diff --git a/youtube-dl b/youtube-dl index 0aae905052..7532a142f3 100755 --- a/youtube-dl +++ b/youtube-dl @@ -288,7 +288,6 @@ class FileDownloader(object): return - try: template_dict = dict(info_dict) template_dict['epoch'] = unicode(long(time.time())) @@ -621,53 +620,53 @@ class YoutubeIE(InfoExtractor): best_quality = True while True: + # Extension + video_extension = self._video_extensions.get(format_param, 'flv') + + # Normalize URL, including format + normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id + if format_param is not None: + normalized_url = '%s&fmt=%s' % (normalized_url, format_param) + request = urllib2.Request(normalized_url, None, std_headers) try: - # Extension - video_extension = self._video_extensions.get(format_param, 'flv') - - # Normalize URL, including format - normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id - if format_param is not None: - normalized_url = '%s&fmt=%s' % (normalized_url, format_param) - request = urllib2.Request(normalized_url, None, std_headers) - try: - self.report_webpage_download(video_id) - video_webpage = urllib2.urlopen(request).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) - return - self.report_information_extraction(video_id) - - # "t" param - mobj = re.search(r', "t": "([^"]+)"', video_webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract "t" parameter') - return - video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1)) - 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"var watchUsername = '([^']+)';", video_webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract uploader nickname') - return - video_uploader = mobj.group(1) + self.report_webpage_download(video_id) + video_webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return + self.report_information_extraction(video_id) + + # "t" param + mobj = re.search(r', "t": "([^"]+)"', video_webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract "t" parameter') + return + video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1)) + 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"var watchUsername = '([^']+)';", video_webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = mobj.group(1) - # title - mobj = re.search(r'(?im)YouTube - ([^<]*)', video_webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video title') - return - video_title = mobj.group(1).decode('utf-8') - video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title) - video_title = video_title.replace(os.sep, u'%') + # title + mobj = re.search(r'(?im)YouTube - ([^<]*)', video_webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1).decode('utf-8') + video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title) + video_title = video_title.replace(os.sep, u'%') - # simplified title - simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) - simple_title = simple_title.strip(ur'_') + # simplified title + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + simple_title = simple_title.strip(ur'_') + try: # Process video information self._downloader.process_info({ 'id': video_id.decode('utf-8'),