Imported Upstream version 2010.11.19

[youtubedl] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 466b506b5fc93af86e5c18b9a569a43c9d474dde..24722d292ecadfd4b16e2775ca9a53efc145628a 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -28,7 +28,7 @@ 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:1.9.2.11) Gecko/20101019 Firefox/3.6.11',
+       'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.12) Gecko/20101028 Firefox/3.6.12',

        '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',


@@ -36,6 +36,21 @@ std_headers = {
 
 simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
 
 
 simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
 

+month_name_to_number = {
+       'January':      '01',
+       'February':     '02',
+       'March':        '03',
+       'April':        '04',
+       'May':          '05',
+       'June':         '06',
+       'July':         '07',
+       'August':       '08',
+       'September':    '09',
+       'October':      '10',
+       'November':     '11',
+       'December':     '12',
+}
+

 def preferredencoding():
        """Get preferred encoding.
 
 def preferredencoding():
        """Get preferred encoding.
 


@@ -204,6 +219,7 @@ class FileDownloader(object):
        continuedl:       Try to continue downloads if possible.
        noprogress:       Do not print the progress bar.
        playliststart:    Playlist item to start at.
        continuedl:       Try to continue downloads if possible.
        noprogress:       Do not print the progress bar.
        playliststart:    Playlist item to start at.

+       playlistend:      Playlist item to end at.

        logtostderr:      Log messages to stderr instead of stdout.
        """
 
        logtostderr:      Log messages to stderr instead of stdout.
        """
 


@@ -412,7 +428,7 @@ class FileDownloader(object):
                try:
                        template_dict = dict(info_dict)
                        template_dict['epoch'] = unicode(long(time.time()))
                try:
                        template_dict = dict(info_dict)
                        template_dict['epoch'] = unicode(long(time.time()))

-                       template_dict['ord'] = unicode('%05d' % self._num_downloads)
+                       template_dict['autonumber'] = unicode('%05d' % self._num_downloads)

                        filename = self.params['outtmpl'] % template_dict
                except (ValueError, KeyError), err:
                        self.trouble(u'ERROR: invalid system charset or erroneous output template')
                        filename = self.params['outtmpl'] % template_dict
                except (ValueError, KeyError), err:
                        self.trouble(u'ERROR: invalid system charset or erroneous output template')


@@ -830,7 +846,7 @@ class YoutubeIE(InfoExtractor):
 
                # Get video webpage
                self.report_video_webpage_download(video_id)
 
                # Get video webpage
                self.report_video_webpage_download(video_id)

-               request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id, None, std_headers)
+               request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id, None, std_headers)

                try:
                        video_webpage = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                try:
                        video_webpage = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:


@@ -838,9 +854,9 @@ class YoutubeIE(InfoExtractor):
                        return
 
                # Attempt to extract SWF player URL
                        return
 
                # Attempt to extract SWF player URL

-               mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage)
+               mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)

                if mobj is not None:
                if mobj is not None:

-                       player_url = mobj.group(1)
+                       player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))

                else:
                        player_url = None
 
                else:
                        player_url = None
 


@@ -893,6 +909,23 @@ class YoutubeIE(InfoExtractor):
                else:   # don't panic if we can't find it
                        video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
 
                else:   # don't panic if we can't find it
                        video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
 

+               # upload date
+               upload_date = u'NA'
+               mobj = re.search(r'id="eow-date".*?>(.*?)</span>', video_webpage, re.DOTALL)
+               if mobj is not None:
+                       try:
+                               if ',' in mobj.group(1):
+                                       # Month Day, Year
+                                       m, d, y = mobj.group(1).replace(',', '').split()
+                               else:
+                                       # Day Month Year, we'll suppose
+                                       d, m, y = mobj.group(1).split()
+                               m = month_name_to_number[m]
+                               d = '%02d' % (long(d))
+                               upload_date = '%s%s%s' % (y, m, d)
+                       except:
+                               upload_date = u'NA'
+

