Imported Upstream version 2010.10.03

[youtubedl] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index d5469495404ca1ca9640a0a619628c511edf4f59..51344f27be8932102674821016fb30506c155691 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -194,7 +194,7 @@ class FileDownloader(object):
        ignoreerrors:   Do not stop on download errors.
        ratelimit:      Download speed limit, in bytes/sec.
        nooverwrites:   Prevent overwriting files.
        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
+       retries:        Number of times to retry for HTTP error 5xx

        continuedl:     Try to continue downloads if possible.
        noprogress:     Do not print the progress bar.
        """
        continuedl:     Try to continue downloads if possible.
        noprogress:     Do not print the progress bar.
        """


@@ -353,12 +353,12 @@ class FileDownloader(object):
                                (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
 
        def report_resuming_byte(self, resume_len):
                                (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."""
+               """Report attempt to resume at given byte."""

                self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
        
        def report_retry(self, count, retries):
                self.to_stdout(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_stdout(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."""
        
        def report_file_already_downloaded(self, file_name):
                """Report file has already been fully downloaded."""


@@ -404,15 +404,16 @@ class FileDownloader(object):
                        template_dict['ord'] = unicode('%05d' % self._num_downloads)
                        filename = self.params['outtmpl'] % template_dict
                except (ValueError, KeyError), err:
                        template_dict['ord'] = 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):
                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:
                        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:
                        return
 
                try:


@@ -420,17 +421,17 @@ class FileDownloader(object):
                except (OSError, IOError), err:
                        raise UnavailableVideoError
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                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:
                        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:
                        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):
                                return
 
        def download(self, url_list):


@@ -455,7 +456,7 @@ class FileDownloader(object):
                                break
 
                        if not suitable_found:
                                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
 
 
                return self._download_retcode
 


@@ -495,7 +496,7 @@ class FileDownloader(object):
                        self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
                        return True
                else:
                        self.to_stdout(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):
                        return False
 
        def _do_download(self, filename, url, player_url):


@@ -528,7 +529,7 @@ class FileDownloader(object):
                                data = urllib2.urlopen(request)
                                break
                        except (urllib2.HTTPError, ), err:
                                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:
                                        # Unexpected HTTP error
                                        raise
                                elif err.code == 416:


@@ -538,7 +539,7 @@ class FileDownloader(object):
                                                data = urllib2.urlopen(basic_request)
                                                content_length = data.info()['Content-Length']
                                        except (urllib2.HTTPError, ), err:
                                                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
                                                        raise
                                        else:
                                                # Examine the reported length


@@ -588,12 +589,13 @@ class FileDownloader(object):
                                        (stream, filename) = sanitize_open(filename, open_mode)
                                        self.report_destination(filename)
                                except (OSError, IOError), err:
                                        (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:
                                        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
                        block_size = self.best_block_size(after - before, data_block_len)
 
                        # Progress message


@@ -684,7 +686,7 @@ class InfoExtractor(object):
 class YoutubeIE(InfoExtractor):
        """Information extractor for youtube.com."""
 
 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).+)?$'
+       _VALID_URL = r'^((?:http://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'

        _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'
        _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
        _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'
        _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'


@@ -847,7 +849,7 @@ class YoutubeIE(InfoExtractor):
                                return
                if 'token' not in video_info:
                        if 'reason' in video_info:
                                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
                        else:
                                self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
                        return


@@ -1020,7 +1022,6 @@ class MetacafeIE(InfoExtractor):
                self._downloader.increment_downloads()
 
                simple_title = mobj.group(2).decode('utf-8')
                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)
 
                # Retrieve video webpage to extract further information
                request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)


@@ -1034,20 +1035,33 @@ class MetacafeIE(InfoExtractor):
                # Extract URL, uploader and title from webpage
                self.report_extraction(video_id)
                mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
                # 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:
                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:
 
                mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
                if mobj is None:


@@ -1144,7 +1158,7 @@ class DailymotionIE(InfoExtractor):
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
 
                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
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
                        return


@@ -2087,7 +2101,7 @@ 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='2010.08.04',
+                       version='2010.10.03',

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