]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube-dl
Imported Upstream version 2010.11.19
[youtubedl] / youtube-dl
index d5469495404ca1ca9640a0a619628c511edf4f59..24722d292ecadfd4b16e2775ca9a53efc145628a 100755 (executable)
@@ -4,6 +4,7 @@
 # Author: Danny Colligan
 # Author: Benjamin Johnson
 # License: Public domain code
+import cookielib
 import htmlentitydefs
 import httplib
 import locale
@@ -27,7 +28,7 @@ except ImportError:
        from cgi import parse_qs
 
 std_headers = {
-       'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.8) Gecko/20100723 Firefox/3.6.8',
+       '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',
@@ -35,6 +36,21 @@ std_headers = {
 
 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.
 
@@ -94,6 +110,9 @@ def sanitize_open(filename, open_mode):
        """
        try:
                if filename == u'-':
+                       if sys.platform == 'win32':
+                               import msvcrt
+                               msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
                        return (sys.stdout, filename)
                stream = open(filename, open_mode)
                return (stream, filename)
@@ -181,22 +200,27 @@ class FileDownloader(object):
 
        Available options:
 
-       username:       Username for authentication purposes.
-       password:       Password for authentication purposes.
-       usenetrc:       Use netrc for authentication instead.
-       quiet:          Do not print messages to stdout.
-       forceurl:       Force printing final URL.
-       forcetitle:     Force printing title.
-       simulate:       Do not download the video files.
-       format:         Video format code.
-       format_limit:   Highest quality format to try.
-       outtmpl:        Template for output names.
-       ignoreerrors:   Do not stop on download errors.
-       ratelimit:      Download speed limit, in bytes/sec.
-       nooverwrites:   Prevent overwriting files.
-       retries:        Number of times to retry for HTTP error 503
-       continuedl:     Try to continue downloads if possible.
-       noprogress:     Do not print the progress bar.
+       username:         Username for authentication purposes.
+       password:         Password for authentication purposes.
+       usenetrc:         Use netrc for authentication instead.
+       quiet:            Do not print messages to stdout.
+       forceurl:         Force printing final URL.
+       forcetitle:       Force printing title.
+       forcethumbnail:   Force printing thumbnail URL.
+       forcedescription: Force printing description.
+       simulate:         Do not download the video files.
+       format:           Video format code.
+       format_limit:     Highest quality format to try.
+       outtmpl:          Template for output names.
+       ignoreerrors:     Do not stop on download errors.
+       ratelimit:        Download speed limit, in bytes/sec.
+       nooverwrites:     Prevent overwriting files.
+       retries:          Number of times to retry for HTTP error 5xx
+       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.
        """
 
        params = None
@@ -204,6 +228,7 @@ class FileDownloader(object):
        _pps = []
        _download_retcode = None
        _num_downloads = None
+       _screen_file = None
 
        def __init__(self, params):
                """Create a FileDownloader object with the given options."""
@@ -211,6 +236,7 @@ class FileDownloader(object):
                self._pps = []
                self._download_retcode = 0
                self._num_downloads = 0
+               self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
                self.params = params
        
        @staticmethod
@@ -297,12 +323,13 @@ class FileDownloader(object):
                self._pps.append(pp)
                pp.set_downloader(self)
        
-       def to_stdout(self, message, skip_eol=False, ignore_encoding_errors=False):
+       def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False):
                """Print message to stdout if not in quiet mode."""
                try:
                        if not self.params.get('quiet', False):
-                               print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
-                       sys.stdout.flush()
+                               terminator = [u'\n', u''][skip_eol]
+                               print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()),
+                       self._screen_file.flush()
                except (UnicodeEncodeError), err:
                        if not ignore_encoding_errors:
                                raise
@@ -343,40 +370,40 @@ class FileDownloader(object):
 
        def report_destination(self, filename):
                """Report destination filename."""
-               self.to_stdout(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
+               self.to_screen(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."""
                if self.params.get('noprogress', False):
                        return
-               self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
+               self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
                                (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
 
        def report_resuming_byte(self, resume_len):
-               """Report attemtp to resume at given byte."""
-               self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
+               """Report attempt to resume at given byte."""
+               self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
        
        def report_retry(self, count, retries):
-               """Report retry in case of HTTP error 503"""
-               self.to_stdout(u'[download] Got HTTP error 503. Retrying (attempt %d of %d)...' % (count, retries))
+               """Report retry in case of HTTP error 5xx"""
+               self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
        
        def report_file_already_downloaded(self, file_name):
                """Report file has already been fully downloaded."""
                try:
-                       self.to_stdout(u'[download] %s has already been downloaded' % file_name)
+                       self.to_screen(u'[download] %s has already been downloaded' % file_name)
                except (UnicodeEncodeError), err:
-                       self.to_stdout(u'[download] The file has already been downloaded')
+                       self.to_screen(u'[download] The file has already been downloaded')
        
        def report_unable_to_resume(self):
                """Report it was impossible to resume download."""
-               self.to_stdout(u'[download] Unable to resume')
+               self.to_screen(u'[download] Unable to resume')
        
        def report_finish(self):
                """Report download finished."""
                if self.params.get('noprogress', False):
-                       self.to_stdout(u'[download] Download completed')
+                       self.to_screen(u'[download] Download completed')
                else:
-                       self.to_stdout(u'')
+                       self.to_screen(u'')
        
        def increment_downloads(self):
                """Increment the ordinal that assigns a number to each file."""
@@ -401,18 +428,19 @@ 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('ERROR: invalid output template or system charset: %s' % str(err))
+                       self.trouble(u'ERROR: invalid system charset or erroneous output template')
+                       return
                if self.params.get('nooverwrites', False) and os.path.exists(filename):
-                       self.to_stderr(u'WARNING: file exists: %s; skipping' % filename)
+                       self.to_stderr(u'WARNING: file exists and will be skipped')
                        return
 
                try:
                        self.pmkdir(filename)
                except (OSError, IOError), err:
-                       self.trouble('ERROR: unable to create directories: %s' % str(err))
+                       self.trouble(u'ERROR: unable to create directories: %s' % str(err))
                        return
 
                try:
@@ -420,17 +448,17 @@ class FileDownloader(object):
                except (OSError, IOError), err:
                        raise UnavailableVideoError
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-                       self.trouble('ERROR: unable to download video data: %s' % str(err))
+                       self.trouble(u'ERROR: unable to download video data: %s' % str(err))
                        return
                except (ContentTooShortError, ), err:
-                       self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
+                       self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
                        return
 
                if success:
                        try:
                                self.post_process(filename, info_dict)
                        except (PostProcessingError), err:
-                               self.trouble('ERROR: postprocessing: %s' % str(err))
+                               self.trouble(u'ERROR: postprocessing: %s' % str(err))
                                return
 
        def download(self, url_list):
@@ -455,7 +483,7 @@ class FileDownloader(object):
                                break
 
                        if not suitable_found:
-                               self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
+                               self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)
 
                return self._download_retcode
 
@@ -485,17 +513,17 @@ class FileDownloader(object):
                retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
                while retval == 2 or retval == 1:
                        prevsize = os.path.getsize(filename)
-                       self.to_stdout(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
+                       self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
                        time.sleep(5.0) # This seems to be needed
                        retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
                        cursize = os.path.getsize(filename)
                        if prevsize == cursize and retval == 1:
                                break
                if retval == 0:
-                       self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
+                       self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
                        return True
                else:
-                       self.trouble('\nERROR: rtmpdump exited with code %d' % retval)
+                       self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
                        return False
 
        def _do_download(self, filename, url, player_url):
@@ -528,7 +556,7 @@ class FileDownloader(object):
                                data = urllib2.urlopen(request)
                                break
                        except (urllib2.HTTPError, ), err:
-                               if err.code != 503 and err.code != 416:
+                               if (err.code < 500 or err.code >= 600) and err.code != 416:
                                        # Unexpected HTTP error
                                        raise
                                elif err.code == 416:
@@ -538,7 +566,7 @@ class FileDownloader(object):
                                                data = urllib2.urlopen(basic_request)
                                                content_length = data.info()['Content-Length']
                                        except (urllib2.HTTPError, ), err:
-                                               if err.code != 503:
+                                               if err.code < 500 or err.code >= 600:
                                                        raise
                                        else:
                                                # Examine the reported length
@@ -588,12 +616,13 @@ class FileDownloader(object):
                                        (stream, filename) = sanitize_open(filename, open_mode)
                                        self.report_destination(filename)
                                except (OSError, IOError), err:
-                                       self.trouble('ERROR: unable to open for writing: %s' % str(err))
+                                       self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
                                        return False
                        try:
                                stream.write(data_block)
                        except (IOError, OSError), err:
-                               self.trouble('\nERROR: unable to write data: %s' % str(err))
+                               self.trouble(u'\nERROR: unable to write data: %s' % str(err))
+                               return False
                        block_size = self.best_block_size(after - before, data_block_len)
 
                        # Progress message
@@ -684,9 +713,9 @@ class InfoExtractor(object):
 class YoutubeIE(InfoExtractor):
        """Information extractor for youtube.com."""
 
