION
index 382e966d8ada4563018317d2d1633c35e1736c8d..7ed3afa000beda9d4307742f20df8a1d4a7bcb06 100644 (file)
--- a/LATEST_VERSION
+++ b/LATEST_VERSION
@@ -1 +1 @@
-2010.01.06
+2010.01.15

diff --git a/youtube-dl b/youtube-dl
index 640ed4bdc801855e71a2fd6809dd65fc0724fb87..732ebce1d3283e2ec7b365eccc9a33e86394cd33 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -2,6 +2,7 @@
 # -*- coding: utf-8 -*-
 # Author: Ricardo Garcia Gonzalez
 # Author: Danny Colligan
+# Author: Benjamin Johnson
 # License: Public domain code
 import htmlentitydefs
 import httplib
@@ -936,6 +937,159 @@ class MetacafeIE(InfoExtractor):
                        self._downloader.trouble(u'ERROR: format not available for video')
 
 
+class GoogleIE(InfoExtractor):
+       """Information extractor for video.google.com."""
+
+       _VALID_URL = r'(?:http://)?video\.google\.com/videoplay\?docid=([^\&]+).*'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+
+       @staticmethod
+       def suitable(url):
+               return (re.match(GoogleIE._VALID_URL, url) is not None)
+
+       def report_download_webpage(self, video_id):
+               """Report webpage download."""
+               self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id)
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id)
+
+       def _real_initialize(self):
+               return
+
+       def _real_extract(self, url):
+               # Extract id 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)
+
+               video_extension = 'mp4'
+
+               # Retrieve video webpage to extract further information
+               request = urllib2.Request('http://video.google.com/videoplay?docid=%s' % video_id)
+               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 to retrieve video webpage: %s' % str(err))
+                       return
+
+               # Extract URL, uploader, and title from webpage
+               self.report_extraction(video_id)
+               mobj = re.search(r"download_url:'(.*)'", webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract media URL')
+                       return
+               mediaURL = urllib.unquote(mobj.group(1))
+               mediaURL = mediaURL.replace('\\x3d', '\x3d')
+               mediaURL = mediaURL.replace('\\x26', '\x26')
+
+               video_url = mediaURL
+
+               mobj = re.search(r'<title>(.*)</title>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract title')
+                       return
+               video_title = mobj.group(1).decode('utf-8')
+
+               # Google Video doesn't show uploader nicknames?
+               video_uploader = 'uploader'
+
+               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.decode('utf-8'),
+                               'stitle':       video_title.decode('utf-8'),
+                               'ext':          video_extension.decode('utf-8'),
+                       })
+               except UnavailableFormatError:
+                       self._downloader.trouble(u'ERROR: format not available for video')
+
+
+class PhotobucketIE(InfoExtractor):
+       """Information extractor for photobucket.com."""
+
+       _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+
+       @staticmethod
+       def suitable(url):
+               return (re.match(PhotobucketIE._VALID_URL, url) is not None)
+
+       def report_download_webpage(self, video_id):
+               """Report webpage download."""
+               self._downloader.to_stdout(u'[photobucket] %s: Downloading webpage' % video_id)
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id)
+
+       def _real_initialize(self):
+               return
+
+       def _real_extract(self, url):
+               # Extract id 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)
+
+               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 to retrieve video webpage: %s' % str(err))
+                       return
+
+               # Extract URL, uploader, and title from webpage
+               self.report_extraction(video_id)
+               mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract media URL')
+                       return
+               mediaURL = urllib.unquote(mobj.group(1))
+
+               video_url = mediaURL
+
+               mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</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_uploader = mobj.group(2).decode('utf-8')
+
+               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.decode('utf-8'),
+                               'stitle':       video_title.decode('utf-8'),
+                               'ext':          video_extension.decode('utf-8'),
+                       })
+               except UnavailableFormatError:
+                       self._downloader.trouble(u'ERROR: format not available for video')
+
+
 class YoutubeSearchIE(InfoExtractor):
        """Information Extractor for YouTube search queries."""
        _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
@@ -1314,6 +1468,8 @@ if __name__ == '__main__':
                youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
                youtube_user_ie = YoutubeUserIE(youtube_ie)
                youtube_search_ie = YoutubeSearchIE(youtube_ie)
+               google_ie = GoogleIE()
+               photobucket_ie = PhotobucketIE()
 
                # File downloader
                fd = FileDownloader({
@@ -1339,6 +1495,8 @@ if __name__ == '__main__':
                fd.add_info_extractor(youtube_user_ie)
                fd.add_info_extractor(metacafe_ie)
                fd.add_info_extractor(youtube_ie)
+               fd.add_info_extractor(google_ie)
+               fd.add_info_extractor(photobucket_ie)
 
                # Update version
                if opts.update_self: