Imported Upstream version 2010.08.04

[youtubedl] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 5fd331e79720bb0e50d92efaa336cad01706f6d0..d5469495404ca1ca9640a0a619628c511edf4f59 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -27,7 +27,7 @@ except ImportError:
        from cgi import parse_qs
 
 std_headers = {
        from cgi import parse_qs
 
 std_headers = {

-       'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.7) Gecko/20100720 Firefox/3.6.7',
+       'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.8) Gecko/20100723 Firefox/3.6.8',

        'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
        'Accept-Language': 'en-us,en;q=0.5',
        'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
        'Accept-Language': 'en-us,en;q=0.5',


@@ -287,16 +287,6 @@ class FileDownloader(object):
                multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
                return long(round(number * multiplier))
 
                multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
                return long(round(number * multiplier))
 

-       @staticmethod
-       def verify_url(url):
-               """Verify a URL is valid and data could be downloaded. Return real data URL."""
-               request = urllib2.Request(url, None, std_headers)
-               data = urllib2.urlopen(request)
-               data.read(1)
-               url = data.geturl()
-               data.close()
-               return url
-

        def add_info_extractor(self, ie):
                """Add an InfoExtractor object to the end of the list."""
                self._ies.append(ie)
        def add_info_extractor(self, ie):
                """Add an InfoExtractor object to the end of the list."""
                self._ies.append(ie)


@@ -396,13 +386,6 @@ class FileDownloader(object):
                """Process a single dictionary returned by an InfoExtractor."""
                # Do nothing else if in simulate mode
                if self.params.get('simulate', False):
                """Process a single dictionary returned by an InfoExtractor."""
                # Do nothing else if in simulate mode
                if self.params.get('simulate', False):

-                       # Verify URL if it's an HTTP one
-                       if info_dict['url'].startswith('http'):
-                               try:
-                                       self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')
-                               except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
-                                       raise UnavailableVideoError
-

                        # Forced printings
                        if self.params.get('forcetitle', False):
                                print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
                        # Forced printings
                        if self.params.get('forcetitle', False):
                                print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')


@@ -539,32 +522,50 @@ class FileDownloader(object):
 
                count = 0
                retries = self.params.get('retries', 0)
 
                count = 0
                retries = self.params.get('retries', 0)

-               while True:
+               while count <= retries:

                        # Establish connection
                        try:
                                data = urllib2.urlopen(request)
                                break
                        except (urllib2.HTTPError, ), err:
                        # Establish connection
                        try:
                                data = urllib2.urlopen(request)
                                break
                        except (urllib2.HTTPError, ), err:

-                               if err.code == 503:
-                                       # Retry in case of HTTP error 503
-                                       count += 1
-                                       if count <= retries:
-                                               self.report_retry(count, retries)
-                                               continue
-                               if err.code != 416: #  416 is 'Requested range not satisfiable'
+                               if err.code != 503 and err.code != 416:
+                                       # Unexpected HTTP error

                                        raise
                                        raise

-                               # Unable to resume
-                               data = urllib2.urlopen(basic_request)
-                               content_length = data.info()['Content-Length']
-
-                               if content_length is not None and long(content_length) == resume_len:
-                                       # Because the file had already been fully downloaded
-                                       self.report_file_already_downloaded(filename)
-                                       return True
-                               else:
-                                       # Because the server didn't let us
-                                       self.report_unable_to_resume()
-                                       open_mode = 'wb'
+                               elif err.code == 416:
+                                       # Unable to resume (requested range not satisfiable)
+                                       try:
+                                               # Open the connection again without the range header
+                                               data = urllib2.urlopen(basic_request)
+                                               content_length = data.info()['Content-Length']
+                                       except (urllib2.HTTPError, ), err:
+                                               if err.code != 503:
+                                                       raise
+                                       else:
+                                               # Examine the reported length
+                                               if (content_length is not None and
+                                                   (resume_len - 100 < long(content_length) < resume_len + 100)):
+                                                       # The file had already been fully downloaded.
+                                                       # Explanation to the above condition: in issue #175 it was revealed that
+                                                       # YouTube sometimes adds or removes a few bytes from the end of the file,
+                                                       # changing the file size slightly and causing problems for some users. So
+                                                       # I decided to implement a suggested change and consider the file
+                                                       # completely downloaded if the file size differs less than 100 bytes from
+                                                       # the one in the hard drive.
+                                                       self.report_file_already_downloaded(filename)
+                                                       return True
+                                               else:
+                                                       # The length does not match, we start the download over
+                                                       self.report_unable_to_resume()
+                                                       open_mode = 'wb'
+                                                       break
+                       # Retry
+                       count += 1
+                       if count <= retries:
+                               self.report_retry(count, retries)
+
+               if count > retries:
+                       self.trouble(u'ERROR: giving up after %s retries' % retries)
+                       return False

 
                data_len = data.info().get('Content-length', None)
                data_len_str = self.format_bytes(data_len)
 
                data_len = data.info().get('Content-length', None)
                data_len_str = self.format_bytes(data_len)


@@ -844,6 +845,14 @@ class YoutubeIE(InfoExtractor):
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                                self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
                                return
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                                self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
                                return

+               if 'token' not in video_info:
+                       if 'reason' in video_info:
+                               self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0])
+                       else:
+                               self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
+                       return
+
+               # Start extracting information

                self.report_information_extraction(video_id)
 
                # uploader
                self.report_information_extraction(video_id)
 
                # uploader


@@ -878,7 +887,13 @@ class YoutubeIE(InfoExtractor):
                        if mobj is not None:
                                video_description = mobj.group(1)
 
                        if mobj is not None:
                                video_description = mobj.group(1)
 

+               # token
+               video_token = urllib.unquote_plus(video_info['token'][0])
+

                # Decide which formats to download
                # Decide which formats to download

+               requested_format = self._downloader.params.get('format', None)
+               get_video_template = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=&ps=&asv=&fmt=%%s' % (video_id, video_token)
+

                if 'fmt_url_map' in video_info:
                        url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
                        format_limit = self._downloader.params.get('format_limit', None)
                if 'fmt_url_map' in video_info:
                        url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
                        format_limit = self._downloader.params.get('format_limit', None)


@@ -890,19 +905,17 @@ class YoutubeIE(InfoExtractor):
                        if len(existing_formats) == 0:
                                self._downloader.trouble(u'ERROR: no known formats available for video')
                                return
                        if len(existing_formats) == 0:
                                self._downloader.trouble(u'ERROR: no known formats available for video')
                                return

-                       requested_format = self._downloader.params.get('format', None)

                        if requested_format is None:
                        if requested_format is None:

-                               video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
+                               video_url_list = [(existing_formats[0], get_video_template % existing_formats[0])] # Best quality

                        elif requested_format == '-1':
                        elif requested_format == '-1':

-                               video_url_list = url_map.items() # All formats
+                               video_url_list = [(f, get_video_template % f) for f in existing_formats] # All formats

                        else:
                        else:

-                               if requested_format not in existing_formats:
-                                       self._downloader.trouble(u'ERROR: format not available for video')
-                                       return
-                               video_url_list = [(requested_format, url_map[requested_format])] # Specific format
+                               video_url_list = [(requested_format, get_video_template % requested_format)] # Specific format
+

                elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
                        self.report_rtmp_download()
                        video_url_list = [(None, video_info['conn'][0])]
                elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
                        self.report_rtmp_download()
                        video_url_list = [(None, video_info['conn'][0])]

+

                else:
                        self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info')
                        return
                else:
                        self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info')
                        return


@@ -930,7 +943,7 @@ class YoutubeIE(InfoExtractor):
                                        'player_url':   player_url,
                                })
                        except UnavailableVideoError, err:
                                        'player_url':   player_url,
                                })
                        except UnavailableVideoError, err:

-                               self._downloader.trouble(u'ERROR: unable to download video')
+                               self._downloader.trouble(u'ERROR: unable to download video (format may not be available)')

 
 
 class MetacafeIE(InfoExtractor):
 
 
 class MetacafeIE(InfoExtractor):


@@ -1026,15 +1039,15 @@ class MetacafeIE(InfoExtractor):
                        return
                mediaURL = urllib.unquote(mobj.group(1))
 
                        return
                mediaURL = urllib.unquote(mobj.group(1))
 

-               #mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
-               #if mobj is None:
-               #       self._downloader.trouble(u'ERROR: unable to extract gdaKey')
-               #       return
-               #gdaKey = mobj.group(1)
-               #
-               #video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
-
-               video_url = mediaURL
+               # Extract gdaKey if available
+               mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
+               if mobj is None:
+                       video_url = mediaURL
+                       #self._downloader.trouble(u'ERROR: unable to extract gdaKey')
+                       #return
+               else:
+                       gdaKey = mobj.group(1)
+                       video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)

 
                mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
                if mobj is None:
 
                mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
                if mobj is None:


@@ -1928,6 +1941,11 @@ class YoutubePlaylistIE(InfoExtractor):
                                break
                        pagenum = pagenum + 1
 
                                break
                        pagenum = pagenum + 1
 

+               playliststart = self._downloader.params.get('playliststart', 1)
+               playliststart -= 1 #our arrays are zero-based but the playlist is 1-based
+               if playliststart > 0:
+                       video_ids = video_ids[playliststart:]
+                       

                for id in video_ids:
                        self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
                return
                for id in video_ids:
                        self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
                return


@@ -1983,6 +2001,11 @@ class YoutubeUserIE(InfoExtractor):
                                ids_in_page.append(mobj.group(1))
                video_ids.extend(ids_in_page)
 
                                ids_in_page.append(mobj.group(1))
                video_ids.extend(ids_in_page)
 

+               playliststart = self._downloader.params.get('playliststart', 1)
+               playliststart = playliststart-1 #our arrays are zero-based but the playlist is 1-based
+               if playliststart > 0:
+                       video_ids = video_ids[playliststart:]   
+

                for id in video_ids:
                        self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
                return
                for id in video_ids:
                        self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
                return


@@ -2064,7 +2087,7 @@ if __name__ == '__main__':
                # Parse command line
                parser = optparse.OptionParser(
                        usage='Usage: %prog [options] url...',
                # Parse command line
                parser = optparse.OptionParser(
                        usage='Usage: %prog [options] url...',

-                       version='2010.07.22',
+                       version='2010.08.04',

                        conflict_handler='resolve',
                )
 
                        conflict_handler='resolve',
                )
 


@@ -2080,6 +2103,8 @@ if __name__ == '__main__':
                                dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
                parser.add_option('-R', '--retries',
                                dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
                                dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
                parser.add_option('-R', '--retries',
                                dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)

+               parser.add_option('--playlist-start',
+                               dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)

 
                authentication = optparse.OptionGroup(parser, 'Authentication Options')
                authentication.add_option('-u', '--username',
 
                authentication = optparse.OptionGroup(parser, 'Authentication Options')
                authentication.add_option('-u', '--username',


@@ -2099,6 +2124,8 @@ if __name__ == '__main__':
                                action='store_const', dest='format', help='download all available video formats', const='-1')
                video_format.add_option('--max-quality',
                                action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
                                action='store_const', dest='format', help='download all available video formats', const='-1')
                video_format.add_option('--max-quality',
                                action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')

+               video_format.add_option('-b', '--best-quality',
+                               action='store_true', dest='bestquality', help='download the best video quality (DEPRECATED)')

                parser.add_option_group(video_format)
 
                verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
                parser.add_option_group(video_format)
 
                verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')


@@ -2151,6 +2178,8 @@ if __name__ == '__main__':
                all_urls = batchurls + args
 
                # Conflicting, missing and erroneous options
                all_urls = batchurls + args
 
                # Conflicting, missing and erroneous options

+               if opts.bestquality:
+                       print >>sys.stderr, u'\nWARNING: -b/--best-quality IS DEPRECATED AS IT IS THE DEFAULT BEHAVIOR NOW\n'

                if opts.usenetrc and (opts.username is not None or opts.password is not None):
                        parser.error(u'using .netrc conflicts with giving username/password')
                if opts.password is not None and opts.username is None:
                if opts.usenetrc and (opts.username is not None or opts.password is not None):
                        parser.error(u'using .netrc conflicts with giving username/password')
                if opts.password is not None and opts.username is None:


@@ -2171,6 +2200,11 @@ if __name__ == '__main__':
                                opts.retries = long(opts.retries)
                        except (TypeError, ValueError), err:
                                parser.error(u'invalid retry count specified')
                                opts.retries = long(opts.retries)
                        except (TypeError, ValueError), err:
                                parser.error(u'invalid retry count specified')

+               if opts.playliststart is not None:
+                       try:
+                               opts.playliststart = long(opts.playliststart)
+                       except (TypeError, ValueError), err:
+                               parser.error(u'invalid playlist page specified')

 
                # Information extractors
                youtube_ie = YoutubeIE()
 
                # Information extractors
                youtube_ie = YoutubeIE()


@@ -2212,6 +2246,7 @@ if __name__ == '__main__':
                        'retries': opts.retries,
                        'continuedl': opts.continue_dl,
                        'noprogress': opts.noprogress,
                        'retries': opts.retries,
                        'continuedl': opts.continue_dl,
                        'noprogress': opts.noprogress,

+                       'playliststart': opts.playliststart,

                        })
                fd.add_info_extractor(youtube_search_ie)
                fd.add_info_extractor(youtube_pl_ie)
                        })
                fd.add_info_extractor(youtube_search_ie)
                fd.add_info_extractor(youtube_pl_ie)