X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube-dl;h=240b2bc7b17ecf554122f8a05960362215c730c3;hb=00f3977f774e14ea77ecfdcf9d2e6f3b4ef88fd5;hp=9e9be67784bedcb67f77881957761922e9616e3a;hpb=1bd9258272dd4884b5c159ae77e20ae75176e8d1;p=youtube-dl diff --git a/youtube-dl b/youtube-dl index 9e9be6778..240b2bc7b 100755 --- a/youtube-dl +++ b/youtube-dl @@ -858,7 +858,7 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' + _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' @@ -1056,7 +1056,7 @@ class YoutubeIE(InfoExtractor): # upload date upload_date = u'NA' - mobj = re.search(r'id="eow-date".*?>(.*?)', video_webpage, re.DOTALL) + mobj = re.search(r'id="eow-date.*?>(.*?)', video_webpage, re.DOTALL) if mobj is not None: upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y'] @@ -1079,7 +1079,7 @@ class YoutubeIE(InfoExtractor): # Decide which formats to download req_format = self._downloader.params.get('format', None) - if 'fmt_url_map' in video_info: + if 'fmt_url_map' in video_info and len(video_info['fmt_url_map']) >= 1 and ',' in video_info['fmt_url_map'][0]: url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(',')) format_limit = self._downloader.params.get('format_limit', None) if format_limit is not None and format_limit in self._available_formats: @@ -1720,6 +1720,123 @@ class YahooIE(InfoExtractor): self._downloader.trouble(u'\nERROR: unable to download video') +class VimeoIE(InfoExtractor): + """Information extractor for vimeo.com.""" + + # _VALID_URL matches Vimeo URLs + _VALID_URL = r'(?:http://)?(?:(?:www|player).)?vimeo\.com/(?:video/)?([0-9]+)' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + @staticmethod + def suitable(url): + return (re.match(VimeoIE._VALID_URL, url) is not None) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[video.vimeo] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[video.vimeo] %s: Extracting information' % video_id) + + def _real_initialize(self): + return + + def _real_extract(self, url, new_video=True): + # Extract ID from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + # At this point we have a new video + self._downloader.increment_downloads() + video_id = mobj.group(1) + video_extension = 'flv' # FIXME + + # Retrieve video webpage to extract further information + request = urllib2.Request("http://vimeo.com/moogaloop/load/clip:%s" % video_id, None, std_headers) + try: + self.report_download_webpage(video_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + # Now we begin extracting as much information as we can from what we + # retrieved. First we extract the information common to all extractors, + # and latter we extract those that are Vimeo specific. + self.report_extraction(video_id) + + # Extract title + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1).decode('utf-8') + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + + # Extract uploader + mobj = re.search(r'http://vimeo.com/(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video uploader') + return + video_uploader = mobj.group(1).decode('utf-8') + + # Extract video thumbnail + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = mobj.group(1).decode('utf-8') + + # # Extract video description + # mobj = re.search(r'', webpage) + # if mobj is None: + # self._downloader.trouble(u'ERROR: unable to extract video description') + # return + # video_description = mobj.group(1).decode('utf-8') + # if not video_description: video_description = 'No description available.' + video_description = 'Foo.' + + # Vimeo specific: extract request signature + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract request signature') + return + sig = mobj.group(1).decode('utf-8') + + # Vimeo specific: Extract request signature expiration + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract request signature expiration') + return + sig_exp = mobj.group(1).decode('utf-8') + + video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s" % (video_id, sig, sig_exp) + + try: + # Process video information + self._downloader.process_info({ + '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'), + 'thumbnail': video_thumbnail.decode('utf-8'), + 'description': video_description, + 'thumbnail': video_thumbnail, + 'description': video_description, + 'player_url': None, + }) + except UnavailableVideoError: + self._downloader.trouble(u'ERROR: unable to download video') + + class GenericIE(InfoExtractor): """Generic last-resort information extractor.""" @@ -2619,10 +2736,13 @@ class FFmpegExtractAudioPP(PostProcessor): @staticmethod def get_audio_codec(path): - handle = subprocess.Popen(['ffprobe', '-show_streams', path], - stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE) - output = handle.communicate()[0] - if handle.wait() != 0: + try: + cmd = ['ffprobe', '-show_streams', '--', path] + handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE) + output = handle.communicate()[0] + if handle.wait() != 0: + return None + except (IOError, OSError): return None audio_codec = None for line in output.split('\n'): @@ -2635,8 +2755,8 @@ class FFmpegExtractAudioPP(PostProcessor): @staticmethod def run_ffmpeg(path, out_path, codec, more_opts): try: - ret = subprocess.call(['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + [out_path], - stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT) + cmd = ['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + ['--', out_path] + ret = subprocess.call(cmd, stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT) return (ret == 0) except (IOError, OSError): return False @@ -2646,7 +2766,7 @@ class FFmpegExtractAudioPP(PostProcessor): filecodec = self.get_audio_codec(path) if filecodec is None: - self._downloader.to_stderr(u'WARNING: no audio codec found in file') + self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe') return None more_opts = [] @@ -2720,7 +2840,7 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='2011.02.25', + version='2011.03.29', conflict_handler='resolve', ) @@ -2895,6 +3015,7 @@ if __name__ == '__main__': parser.error(u'invalid audio format specified') # Information extractors + vimeo_ie = VimeoIE() youtube_ie = YoutubeIE() metacafe_ie = MetacafeIE(youtube_ie) dailymotion_ie = DailymotionIE() @@ -2947,6 +3068,7 @@ if __name__ == '__main__': 'nopart': opts.nopart, 'updatetime': opts.updatetime, }) + fd.add_info_extractor(vimeo_ie) fd.add_info_extractor(youtube_search_ie) fd.add_info_extractor(youtube_pl_ie) fd.add_info_extractor(youtube_user_ie)