aboutsummaryrefslogtreecommitdiffhomepage
path: root/youtube_dl/extractor/buzzfeed.py
diff options
context:
space:
mode:
authorPhilipp Hagemeister <[email protected]>2014-11-26 22:52:52 +0100
committerPhilipp Hagemeister <[email protected]>2014-11-26 22:52:52 +0100
commite232f787f675e95c85a0b2471e496a8b1683fd95 (patch)
treebc836a6468df384ea174aa924a2e985c913d614b /youtube_dl/extractor/buzzfeed.py
parent155f9550c0f7c0f671d7607f1be671e26a75f39d (diff)
downloadyoutube-dl-e232f787f675e95c85a0b2471e496a8b1683fd95.tar.gz
youtube-dl-e232f787f675e95c85a0b2471e496a8b1683fd95.zip
[buzzfeed] Add new extractor (Fixes #4259)
Diffstat (limited to 'youtube_dl/extractor/buzzfeed.py')
-rw-r--r--youtube_dl/extractor/buzzfeed.py52
1 files changed, 52 insertions, 0 deletions
diff --git a/youtube_dl/extractor/buzzfeed.py b/youtube_dl/extractor/buzzfeed.py
new file mode 100644
index 000000000..9c891af51
--- /dev/null
+++ b/youtube_dl/extractor/buzzfeed.py
@@ -0,0 +1,52 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+
+
+class BuzzFeedIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?buzzfeed\.com/[^?#]*?/(?P<id>[^?#]+)'
+ _TEST = {
+ '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',
+ 'title': 'This Angry Ram Destroys A Punching Bag Like A Boss',
+ 'description': 'Rambro!',
+ },
+ 'playlist': [{
+ 'info_dict': {
+ 'id': 'aVCR29aE_OQ',
+ 'ext': 'mp4',
+ 'upload_date': '20141024',
+ 'uploader_id': 'Buddhanz1',
+ 'description': 'He likes to stay in shape with his heavy bag, he wont stop until its on the ground\n\nFollow Angry Ram on Facebook for regular updates -\nhttps://www.facebook.com/pages/Angry-Ram/1436897249899558?ref=hl',
+ 'uploader': 'Buddhanz',
+ 'title': 'Angry Ram destroys a punching bag',
+ }
+ }]
+ }
+
+ 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=\'([^\']+)\'',
+ webpage)
+ entries = []
+ for bd_json in all_buckets:
+ bd = json.loads(bd_json)
+ if 'video' not in bd:
+ continue
+ entries.append(self.url_result(bd['video']['url']))
+
+ return {
+ '_type': 'playlist',
+ 'id': playlist_id,
+ 'title': self._og_search_title(webpage),
+ 'description': self._og_search_description(webpage),
+ 'entries': entries,
+ }