                # description
                video_description = 'No description available.'
                if self._downloader.params.get('forcedescription', False):
                # description
                video_description = 'No description available.'
                if self._downloader.params.get('forcedescription', False):


@@ -947,6 +980,7 @@ class YoutubeIE(InfoExtractor):
                                        'id':           video_id.decode('utf-8'),
                                        'url':          video_real_url.decode('utf-8'),
                                        'uploader':     video_uploader.decode('utf-8'),
                                        'id':           video_id.decode('utf-8'),
                                        'url':          video_real_url.decode('utf-8'),
                                        'uploader':     video_uploader.decode('utf-8'),

+                                       'upload_date':  upload_date,

                                        'title':        video_title,
                                        'stitle':       simple_title,
                                        'ext':          video_extension.decode('utf-8'),
                                        'title':        video_title,
                                        'stitle':       simple_title,
                                        'ext':          video_extension.decode('utf-8'),


@@ -1093,6 +1127,7 @@ class MetacafeIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader.decode('utf-8'),
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader.decode('utf-8'),

+                               'upload_date':  u'NA',

                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),


@@ -1181,6 +1216,7 @@ class DailymotionIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader.decode('utf-8'),
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader.decode('utf-8'),

+                               'upload_date':  u'NA',

                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),


@@ -1290,6 +1326,7 @@ class GoogleIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     u'NA',
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     u'NA',

+                               'upload_date':  u'NA',

                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),


@@ -1371,6 +1408,7 @@ class PhotobucketIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,

+                               'upload_date':  u'NA',

                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),


@@ -1525,6 +1563,7 @@ class YahooIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url,
                                'uploader':     video_uploader,
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url,
                                'uploader':     video_uploader,

+                               'upload_date':  u'NA',

                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),


@@ -1627,6 +1666,7 @@ class GenericIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,

+                               'upload_date':  u'NA',

                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),


@@ -1966,11 +2006,10 @@ 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:]
-                       
+               playliststart = self._downloader.params.get('playliststart', 1) - 1
+               playlistend = self._downloader.params.get('playlistend', -1)
+               video_ids = video_ids[playliststart:playlistend]
+

                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


@@ -2026,10 +2065,9 @@ 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:]   
+               playliststart = self._downloader.params.get('playliststart', 1) - 1
+               playlistend = self._downloader.params.get('playlistend', -1)
+               video_ids = video_ids[playliststart:playlistend]

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


@@ -2095,9 +2133,9 @@ if __name__ == '__main__':
                                sys.exit('ERROR: no write permissions on %s' % filename)
 
                        downloader.to_screen('Updating to latest stable version...')
                                sys.exit('ERROR: no write permissions on %s' % filename)
 
                        downloader.to_screen('Updating to latest stable version...')

-                       latest_url = 'http://bitbucket.org/rg3/youtube-dl/raw/tip/LATEST_VERSION'
+                       latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION'

                        latest_version = urllib.urlopen(latest_url).read().strip()
                        latest_version = urllib.urlopen(latest_url).read().strip()

-                       prog_url = 'http://bitbucket.org/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
+                       prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version

                        newcontent = urllib.urlopen(prog_url).read()
                        stream = open(filename, 'w')
                        stream.write(newcontent)
                        newcontent = urllib.urlopen(prog_url).read()
                        stream = open(filename, 'w')
                        stream.write(newcontent)


@@ -2107,7 +2145,7 @@ 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='2010.10.24',
+                       version='2010.11.19',

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


@@ -2125,6 +2163,8 @@ if __name__ == '__main__':
                                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)
                                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)

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

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


@@ -2170,6 +2210,8 @@ if __name__ == '__main__':
                                action='store_true', dest='usetitle', help='use title in file name', default=False)
                filesystem.add_option('-l', '--literal',
                                action='store_true', dest='useliteral', help='use literal title in file name', default=False)
                                action='store_true', dest='usetitle', help='use title in file name', default=False)
                filesystem.add_option('-l', '--literal',
                                action='store_true', dest='useliteral', help='use literal title in file name', default=False)

