Restore file permissions

[youtube-dl.git] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 24cc454a8604d8b8d83fdcf9809b4995890b08fc..e164d5c8caa5a287eadcf02d1cc6fdbcc55dca80 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -5,6 +5,7 @@
 # Author: Benjamin Johnson
 # License: Public domain code
 import cookielib
+import datetime
 import htmlentitydefs
 import httplib
 import locale
@@ -413,7 +414,7 @@ class FileDownloader(object):
                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')
@@ -831,7 +832,7 @@ class YoutubeIE(InfoExtractor):
 
                # 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:
@@ -839,9 +840,9 @@ class YoutubeIE(InfoExtractor):
                        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:
-                       player_url = mobj.group(1)
+                       player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
                else:
                        player_url = None
 
@@ -894,6 +895,18 @@ class YoutubeIE(InfoExtractor):
                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:
+                       upload_date = mobj.group(1).split()
+                       format_expressions = ['%d %B %Y', '%B %d, %Y']
+                       for expression in format_expressions:
+                               try:
+                                       upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
+                               except:
+                                       pass
+
                # description
                video_description = 'No description available.'
                if self._downloader.params.get('forcedescription', False):
@@ -948,6 +961,7 @@ class YoutubeIE(InfoExtractor):
                                        'id':           video_id.decode('utf-8'),
                                        'url':          video_real_url.decode('utf-8'),
                                        'uploader':     video_uploader.decode('utf-8'),
+                                       'uploaddate':   upload_date,
                                        'title':        video_title,
                                        'stitle':       simple_title,
                                        'ext':          video_extension.decode('utf-8'),
@@ -1094,6 +1108,7 @@ class MetacafeIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader.decode('utf-8'),
+                               'uploaddate':   u'NA',
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
@@ -1182,6 +1197,7 @@ class DailymotionIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader.decode('utf-8'),
+                               'uploaddate':   u'NA',
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
@@ -1291,6 +1307,7 @@ class GoogleIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     u'NA',
+                               'uploaddate':   u'NA',
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
@@ -1372,6 +1389,7 @@ class PhotobucketIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,
+                               'uploaddate':   u'NA',
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
@@ -1526,6 +1544,7 @@ class YahooIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url,
                                'uploader':     video_uploader,
+                               'uploaddate':   u'NA',
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
@@ -1628,6 +1647,7 @@ class GenericIE(InfoExtractor):
                                'id':           video_id.decode('utf-8'),
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,
+                               'uploaddate':   u'NA',
                                'title':        video_title,
                                'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
@@ -2171,6 +2191,8 @@ 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)
+               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',
@@ -2224,8 +2246,8 @@ 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')
-               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:
@@ -2284,8 +2306,11 @@ 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.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.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
                                or u'%(id)s.%(ext)s'),
                        'ignoreerrors': opts.ignoreerrors,
                        'ratelimit': opts.ratelimit,