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

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import str_to_int
   8
   9
  10 class NineGagIE(InfoExtractor):
  11     IE_NAME = '9gag'
  12     _VALID_URL = r'''(?x)^https?://(?:www\.)?9gag\.tv/
  13         (?:
  14             v/(?P<numid>[0-9]+)|
  15             p/(?P<id>[a-zA-Z0-9]+)/(?P<display_id>[^?#/]+)
  16         )
  17     '''
  18
  19     _TESTS = [{
  20         "url": "http://9gag.tv/v/1912",
  21         "info_dict": {
  22             "id": "1912",
  23             "ext": "mp4",
  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",
  26             'uploader_id': 'UCdEH6EjDKwtTe-sO2f0_1XA',
  27             'uploader': 'CompilationChannel',
  28             'upload_date': '20131110',
  29             "view_count": int,
  30             "thumbnail": "re:^https?://",
  31         },
  32         'add_ie': ['Youtube']
  33     }, {
  34         'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar',
  35         'info_dict': {
  36             'id': 'KklwM',
  37             'ext': 'mp4',
  38             'display_id': 'alternate-banned-opening-scene-of-gravity',
  39             "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.",
  40             'title': "Banned Opening Scene Of \"Gravity\" That Changes The Whole Movie",
  41             'uploader': 'Krishna Shenoi',
  42             'upload_date': '20140401',
  43             'uploader_id': 'krishnashenoi93',
  44         },
  45     }]
  46
  47     def _real_extract(self, url):
  48         mobj = re.match(self._VALID_URL, url)
  49         video_id = mobj.group('numid') or mobj.group('id')
  50         display_id = mobj.group('display_id') or video_id
  51
  52         webpage = self._download_webpage(url, display_id)
  53
  54         post_view = json.loads(self._html_search_regex(
  55             r'var postView = new app\.PostView\({\s*post:\s*({.+?}),\s*posts:\s*prefetchedCurrentPost', webpage, 'post view'))
  56
  57         youtube_id = post_view['videoExternalId']
  58         title = post_view['title']
  59         description = post_view['description']
  60         view_count = str_to_int(post_view['externalView'])
  61         thumbnail = post_view.get('thumbnail_700w') or post_view.get('ogImageUrl') or post_view.get('thumbnail_300w')
  62
  63         return {
  64             '_type': 'url_transparent',
  65             'url': youtube_id,
  66             'ie_key': 'Youtube',
  67             'id': video_id,
  68             'display_id': display_id,
  69             'title': title,
  70             'description': description,
  71             'view_count': view_count,
  72             'thumbnail': thumbnail,
  73         }