aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2014-11-27 15:44:35 +0100
committerPhilipp Hagemeister <phihag@phihag.de>2014-11-27 15:44:35 +0100
commit4207558e8bd3f9586f50e80cde4725cec636fcff (patch)
tree333b109a1ae56e1ee80b80a29766edb4284a3215 /youtube_dl/extractor
parentad0d800fc3ab62f925076d851a2cb933ac3e8887 (diff)
[buzzfeed] Add support for more video types (#4259)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/buzzfeed.py32
1 files changed, 27 insertions, 5 deletions
diff --git a/youtube_dl/extractor/buzzfeed.py b/youtube_dl/extractor/buzzfeed.py
index 9c891af51..a40a1bbc4 100644
--- a/youtube_dl/extractor/buzzfeed.py
+++ b/youtube_dl/extractor/buzzfeed.py
@@ -9,7 +9,7 @@ from .common import InfoExtractor
class BuzzFeedIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?buzzfeed\.com/[^?#]*?/(?P<id>[^?#]+)'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.buzzfeed.com/abagg/this-angry-ram-destroys-a-punching-bag-like-a-boss?utm_term=4ldqpia',
'info_dict': {
'id': 'this-angry-ram-destroys-a-punching-bag-like-a-boss',
@@ -27,21 +27,43 @@ class BuzzFeedIE(InfoExtractor):
'title': 'Angry Ram destroys a punching bag',
}
}]
- }
+ }, {
+ 'url': 'http://www.buzzfeed.com/sheridanwatson/look-at-this-cute-dog-omg?utm_term=4ldqpia',
+ 'params': {
+ 'skip_download': True, # Got enough YouTube download tests
+ },
+ 'info_dict': {
+ 'description': 'Munchkin the Teddy Bear is back !',
+ 'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill',
+ },
+ 'playlist': [{
+ 'info_dict': {
+ 'id': 'mVmBL8B-In0',
+ 'ext': 'mp4',
+ 'upload_date': '20141124',
+ 'uploader_id': 'CindysMunchkin',
+ 'description': '© 2014 Munchkin the Shih Tzu\nAll rights reserved\nFacebook: http://facebook.com/MunchkintheShihTzu',
+ 'uploader': 'Munchkin the Shih Tzu',
+ 'title': 'Munchkin the Teddy Bear gets her exercise',
+ },
+ }]
+ }]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
all_buckets = re.findall(
- r'<div class="video-embed-videopost[^"]*".*?rel:bf_bucket_data=\'([^\']+)\'',
+ r'(?s)<div class="video-embed[^"]*"..*?rel:bf_bucket_data=\'([^\']+)\'',
webpage)
+
entries = []
for bd_json in all_buckets:
bd = json.loads(bd_json)
- if 'video' not in bd:
+ video = bd.get('video') or bd.get('progload_video')
+ if not video:
continue
- entries.append(self.url_result(bd['video']['url']))
+ entries.append(self.url_result(video['url']))
return {
'_type': 'playlist',