Imported Upstream version 2010.03.13

[youtubedl] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 47c64658631ca9581ff62f344aca60595c398e49..4530c5da2132340a9ca6d415c65fc004e217ecd7 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -192,6 +192,7 @@ class FileDownloader(object):
        ratelimit:      Download speed limit, in bytes/sec.
        nooverwrites:   Prevent overwriting files.
        continuedl:     Try to continue downloads if possible.
        ratelimit:      Download speed limit, in bytes/sec.
        nooverwrites:   Prevent overwriting files.
        continuedl:     Try to continue downloads if possible.

+       noprogress:     Do not print the progress bar.

        """
 
        params = None
        """
 
        params = None


@@ -300,11 +301,15 @@ class FileDownloader(object):
                self._pps.append(pp)
                pp.set_downloader(self)
        
                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."""
                """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()
                        sys.stdout.flush()

+               except (UnicodeEncodeError), err:
+                       if not ignore_encoding_errors:
+                               raise

        
        def to_stderr(self, message):
                """Print message to stderr."""
        
        def to_stderr(self, message):
                """Print message to stderr."""


@@ -342,10 +347,12 @@ class FileDownloader(object):
 
        def report_destination(self, filename):
                """Report destination filename."""
 
        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."""
        
        def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
                """Report download progress."""

+               if self.params.get('noprogress', False):
+                       return

                self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
                                (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
 
                self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
                                (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
 


@@ -355,7 +362,10 @@ class FileDownloader(object):
        
        def report_file_already_downloaded(self, file_name):
                """Report file has already been fully downloaded."""
        
        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."""
        
        def report_unable_to_resume(self):
                """Report it was impossible to resume download."""


@@ -363,7 +373,10 @@ class FileDownloader(object):
        
        def report_finish(self):
                """Report download finished."""
        
        def report_finish(self):
                """Report download finished."""

-               self.to_stdout(u'')
+               if self.params.get('noprogress', False):
+                       self.to_stdout(u'[download] Download completed')
+               else:
+                       self.to_stdout(u'')

 
        def process_info(self, info_dict):
                """Process a single dictionary returned by an InfoExtractor."""
 
        def process_info(self, info_dict):
                """Process a single dictionary returned by an InfoExtractor."""


@@ -372,7 +385,7 @@ class FileDownloader(object):
                        # Verify URL if it's an HTTP one
                        if info_dict['url'].startswith('http'):
                                try:
                        # Verify URL if it's an HTTP one
                        if info_dict['url'].startswith('http'):
                                try:

-                                       info_dict['url'] = self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')
+                                       self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')

                                except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
                                        raise UnavailableFormatError
 
                                except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
                                        raise UnavailableFormatError
 


@@ -629,7 +642,7 @@ 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'
        _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',
        _video_extensions = {
                '13': '3gp',
                '17': 'mp4',


@@ -1034,6 +1047,7 @@ class GoogleIE(InfoExtractor):
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
                        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'
 
                # Google Video doesn't show uploader nicknames?
                video_uploader = 'NA'


@@ -1045,7 +1059,7 @@ class GoogleIE(InfoExtractor):
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader.decode('utf-8'),
                                'title':        video_title,
                                '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:
                                'ext':          video_extension.decode('utf-8'),
                        })
                except UnavailableFormatError:


@@ -1111,6 +1125,7 @@ class PhotobucketIE(InfoExtractor):
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
                        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')
 
 
                video_uploader = mobj.group(2).decode('utf-8')
 


@@ -1121,7 +1136,7 @@ class PhotobucketIE(InfoExtractor):
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,
                                'title':        video_title,
                                '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:
                                'ext':          video_extension.decode('utf-8'),
                        })
                except UnavailableFormatError:


@@ -1199,6 +1214,7 @@ class GenericIE(InfoExtractor):
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
                        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)
 
                # video uploader is domain name
                mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)


@@ -1214,7 +1230,7 @@ class GenericIE(InfoExtractor):
                                'url':          video_url.decode('utf-8'),
                                'uploader':     video_uploader,
                                'title':        video_title,
                                '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:
                                'ext':          video_extension.decode('utf-8'),
                        })
                except UnavailableFormatError:


@@ -1504,7 +1520,7 @@ 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='2010.02.13',
+                       version='2010.03.07',

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


@@ -1548,6 +1564,8 @@ if __name__ == '__main__':
                                action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
                verbosity.add_option('-e', '--get-title',
                                action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
                                action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
                verbosity.add_option('-e', '--get-title',
                                action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)

+               verbosity.add_option('--no-progress',
+                               action='store_true', dest='noprogress', help='do not print progress bar', default=False)

                parser.add_option_group(verbosity)
 
                filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
                parser.add_option_group(verbosity)
 
                filesystem = optparse.OptionGroup(parser, 'Filesystem Options')


@@ -1578,10 +1596,6 @@ if __name__ == '__main__':
                                sys.exit(u'ERROR: batch file could not be read')
                all_urls = batchurls + args
 
                                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')
                # 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')


@@ -1627,6 +1641,7 @@ if __name__ == '__main__':
                        'ratelimit': opts.ratelimit,
                        'nooverwrites': opts.nooverwrites,
                        'continuedl': opts.continue_dl,
                        'ratelimit': opts.ratelimit,
                        'nooverwrites': opts.nooverwrites,
                        'continuedl': opts.continue_dl,

+                       'noprogress': opts.noprogress,

                        })
                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)