-       _VALID_URL = r'^((?:http://)?(?:youtu\.be/|(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?[\?#](?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
+       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
        _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
-       _LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
+       _LOGIN_URL = 'https://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'
        # Listed in order of quality
@@ -708,35 +737,35 @@ class YoutubeIE(InfoExtractor):
 
        def report_lang(self):
                """Report attempt to set language."""
-               self._downloader.to_stdout(u'[youtube] Setting language')
+               self._downloader.to_screen(u'[youtube] Setting language')
 
        def report_login(self):
                """Report attempt to log in."""
-               self._downloader.to_stdout(u'[youtube] Logging in')
+               self._downloader.to_screen(u'[youtube] Logging in')
        
        def report_age_confirmation(self):
                """Report attempt to confirm age."""
-               self._downloader.to_stdout(u'[youtube] Confirming age')
+               self._downloader.to_screen(u'[youtube] Confirming age')
        
        def report_video_webpage_download(self, video_id):
                """Report attempt to download video webpage."""
-               self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
+               self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
        
        def report_video_info_webpage_download(self, video_id):
                """Report attempt to download video info webpage."""
-               self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id)
+               self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
        
        def report_information_extraction(self, video_id):
                """Report attempt to extract video information."""
-               self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
+               self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
        
        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))
+               self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
        
        def report_rtmp_download(self):
                """Indicate the download will use the RTMP protocol."""
-               self._downloader.to_stdout(u'[youtube] RTMP download detected')
+               self._downloader.to_screen(u'[youtube] RTMP download detected')
        
        def _real_initialize(self):
                if self._downloader is None:
@@ -817,7 +846,7 @@ 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&amp;has_verified=1' % video_id, None, std_headers)
                try:
                        video_webpage = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@@ -825,9 +854,9 @@ 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
 
@@ -847,7 +876,7 @@ class YoutubeIE(InfoExtractor):
                                return
                if 'token' not in video_info:
                        if 'reason' in video_info:
-                               self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0])
+                               self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8'))
                        else:
                                self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
                        return
@@ -880,6 +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])
 
+               # 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):
@@ -934,6 +980,7 @@ class YoutubeIE(InfoExtractor):
                                        'id':           video_id.decode('utf-8'),
                                        'url':          video_real_url.decode('utf-8'),
                                        'uploader':     video_uploader.decode('utf-8'),
+                                       'upload_date':  upload_date,
                                        'title':        video_title,
                                        'stitle':       simple_title,
                                        'ext':          video_extension.decode('utf-8'),
@@ -964,19 +1011,19 @@ class MetacafeIE(InfoExtractor):
 
        def report_disclaimer(self):
                """Report disclaimer retrieval."""
-               self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer')
+               self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
 
        def report_age_confirmation(self):
                """Report attempt to confirm age."""
-               self._downloader.to_stdout(u'[metacafe] Confirming age')
+               self._downloader.to_screen(u'[metacafe] Confirming age')
        
        def report_download_webpage(self, video_id):
                """Report webpage download."""
-               self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
+               self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
        
        def report_extraction(self, video_id):
                """Report information extraction."""
-               self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
+               self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
 
        def _real_initialize(self):
                # Retrieve disclaimer
@@ -1020,7 +1067,6 @@ class MetacafeIE(InfoExtractor):
                self._downloader.increment_downloads()
 
                simple_title = mobj.group(2).decode('utf-8')
-               video_extension = 'flv'
 
