Use unquote_plus to decode video title

[youtube-dl] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 472a8e1ccc677318be39d328c945be37b04a8435..c3d9271c2cacef4dc9b1c29aef3185fdf87a8524 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -33,15 +33,15 @@ def preferredencoding():
        Returns the best encoding scheme for the system, based on
        locale.getpreferredencoding() and some further tweaks.
        """
-       try:
-               pref = locale.getpreferredencoding()
-               # Mac OSX systems have this problem sometimes
-               if pref == '':
-                       return 'UTF-8'
-               return pref
-       except:
-               sys.stderr.write('WARNING: problem obtaining preferred encoding. Falling back to UTF-8.\n')
-               return 'UTF-8'
+       def yield_preferredencoding():
+               try:
+                       pref = locale.getpreferredencoding()
+                       u'TEST'.encode(pref)
+               except:
+                       pref = 'UTF-8'
+               while True:
+                       yield pref
+       return yield_preferredencoding().next()
 
 class DownloadError(Exception):
        """Download Error exception.
@@ -221,11 +221,13 @@ class FileDownloader(object):
 
        @staticmethod
        def verify_url(url):
-               """Verify a URL is valid and data could be downloaded."""
+               """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."""
@@ -307,7 +309,7 @@ class FileDownloader(object):
                # Do nothing else if in simulate mode
                if self.params.get('simulate', False):
                        try:
-                               self.verify_url(info_dict['url'])
+                               info_dict['url'] = self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')
                        except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
                                raise UnavailableFormatError
 
@@ -325,7 +327,7 @@ class FileDownloader(object):
                        filename = self.params['outtmpl'] % template_dict
                except (ValueError, KeyError), err:
                        self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
-               if self.params['nooverwrites'] and os.path.exists(filename):
+               if self.params.get('nooverwrites', False) and os.path.exists(filename):
                        self.to_stderr(u'WARNING: file exists: %s; skipping' % filename)
                        return
 
@@ -336,7 +338,7 @@ class FileDownloader(object):
                        return
 
                try:
-                       success = self._do_download(filename, info_dict['url'])
+                       success = self._do_download(filename, info_dict['url'].encode('utf-8'))
                except (OSError, IOError), err:
                        raise UnavailableFormatError
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@@ -400,7 +402,7 @@ class FileDownloader(object):
                        resume_len = os.path.getsize(filename)
                else:
                        resume_len = 0
-               if self.params['continuedl'] and resume_len != 0:
+               if self.params.get('continuedl', False) and resume_len != 0:
                        self.report_resuming_byte(resume_len)
                        request.add_header('Range','bytes=%d-' % resume_len)
 
@@ -583,10 +585,6 @@ class YoutubeIE(InfoExtractor):
                """Report attempt to extract video information."""
                self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
        
-       def report_video_url(self, video_id, video_real_url):
-               """Report extracted video URL."""
-               self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
-       
        def report_unavailable_format(self, video_id, format):
                """Report extracted video URL."""
                self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
@@ -712,7 +710,6 @@ class YoutubeIE(InfoExtractor):
                        video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=detailpage&ps=default&gl=US&hl=en' % (video_id, token)
                        if format_param is not None:
                                video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
-                       self.report_video_url(video_id, video_real_url)
 
                        # uploader
                        mobj = re.search(r'(?m)&author=([^&]+)(?:&|$)', video_info_webpage)
@@ -722,11 +719,11 @@ class YoutubeIE(InfoExtractor):
                        video_uploader = urllib.unquote(mobj.group(1))
 
                        # title
-                       mobj = re.search(r'(?m)&title=([^&]+)(?:&|$)', video_info_webpage)
+                       mobj = re.search(r'(?m)&title=([^&]*)(?:&|$)', video_info_webpage)
                        if mobj is None:
                                self._downloader.trouble(u'ERROR: unable to extract video title')
                                return
-                       video_title = urllib.unquote(mobj.group(1))
+                       video_title = urllib.unquote_plus(mobj.group(1))
                        video_title = video_title.decode('utf-8')
                        video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
                        video_title = video_title.replace(os.sep, u'%')