]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/buzzfeed.py
debian/copyright: Fix lintian's dep5-copyright-license-name-not-unique.
[youtubedl] / youtube_dl / extractor / buzzfeed.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import json
5 import re
6
7 from .common import InfoExtractor
8
9
10 class BuzzFeedIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?buzzfeed\.com/[^?#]*?/(?P<id>[^?#]+)'
12 _TESTS = [{
13 'url': 'http://www.buzzfeed.com/abagg/this-angry-ram-destroys-a-punching-bag-like-a-boss?utm_term=4ldqpia',
14 'info_dict': {
15 'id': 'this-angry-ram-destroys-a-punching-bag-like-a-boss',
16 'title': 'This Angry Ram Destroys A Punching Bag Like A Boss',
17 'description': 'Rambro!',
18 },
19 'playlist': [{
20 'info_dict': {
21 'id': 'aVCR29aE_OQ',
22 'ext': 'mp4',
23 'upload_date': '20141024',
24 'uploader_id': 'Buddhanz1',
25 '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',
26 'uploader': 'Buddhanz',
27 'title': 'Angry Ram destroys a punching bag',
28 }
29 }]
30 }, {
31 'url': 'http://www.buzzfeed.com/sheridanwatson/look-at-this-cute-dog-omg?utm_term=4ldqpia',
32 'params': {
33 'skip_download': True, # Got enough YouTube download tests
34 },
35 'info_dict': {
36 'id': 'look-at-this-cute-dog-omg',
37 'description': 're:Munchkin the Teddy Bear is back ?!',
38 'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill',
39 },
40 'playlist': [{
41 'info_dict': {
42 'id': 'mVmBL8B-In0',
43 'ext': 'mp4',
44 'upload_date': '20141124',
45 'uploader_id': 'CindysMunchkin',
46 'description': 're:© 2014 Munchkin the',
47 'uploader': 're:^Munchkin the',
48 'title': 're:Munchkin the Teddy Bear gets her exercise',
49 },
50 }]
51 }]
52
53 def _real_extract(self, url):
54 playlist_id = self._match_id(url)
55 webpage = self._download_webpage(url, playlist_id)
56
57 all_buckets = re.findall(
58 r'(?s)<div class="video-embed[^"]*"..*?rel:bf_bucket_data=\'([^\']+)\'',
59 webpage)
60
61 entries = []
62 for bd_json in all_buckets:
63 bd = json.loads(bd_json)
64 video = bd.get('video') or bd.get('progload_video')
65 if not video:
66 continue
67 entries.append(self.url_result(video['url']))
68
69 return {
70 '_type': 'playlist',
71 'id': playlist_id,
72 'title': self._og_search_title(webpage),
73 'description': self._og_search_description(webpage),
74 'entries': entries,
75 }