from __future__ import unicode_literals
import re
+import json
from .common import InfoExtractor
+from ..utils import str_to_int
class NineGagIE(InfoExtractor):
"ext": "mp4",
"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!)",
"title": "\"People Are Awesome 2013\" Is Absolutely Awesome",
+ 'uploader_id': 'UCdEH6EjDKwtTe-sO2f0_1XA',
+ 'uploader': 'CompilationChannel',
+ 'upload_date': '20131110',
"view_count": int,
"thumbnail": "re:^https?://",
},
'add_ie': ['Youtube']
- },
- {
+ }, {
'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar',
'info_dict': {
'id': 'KklwM',
'display_id': 'alternate-banned-opening-scene-of-gravity',
"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.",
'title': "Banned Opening Scene Of \"Gravity\" That Changes The Whole Movie",
+ 'uploader': 'Krishna Shenoi',
+ 'upload_date': '20140401',
+ 'uploader_id': 'krishnashenoi93',
},
}]
webpage = self._download_webpage(url, display_id)
- youtube_id = self._html_search_regex(
- r'(?s)id="jsid-video-post-container".*?data-external-id="([^"]+)"',
- webpage, 'video ID')
- title = self._html_search_regex(
- r'(?s)id="jsid-video-post-container".*?data-title="([^"]+)"',
- webpage, 'title', default=None)
- if not title:
- title = self._og_search_title(webpage)
- description = self._html_search_regex(
- r'(?s)<div class="video-caption">.*?<p>(.*?)</p>', webpage,
- 'description', fatal=False)
- view_count_str = self._html_search_regex(
- r'<p><b>([0-9][0-9,]*)</b> views</p>', webpage, 'view count',
- fatal=False)
- view_count = (
- None if view_count_str is None
- else int(view_count_str.replace(',', '')))
+ post_view = json.loads(self._html_search_regex(
+ r'var postView = new app\.PostView\({\s*post:\s*({.+?}),\s*posts:\s*prefetchedCurrentPost', webpage, 'post view'))
+
+ youtube_id = post_view['videoExternalId']
+ title = post_view['title']
+ description = post_view['description']
+ view_count = str_to_int(post_view['externalView'])
+ thumbnail = post_view.get('thumbnail_700w') or post_view.get('ogImageUrl') or post_view.get('thumbnail_300w')
return {
'_type': 'url_transparent',
'title': title,
'description': description,
'view_count': view_count,
- 'thumbnail': self._og_search_thumbnail(webpage),
+ 'thumbnail': thumbnail,
}