youtube_dl/extractor/ninegag.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class NineGagIE(InfoExtractor):
  10     IE_NAME = '9gag'
  11     _VALID_URL = r'^https?://(?:www\.)?9gag\.tv/v/(?P<id>[0-9]+)'
  12
  13     _TEST = {
  14         "url": "http://9gag.tv/v/1912",
  15         "file": "1912.mp4",
  16         "info_dict": {
  17             "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!)",
  18             "title": "\"People Are Awesome 2013\" Is Absolutely Awesome"
  19         },
  20         'add_ie': ['Youtube']
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('id')
  26
  27         webpage = self._download_webpage(url, video_id)
  28         data_json = self._html_search_regex(r'''(?x)
  29             <div\s*id="tv-video"\s*data-video-source="youtube"\s*
  30                 data-video-meta="([^"]+)"''', webpage, 'video metadata')
  31
  32         data = json.loads(data_json)
  33
  34         return {
  35             '_type': 'url_transparent',
  36             'url': data['youtubeVideoId'],
  37             'ie_key': 'Youtube',
  38             'id': video_id,
  39             'title': data['title'],
  40             'description': data['description'],
  41             'view_count': int(data['view_count']),
  42             'like_count': int(data['statistic']['like']),
  43             'dislike_count': int(data['statistic']['dislike']),
  44             'thumbnail': data['thumbnail_url'],
  45         }