diff options
| author | Ricardo Garcia <sarbalap+freshmeat@gmail.com> | 2010-08-12 19:15:26 +0200 |
|---|---|---|
| committer | Ricardo Garcia <sarbalap+freshmeat@gmail.com> | 2010-10-31 11:28:41 +0100 |
| commit | c6c555cf8a3e5457f84c6650b1f96a332db50d44 (patch) | |
| tree | e78cb0f7f875e2f259e43d065bc5f5c10b8701f2 | |
| parent | db7e31b853d888d129c7eeb8532ac29fd704b977 (diff) | |
Fix metacafe.com downloads for some videos (fixes issue #189)
| -rwxr-xr-x | youtube-dl | 36 |
1 files changed, 23 insertions, 13 deletions
diff --git a/youtube-dl b/youtube-dl index 717d97d96..e9211b240 100755 --- a/youtube-dl +++ b/youtube-dl @@ -1036,20 +1036,30 @@ 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)) + + # 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 + video_url = '%s?__gda__=%s' % (mobj.group(1).replace('\\/', '/'), mobj.group(2)) mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) if mobj is None: |