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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str
   6 from ..utils import (
   7     float_or_none,
   8     int_or_none,
   9     try_get,
  10 )
  11
  12
  13 class CarambaTVIE(InfoExtractor):
  14     _VALID_URL = r'(?:carambatv:|https?://video1\.carambatv\.ru/v/)(?P<id>\d+)'
  15     _TESTS = [{
  16         'url': 'http://video1.carambatv.ru/v/191910501',
  17         'md5': '2f4a81b7cfd5ab866ee2d7270cb34a2a',
  18         'info_dict': {
  19             'id': '191910501',
  20             'ext': 'mp4',
  21             'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
  22             'thumbnail': 're:^https?://.*\.jpg',
  23             'duration': 2678.31,
  24         },
  25     }, {
  26         'url': 'carambatv:191910501',
  27         'only_matching': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32
  33         video = self._download_json(
  34             'http://video1.carambatv.ru/v/%s/videoinfo.js' % video_id,
  35             video_id)
  36
  37         title = video['title']
  38
  39         base_url = video.get('video') or 'http://video1.carambatv.ru/v/%s/' % video_id
  40
  41         formats = [{
  42             'url': base_url + f['fn'],
  43             'height': int_or_none(f.get('height')),
  44             'format_id': '%sp' % f['height'] if f.get('height') else None,
  45         } for f in video['qualities'] if f.get('fn')]
  46         self._sort_formats(formats)
  47
  48         thumbnail = video.get('splash')
  49         duration = float_or_none(try_get(
  50             video, lambda x: x['annotations'][0]['end_time'], compat_str))
  51
  52         return {
  53             'id': video_id,
  54             'title': title,
  55             'thumbnail': thumbnail,
  56             'duration': duration,
  57             'formats': formats,
  58         }
  59
  60
  61 class CarambaTVPageIE(InfoExtractor):
  62     _VALID_URL = r'https?://carambatv\.ru/(?:[^/]+/)+(?P<id>[^/?#&]+)'
  63     _TEST = {
  64         'url': 'http://carambatv.ru/movie/bad-comedian/razborka-v-manile/',
  65         'md5': '',
  66         'info_dict': {
  67             'id': '191910501',
  68             'ext': 'mp4',
  69             'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
  70             'thumbnail': 're:^https?://.*\.jpg$',
  71             'duration': 2678.31,
  72         },
  73     }
  74
  75     def _real_extract(self, url):
  76         video_id = self._match_id(url)
  77
  78         webpage = self._download_webpage(url, video_id)
  79
  80         video_url = self._og_search_property('video:iframe', webpage, default=None)
  81
  82         if not video_url:
  83             video_id = self._search_regex(
  84                 r'(?:video_id|crmb_vuid)\s*[:=]\s*["\']?(\d+)',
  85                 webpage, 'video id')
  86             video_url = 'carambatv:%s' % video_id
  87
  88         return self.url_result(video_url, CarambaTVIE.ie_key())