diff options
| author | Sergey M․ <dstftw@gmail.com> | 2015-10-08 20:49:56 +0600 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2015-10-08 21:05:48 +0600 |
| commit | 4356d907c1afae09ff67a17c90b53be466b13623 (patch) | |
| tree | 348f9114c2646bdb2c7445d5049da87b776f01d2 | |
| parent | c677e49bd11c3dfada05de9fc1d4de04a577d70e (diff) | |
[4tube] Try extracting sources from the webpage before fetching player.js (Closes #7103)
| -rw-r--r-- | youtube_dl/extractor/fourtube.py | 31 |
1 files changed, 18 insertions, 13 deletions
diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py index cd7668f18..fb6d108c0 100644 --- a/youtube_dl/extractor/fourtube.py +++ b/youtube_dl/extractor/fourtube.py @@ -68,19 +68,24 @@ class FourTubeIE(InfoExtractor): webpage, 'like count', fatal=False)) duration = parse_duration(self._html_search_meta('duration', webpage)) - player_js = self._download_webpage( - self._search_regex( - r'<script[^>]id=(["\'])playerembed\1[^>]+src=(["\'])(?P<url>.+?)\2', - webpage, 'player JS', group='url'), - video_id, 'Downloading player JS') - - params_js = self._search_regex( - r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)', - player_js, 'initialization parameters' - ) - params = self._parse_json('[%s]' % params_js, video_id) - media_id = params[0] - sources = ['%s' % p for p in params[2]] + media_id = self._search_regex( + r'<button[^>]+data-id=(["\'])(?P<id>\d+)\1[^>]+data-quality=', webpage, + 'media id', default=None, group='id') + sources = [ + quality + for _, quality in re.findall(r'<button[^>]+data-quality=(["\'])(.+?)\1', webpage)] + if not (media_id and sources): + player_js = self._download_webpage( + self._search_regex( + r'<script[^>]id=(["\'])playerembed\1[^>]+src=(["\'])(?P<url>.+?)\2', + webpage, 'player JS', group='url'), + video_id, 'Downloading player JS') + params_js = self._search_regex( + r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)', + player_js, 'initialization parameters') + params = self._parse_json('[%s]' % params_js, video_id) + media_id = params[0] + sources = ['%s' % p for p in params[2]] token_url = 'http://tkn.4tube.com/{0}/desktop/{1}'.format( media_id, '+'.join(sources)) |