Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ninegag.py

   1 import json
   2 import re
   3
   4 from .common import InfoExtractor
   5
   6
   7 class NineGagIE(InfoExtractor):
   8     IE_NAME = '9gag'
   9     _VALID_URL = r'^https?://(?:www\.)?9gag\.tv/v/(?P<id>[0-9]+)'
  10
  11     _TEST = {
  12         u"url": u"http://9gag.tv/v/1912",
  13         u"file": u"1912.mp4",
  14         u"info_dict": {
  15             u"description": u"This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)",
  16             u"title": u"\"People Are Awesome 2013\" Is Absolutely Awesome"
  17         },
  18         u'add_ie': [u'Youtube']
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23         video_id = mobj.group('id')
  24
  25         webpage = self._download_webpage(url, video_id)
  26         data_json = self._html_search_regex(r'''(?x)
  27             <div\s*id="tv-video"\s*data-video-source="youtube"\s*
  28                 data-video-meta="([^"]+)"''', webpage, u'video metadata')
  29
  30         data = json.loads(data_json)
  31
  32         return {
  33             '_type': 'url_transparent',
  34             'url': data['youtubeVideoId'],
  35             'ie_key': 'Youtube',
  36             'id': video_id,
  37             'title': data['title'],
  38             'description': data['description'],
  39             'view_count': int(data['view_count']),
  40             'like_count': int(data['statistic']['like']),
  41             'dislike_count': int(data['statistic']['dislike']),
  42             'thumbnail': data['thumbnail_url'],
  43         }