                # Retrieve video webpage to extract further information
                request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
@@ -1034,20 +1080,33 @@ class MetacafeIE(InfoExtractor):
                # Extract URL, uploader and title from webpage
                self.report_extraction(video_id)
                mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
-               if mobj is None:
-                       self._downloader.trouble(u'ERROR: unable to extract media URL')
-                       return
-               mediaURL = urllib.unquote(mobj.group(1))
-
-               # Extract gdaKey if available
-               mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
-               if mobj is None:
-                       video_url = mediaURL
-                       #self._downloader.trouble(u'ERROR: unable to extract gdaKey')
-                       #return
+               if mobj is not None:
+                       mediaURL = urllib.unquote(mobj.group(1))
+                       video_extension = mediaURL[-3:]
+                       
+                       # Extract gdaKey if available
+                       mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
+                       if mobj is None:
+                               video_url = mediaURL
+                       else:
+                               gdaKey = mobj.group(1)
+                               video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
                else:
-                       gdaKey = mobj.group(1)
-                       video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+                       mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
+                       if mobj is None:
+                               self._downloader.trouble(u'ERROR: unable to extract media URL')
+                               return
+                       vardict = parse_qs(mobj.group(1))
+                       if 'mediaData' not in vardict:
+                               self._downloader.trouble(u'ERROR: unable to extract media URL')
+                               return
+                       mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
+                       if mobj is None:
+                               self._downloader.trouble(u'ERROR: unable to extract media URL')
+                               return
+                       mediaURL = mobj.group(1).replace('\\/', '/')
+                       video_extension = mediaURL[-3:]
+                       video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
 
                mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
                if mobj is None:
@@ -1068,6 +1127,7 @@ class MetacafeIE(InfoExtractor):
                                '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'),
@@ -1092,11 +1152,11 @@ class DailymotionIE(InfoExtractor):
 
        def report_download_webpage(self, video_id):
                """Report webpage download."""
-               self._downloader.to_stdout(u'[dailymotion] %s: Downloading webpage' % video_id)
+               self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
        
        def report_extraction(self, video_id):
                """Report information extraction."""
-               self._downloader.to_stdout(u'[dailymotion] %s: Extracting information' % video_id)
+               self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
 
        def _real_initialize(self):
                return
@@ -1144,7 +1204,7 @@ class DailymotionIE(InfoExtractor):
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
 
-               mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a></div>', webpage)
+               mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a>', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
                        return
@@ -1156,6 +1216,7 @@ class DailymotionIE(InfoExtractor):
                                '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'),
@@ -1179,11 +1240,11 @@ class GoogleIE(InfoExtractor):
 
        def report_download_webpage(self, video_id):
                """Report webpage download."""
-               self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id)
+               self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
 
        def report_extraction(self, video_id):
                """Report information extraction."""
-               self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id)
+               self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
 
        def _real_initialize(self):
                return
@@ -1265,6 +1326,7 @@ class GoogleIE(InfoExtractor):
                                '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'),
@@ -1289,11 +1351,11 @@ class PhotobucketIE(InfoExtractor):
 
        def report_download_webpage(self, video_id):
                """Report webpage download."""
-               self._downloader.to_stdout(u'[photobucket] %s: Downloading webpage' % video_id)
+               self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
 
        def report_extraction(self, video_id):
                """Report information extraction."""
-               self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id)
+               self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
 
        def _real_initialize(self):
                return
@@ -1346,6 +1408,7 @@ class PhotobucketIE(InfoExtractor):
                                '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'),
@@ -1373,11 +1436,11 @@ class YahooIE(InfoExtractor):
 
        def report_download_webpage(self, video_id):
                """Report webpage download."""
-               self._downloader.to_stdout(u'[video.yahoo] %s: Downloading webpage' % video_id)
+               self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
 
        def report_extraction(self, video_id):
                """Report information extraction."""
-               self._downloader.to_stdout(u'[video.yahoo] %s: Extracting information' % video_id)
+               self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
 
        def _real_initialize(self):
                return
@@ -1500,6 +1563,7 @@ class YahooIE(InfoExtractor):
                                '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'),
@@ -1525,12 +1589,12 @@ class GenericIE(InfoExtractor):
 
        def report_download_webpage(self, video_id):
                """Report webpage download."""
-               self._downloader.to_stdout(u'WARNING: Falling back on generic information extractor.')
-               self._downloader.to_stdout(u'[generic] %s: Downloading webpage' % video_id)
+               self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
+               self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
 
        def report_extraction(self, video_id):
                """Report information extraction."""
-               self._downloader.to_stdout(u'[generic] %s: Extracting information' % video_id)
+               self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
 
        def _real_initialize(self):
                return
@@ -1602,6 +1666,7 @@ class GenericIE(InfoExtractor):
                                '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'),
@@ -1632,7 +1697,7 @@ class YoutubeSearchIE(InfoExtractor):
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())
-               self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+               self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
 
        def _real_initialize(self):
                self._youtube_ie.initialize()
@@ -1723,7 +1788,7 @@ class GoogleSearchIE(InfoExtractor):
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())
-               self._downloader.to_stdout(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
+               self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
 
