youtube_dl/extractor/biqle.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from .vk import VKIE
   6 from ..utils import (
   7     HEADRequest,
   8     int_or_none,
   9 )
  10
  11
  12 class BIQLEIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?biqle\.(?:com|org|ru)/watch/(?P<id>-?\d+_\d+)'
  14     _TESTS = [{
  15         # Youtube embed
  16         'url': 'https://biqle.ru/watch/-115995369_456239081',
  17         'md5': '97af5a06ee4c29bbf9c001bdb1cf5c06',
  18         'info_dict': {
  19             'id': '8v4f-avW-VI',
  20             'ext': 'mp4',
  21             'title': "PASSE-PARTOUT - L'ete c'est fait pour jouer",
  22             'description': 'Passe-Partout',
  23             'uploader_id': 'mrsimpsonstef3',
  24             'uploader': 'Phanolito',
  25             'upload_date': '20120822',
  26         },
  27     }, {
  28         'url': 'http://biqle.org/watch/-44781847_168547604',
  29         'md5': '7f24e72af1db0edf7c1aaba513174f97',
  30         'info_dict': {
  31             'id': '-44781847_168547604',
  32             'ext': 'mp4',
  33             'title': 'Ребенок в шоке от автоматической мойки',
  34             'timestamp': 1396633454,
  35             'uploader': 'Dmitry Kotov',
  36             'upload_date': '20140404',
  37             'uploader_id': '47850140',
  38         },
  39     }]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43         webpage = self._download_webpage(url, video_id)
  44         embed_url = self._proto_relative_url(self._search_regex(
  45             r'<iframe.+?src="((?:https?:)?//daxab\.com/[^"]+)".*?></iframe>',
  46             webpage, 'embed url'))
  47         if VKIE.suitable(embed_url):
  48             return self.url_result(embed_url, VKIE.ie_key(), video_id)
  49
  50         self._request_webpage(
  51             HEADRequest(embed_url), video_id, headers={'Referer': url})
  52         video_id, sig, _, access_token = self._get_cookies(embed_url)['video_ext'].value.split('%3A')
  53         item = self._download_json(
  54             'https://api.vk.com/method/video.get', video_id,
  55             headers={'User-Agent': 'okhttp/3.4.1'}, query={
  56                 'access_token': access_token,
  57                 'sig': sig,
  58                 'v': 5.44,
  59                 'videos': video_id,
  60             })['response']['items'][0]
  61         title = item['title']
  62
  63         formats = []
  64         for f_id, f_url in item.get('files', {}).items():
  65             if f_id == 'external':
  66                 return self.url_result(f_url)
  67             ext, height = f_id.split('_')
  68             formats.append({
  69                 'format_id': height + 'p',
  70                 'url': f_url,
  71                 'height': int_or_none(height),
  72                 'ext': ext,
  73             })
  74         self._sort_formats(formats)
  75
  76         thumbnails = []
  77         for k, v in item.items():
  78             if k.startswith('photo_') and v:
  79                 width = k.replace('photo_', '')
  80                 thumbnails.append({
  81                     'id': width,
  82                     'url': v,
  83                     'width': int_or_none(width),
  84                 })
  85
  86         return {
  87             'id': video_id,
  88             'title': title,
  89             'formats': formats,
  90             'comment_count': int_or_none(item.get('comments')),
  91             'description': item.get('description'),
  92             'duration': int_or_none(item.get('duration')),
  93             'thumbnails': thumbnails,
  94             'timestamp': int_or_none(item.get('date')),
  95             'uploader': item.get('owner_id'),
  96             'view_count': int_or_none(item.get('views')),
  97         }