diff --git a/youtube-dl b/youtube-dl index 167fefcc01..9c939023e3 100755 --- a/youtube-dl +++ b/youtube-dl @@ -1165,6 +1165,141 @@ class PhotobucketIE(InfoExtractor): self._downloader.trouble(u'ERROR: format not available for video') +class YahooIE(InfoExtractor): + """Information extractor for video.yahoo.com.""" + + # _VALID_URL matches all Yahoo! Video URLs + # _VPAGE_URL matches only the extractable '/watch/' URLs + _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' + _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + @staticmethod + def suitable(url): + return (re.match(YahooIE._VALID_URL, url) is not None) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_stdout(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) + + def _real_initialize(self): + return + + def _real_extract(self, url): + # 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 + + video_id = mobj.group(2) + video_extension = 'flv' + + # Rewrite valid but non-extractable URLs as + # extractable English language /watch/ URLs + if re.match(self._VPAGE_URL, url) is None: + request = urllib2.Request(url) + try: + 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 + + mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: Unable to extract id field') + return + yahoo_id = mobj.group(1) + + mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: Unable to extract vid field') + return + yahoo_vid = mobj.group(1) + + url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) + return self._real_extract(url) + + # Retrieve video webpage to extract further information + request = urllib2.Request(url) + 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 + + # Extract uploader and title from webpage + self.report_extraction(video_id) + 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) + + mobj = re.search(r'