aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYen Chi Hsuan <yan12125@gmail.com>2015-06-05 22:55:29 +0800
committerYen Chi Hsuan <yan12125@gmail.com>2015-06-05 22:59:04 +0800
commitd31573fa37c8db7133492baf0a6be3ece643f8ff (patch)
tree24e68193cc35e84fee5f613030529aad4c6a05dd
parent0e805e782bd05951ca3f420cf2a050e2ac3ae846 (diff)
[teamcoco] Handle incomplete m3u8 URLs (fixes #5798)
There are 2 TODOs. I don't know how to handle these cases correctly.
-rw-r--r--youtube_dl/extractor/teamcoco.py29
1 files changed, 27 insertions, 2 deletions
diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py
index b2a4b1fc0..d1b7264b4 100644
--- a/youtube_dl/extractor/teamcoco.py
+++ b/youtube_dl/extractor/teamcoco.py
@@ -51,6 +51,17 @@ class TeamcocoIE(InfoExtractor):
'params': {
'skip_download': True, # m3u8 downloads
}
+ }, {
+ 'url': 'http://teamcoco.com/video/full-episode-mon-6-1-joel-mchale-jake-tapper-and-musical-guest-courtney-barnett?playlist=x;eyJ0eXBlIjoidGFnIiwiaWQiOjl9',
+ 'info_dict': {
+ 'id': '89341',
+ 'ext': 'mp4',
+ 'title': 'Full Episode - Mon. 6/1 - Joel McHale, Jake Tapper, And Musical Guest Courtney Barnett',
+ 'description': 'Guests: Joel McHale, Jake Tapper, And Musical Guest Courtney Barnett',
+ },
+ 'params': {
+ 'skip_download': True, # m3u8 downloads
+ }
}
]
_VIDEO_ID_REGEXES = (
@@ -110,9 +121,23 @@ class TeamcocoIE(InfoExtractor):
get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
for filed in data['files']:
if determine_ext(filed['url']) == 'm3u8':
- formats.extend(self._extract_m3u8_formats(
- filed['url'], video_id, ext='mp4'))
+ # compat_urllib_parse.urljoin does not work here
+ if filed['url'].startswith('/'):
+ m3u8_url = 'http://ht.cdn.turner.com/tbs/big/teamcoco' + filed['url']
+ else:
+ m3u8_url = filed['url']
+ m3u8_formats = self._extract_m3u8_formats(
+ m3u8_url, video_id, ext='mp4')
+ for m3u8_format in m3u8_formats:
+ if m3u8_format not in formats:
+ formats.append(m3u8_format)
+ elif determine_ext(filed['url']) == 'f4m':
+ # TODO Correct f4m extraction
+ continue
else:
+ if filed['url'].startswith('/mp4:protected/'):
+ # TODO Correct extraction for these files
+ continue
m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
if m_format is not None:
format_id = m_format.group(1)