youtube_dl/extractor/ninegag.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class NineGagIE(InfoExtractor):
   9     IE_NAME = '9gag'
  10     _VALID_URL = r'''(?x)^https?://(?:www\.)?9gag\.tv/
  11         (?:
  12             v/(?P<numid>[0-9]+)|
  13             p/(?P<id>[a-zA-Z0-9]+)/(?P<display_id>[^?#/]+)
  14         )
  15     '''
  16
  17     _TESTS = [{
  18         "url": "http://9gag.tv/v/1912",
  19         "info_dict": {
  20             "id": "1912",
  21             "ext": "mp4",
  22             "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!)",
  23             "title": "\"People Are Awesome 2013\" Is Absolutely Awesome",
  24             "view_count": int,
  25             "thumbnail": "re:^https?://",
  26         },
  27         'add_ie': ['Youtube']
  28     },
  29     {
  30         'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar',
  31         'info_dict': {
  32             'id': 'KklwM',
  33             'ext': 'mp4',
  34             'display_id': 'alternate-banned-opening-scene-of-gravity',
  35             "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.",
  36             'title': "Banned Opening Scene Of \"Gravity\" That Changes The Whole Movie",
  37         },
  38     }]
  39
  40     def _real_extract(self, url):
  41         mobj = re.match(self._VALID_URL, url)
  42         video_id = mobj.group('numid') or mobj.group('id')
  43         display_id = mobj.group('display_id') or video_id
  44
  45         webpage = self._download_webpage(url, display_id)
  46
  47         youtube_id = self._html_search_regex(
  48             r'(?s)id="jsid-video-post-container".*?data-external-id="([^"]+)"',
  49             webpage, 'video ID')
  50         title = self._html_search_regex(
  51             r'(?s)id="jsid-video-post-container".*?data-title="([^"]+)"',
  52             webpage, 'title', default=None)
  53         if not title:
  54             title = self._og_search_title(webpage)
  55         description = self._html_search_regex(
  56             r'(?s)<div class="video-caption">.*?<p>(.*?)</p>', webpage,
  57             'description', fatal=False)
  58         view_count_str = self._html_search_regex(
  59             r'<p><b>([0-9][0-9,]*)</b> views</p>', webpage, 'view count',
  60             fatal=False)
  61         view_count = (
  62             None if view_count_str is None
  63             else int(view_count_str.replace(',', '')))
  64
  65         return {
  66             '_type': 'url_transparent',
  67             'url': youtube_id,
  68             'ie_key': 'Youtube',
  69             'id': video_id,
  70             'display_id': display_id,
  71             'title': title,
  72             'description': description,
  73             'view_count': view_count,
  74             'thumbnail': self._og_search_thumbnail(webpage),
  75         }