1 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..utils import str_to_int
10 class NineGagIE(InfoExtractor):
12 _VALID_URL = r'''(?x)^https?://(?:www\.)?9gag\.tv/
15 p/(?P<id>[a-zA-Z0-9]+)/(?P<display_id>[^?#/]+)
20 "url": "http://9gag.tv/v/1912",
24 "description": "This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)",
25 "title": "\"People Are Awesome 2013\" Is Absolutely Awesome",
27 "thumbnail": "re:^https?://",
32 'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar',
36 'display_id': 'alternate-banned-opening-scene-of-gravity',
37 "description": "While Gravity was a pretty awesome movie already, YouTuber Krishna Shenoi came up with a way to improve upon it, introducing a much better solution to Sandra Bullock's seemingly endless tumble in space. The ending is priceless.",
38 'title': "Banned Opening Scene Of \"Gravity\" That Changes The Whole Movie",
42 def _real_extract(self, url):
43 mobj = re.match(self._VALID_URL, url)
44 video_id = mobj.group('numid') or mobj.group('id')
45 display_id = mobj.group('display_id') or video_id
47 webpage = self._download_webpage(url, display_id)
49 post_view = json.loads(self._html_search_regex(
50 r'var postView = new app\.PostView\({\s*post:\s*({.+?}),\s*posts:\s*prefetchedCurrentPost', webpage, 'post view'))
52 youtube_id = post_view['videoExternalId']
53 title = post_view['title']
54 description = post_view['description']
55 view_count = str_to_int(post_view['externalView'])
56 thumbnail = post_view.get('thumbnail_700w') or post_view.get('ogImageUrl') or post_view.get('thumbnail_300w')
59 '_type': 'url_transparent',
63 'display_id': display_id,
65 'description': description,
66 'view_count': view_count,
67 'thumbnail': thumbnail,