+               filesystem.add_option('-A', '--auto-number',
+                               action='store_true', dest='autonumber', help='number downloaded files starting from 00000', default=False)

                filesystem.add_option('-o', '--output',
                                dest='outtmpl', metavar='TEMPLATE', help='output filename template')
                filesystem.add_option('-a', '--batch-file',
                filesystem.add_option('-o', '--output',
                                dest='outtmpl', metavar='TEMPLATE', help='output filename template')
                filesystem.add_option('-a', '--batch-file',


@@ -2211,7 +2253,7 @@ if __name__ == '__main__':
                                        batchfd = open(opts.batchfile, 'r')
                                batchurls = batchfd.readlines()
                                batchurls = [x.strip() for x in batchurls]
                                        batchfd = open(opts.batchfile, 'r')
                                batchurls = batchfd.readlines()
                                batchurls = [x.strip() for x in batchurls]

-                               batchurls = [x for x in batchurls if len(x) > 0]
+                               batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]

                        except IOError:
                                sys.exit(u'ERROR: batch file could not be read')
                all_urls = batchurls + args
                        except IOError:
                                sys.exit(u'ERROR: batch file could not be read')
                all_urls = batchurls + args


@@ -2223,8 +2265,8 @@ if __name__ == '__main__':
                        parser.error(u'using .netrc conflicts with giving username/password')
                if opts.password is not None and opts.username is None:
                        parser.error(u'account username missing')
                        parser.error(u'using .netrc conflicts with giving username/password')
                if opts.password is not None and opts.username is None:
                        parser.error(u'account username missing')

-               if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
-                       parser.error(u'using output template conflicts with using title or literal title')
+               if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber):
+                       parser.error(u'using output template conflicts with using title, literal title or auto number')

                if opts.usetitle and opts.useliteral:
                        parser.error(u'using title conflicts with using literal title')
                if opts.username is not None and opts.password is None:
                if opts.usetitle and opts.useliteral:
                        parser.error(u'using title conflicts with using literal title')
                if opts.username is not None and opts.password is None:


@@ -2239,11 +2281,18 @@ 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')
+               try:
+                       opts.playliststart = long(opts.playliststart)
+                       if opts.playliststart <= 0:
+                               raise ValueError
+               except (TypeError, ValueError), err:
+                       parser.error(u'invalid playlist start number specified')
+               try:
+                       opts.playlistend = long(opts.playlistend)
+                       if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
+                               raise ValueError
+               except (TypeError, ValueError), err:
+                       parser.error(u'invalid playlist end number specified')

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


@@ -2276,8 +2325,11 @@ if __name__ == '__main__':
                                or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
                                or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
                                or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
                                or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
                                or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
                                or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')

+                               or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s')
+                               or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')

                                or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
                                or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
                                or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
                                or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')

+                               or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')

                                or u'%(id)s.%(ext)s'),
                        'ignoreerrors': opts.ignoreerrors,
                        'ratelimit': opts.ratelimit,
                                or u'%(id)s.%(ext)s'),
                        'ignoreerrors': opts.ignoreerrors,
                        'ratelimit': opts.ratelimit,


@@ -2286,6 +2338,7 @@ if __name__ == '__main__':
                        'continuedl': opts.continue_dl,
                        'noprogress': opts.noprogress,
                        'playliststart': opts.playliststart,
                        'continuedl': opts.continue_dl,
                        'noprogress': opts.noprogress,
                        'playliststart': opts.playliststart,

+                       'playlistend': opts.playlistend,

                        'logtostderr': opts.outtmpl == '-',
                        })
                fd.add_info_extractor(youtube_search_ie)
                        'logtostderr': opts.outtmpl == '-',
                        })
                fd.add_info_extractor(youtube_search_ie)