        def _real_initialize(self):
                self._google_ie.initialize()
@@ -1814,7 +1879,7 @@ class YahooSearchIE(InfoExtractor):
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())
-               self._downloader.to_stdout(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
+               self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
 
        def _real_initialize(self):
                self._yahoo_ie.initialize()
@@ -1904,7 +1969,7 @@ class YoutubePlaylistIE(InfoExtractor):
 
        def report_download_page(self, playlist_id, pagenum):
                """Report attempt to download playlist page with given number."""
-               self._downloader.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+               self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
 
        def _real_initialize(self):
                self._youtube_ie.initialize()
@@ -1941,11 +2006,10 @@ class YoutubePlaylistIE(InfoExtractor):
                                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
@@ -1968,7 +2032,7 @@ class YoutubeUserIE(InfoExtractor):
 
        def report_download_page(self, username):
                """Report attempt to download user page."""
-               self._downloader.to_stdout(u'[youtube] user %s: Downloading page ' % (username))
+               self._downloader.to_screen(u'[youtube] user %s: Downloading page ' % (username))
 
        def _real_initialize(self):
                self._youtube_ie.initialize()
@@ -2001,10 +2065,9 @@ class YoutubeUserIE(InfoExtractor):
                                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)
@@ -2069,25 +2132,20 @@ if __name__ == '__main__':
                        if not os.access (filename, os.W_OK):
                                sys.exit('ERROR: no write permissions on %s' % filename)
 
-                       downloader.to_stdout('Updating to latest stable version...')
-                       latest_url = 'http://bitbucket.org/rg3/youtube-dl/raw/tip/LATEST_VERSION'
+                       downloader.to_screen('Updating to latest stable version...')
+                       latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION'
                        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)
                        stream.close()
-                       downloader.to_stdout('Updated to version %s' % latest_version)
-
-               # General configuration
-               urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
-               urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
-               socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+                       downloader.to_screen('Updated to version %s' % latest_version)
 
                # Parse command line
                parser = optparse.OptionParser(
                        usage='Usage: %prog [options] url...',
-                       version='2010.08.04',
+                       version='2010.11.19',
                        conflict_handler='resolve',
                )
 
@@ -2105,6 +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)
+               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',
@@ -2150,6 +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)
+               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',
@@ -2158,10 +2220,29 @@ if __name__ == '__main__':
                                action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
                filesystem.add_option('-c', '--continue',
                                action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
+               filesystem.add_option('--cookies',
+                               dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
                parser.add_option_group(filesystem)
 
                (opts, args) = parser.parse_args()
 
+               # Open appropriate CookieJar
+               if opts.cookiefile is None:
+                       jar = cookielib.CookieJar()
+               else:
+                       try:
+                               jar = cookielib.MozillaCookieJar(opts.cookiefile)
+                               if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK):
+                                       jar.load()
+                       except (IOError, OSError), err:
+                               sys.exit(u'ERROR: unable to open cookie file')
+
+               # General configuration
+               cookie_processor = urllib2.HTTPCookieProcessor(jar)
+               urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
+               urllib2.install_opener(urllib2.build_opener(cookie_processor))
+               socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+
                # Batch file verification
                batchurls = []
                if opts.batchfile is not None:
@@ -2172,7 +2253,7 @@ if __name__ == '__main__':
                                        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
@@ -2184,8 +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')
-               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:
@@ -2200,11 +2281,18 @@ if __name__ == '__main__':
                                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()
@@ -2237,8 +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.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,
@@ -2247,6 +2338,8 @@ if __name__ == '__main__':
                        'continuedl': opts.continue_dl,
                        'noprogress': opts.noprogress,
                        'playliststart': opts.playliststart,
+                       'playlistend': opts.playlistend,
+                       'logtostderr': opts.outtmpl == '-',
                        })
                fd.add_info_extractor(youtube_search_ie)
                fd.add_info_extractor(youtube_pl_ie)
@@ -2275,6 +2368,14 @@ if __name__ == '__main__':
                        else:
                                sys.exit()
                retcode = fd.download(all_urls)
+
+               # Dump cookie jar if requested
+               if opts.cookiefile is not None:
+                       try:
+                               jar.save()
+                       except (IOError, OSError), err:
+                               sys.exit(u'ERROR: unable to save cookie jar')
+
                sys.exit(retcode)
 
        except DownloadError: