Give preference to format 34 before format 5 in quality list

[youtube-dl] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 47c64658631ca9581ff62f344aca60595c398e49..10dd7c7916c990815c4c388211e1c17d709b1dce 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -300,11 +300,15 @@ class FileDownloader(object):
                self._pps.append(pp)
                pp.set_downloader(self)
        
-       def to_stdout(self, message, skip_eol=False):
+       def to_stdout(self, message, skip_eol=False, ignore_encoding_errors=False):
                """Print message to stdout if not in quiet mode."""
-               if not self.params.get('quiet', False):
-                       print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
+               try:
+                       if not self.params.get('quiet', False):
+                               print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
                        sys.stdout.flush()
+               except (UnicodeEncodeError), err:
+                       if not ignore_encoding_errors:
+                               raise
        
        def to_stderr(self, message):
                """Print message to stderr."""
@@ -342,7 +346,7 @@ class FileDownloader(object):
 
        def report_destination(self, filename):
                """Report destination filename."""
-               self.to_stdout(u'[download] Destination: %s' % filename)
+               self.to_stdout(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
        
        def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
                """Report download progress."""
@@ -355,7 +359,10 @@ class FileDownloader(object):
        
        def report_file_already_downloaded(self, file_name):
                """Report file has already been fully downloaded."""
-               self.to_stdout(u'[download] %s has already been downloaded' % file_name)
+               try:
+                       self.to_stdout(u'[download] %s has already been downloaded' % file_name)
+               except (UnicodeEncodeError), err:
+                       self.to_stdout(u'[download] The file has already been downloaded')
        
        def report_unable_to_resume(self):
                """Report it was impossible to resume download."""
@@ -629,7 +636,7 @@ class YoutubeIE(InfoExtractor):
        _LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
        _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
        _NETRC_MACHINE = 'youtube'
-       _available_formats = ['37', '22', '35', '18', '5', '17', '13', None] # listed in order of priority for -b flag
+       _available_formats = ['37', '22', '35', '18', '34', '5', '17', '13', None] # listed in order of priority for -b flag
        _video_extensions = {
                '13': '3gp',
                '17': 'mp4',
@@ -1034,6 +1041,7 @@ class GoogleIE(InfoExtractor):
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
+               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
 
                # Google Video doesn't show uploader nicknames?
                video_uploader = 'NA'
@@ -1045,7 +1053,7 @@ class GoogleIE(InfoExtractor):
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader.decode('utf-8'),
                                'title':        video_title,
-                               'stitle':       video_title,
+                               'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                        })
                except UnavailableFormatError:
@@ -1111,6 +1119,7 @@ class PhotobucketIE(InfoExtractor):
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
+               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
 
                video_uploader = mobj.group(2).decode('utf-8')
 
@@ -1121,7 +1130,7 @@ class PhotobucketIE(InfoExtractor):
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,
                                'title':        video_title,
-                               'stitle':       video_title,
+                               'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                        })
                except UnavailableFormatError:
@@ -1199,6 +1208,7 @@ class GenericIE(InfoExtractor):
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
+               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
 
                # video uploader is domain name
                mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
@@ -1214,7 +1224,7 @@ class GenericIE(InfoExtractor):
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,
                                'title':        video_title,
-                               'stitle':       video_title,
+                               'stitle':       simple_title,
                                'ext':          video_extension.decode('utf-8'),
                        })
                except UnavailableFormatError:
@@ -1578,10 +1588,6 @@ if __name__ == '__main__':
                                sys.exit(u'ERROR: batch file could not be read')
                all_urls = batchurls + args
 
-               # Make sure all URLs are in our preferred encoding
-               for i in range(0, len(all_urls)):
-                       all_urls[i] = unicode(all_urls[i], preferredencoding())
-
                # Conflicting, missing and erroneous options
                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')