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 from .videomore import VideomoreIE
  13
  14
  15 class CarambaTVIE(InfoExtractor):
  16     _VALID_URL = r'(?:carambatv:|https?://video1\.carambatv\.ru/v/)(?P<id>\d+)'
  17     _TESTS = [{
  18         'url': 'http://video1.carambatv.ru/v/191910501',
  19         'md5': '2f4a81b7cfd5ab866ee2d7270cb34a2a',
  20         'info_dict': {
  21             'id': '191910501',
  22             'ext': 'mp4',
  23             'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
  24             'thumbnail': r're:^https?://.*\.jpg',
  25             'duration': 2678.31,
  26         },
  27     }, {
  28         'url': 'carambatv:191910501',
  29         'only_matching': True,
  30     }]
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34
  35         video = self._download_json(
  36             'http://video1.carambatv.ru/v/%s/videoinfo.js' % video_id,
  37             video_id)
  38
  39         title = video['title']
  40
  41         base_url = video.get('video') or 'http://video1.carambatv.ru/v/%s/' % video_id
  42
  43         formats = [{
  44             'url': base_url + f['fn'],
  45             'height': int_or_none(f.get('height')),
  46             'format_id': '%sp' % f['height'] if f.get('height') else None,
  47         } for f in video['qualities'] if f.get('fn')]
  48         self._sort_formats(formats)
  49
  50         thumbnail = video.get('splash')
  51         duration = float_or_none(try_get(
  52             video, lambda x: x['annotations'][0]['end_time'], compat_str))
  53
  54         return {
  55             'id': video_id,
  56             'title': title,
  57             'thumbnail': thumbnail,
  58             'duration': duration,
  59             'formats': formats,
  60         }
  61
  62
  63 class CarambaTVPageIE(InfoExtractor):
  64     _VALID_URL = r'https?://carambatv\.ru/(?:[^/]+/)+(?P<id>[^/?#&]+)'
  65     _TEST = {
  66         'url': 'http://carambatv.ru/movie/bad-comedian/razborka-v-manile/',
  67         'md5': 'a49fb0ec2ad66503eeb46aac237d3c86',
  68         'info_dict': {
  69             'id': '475222',
  70             'ext': 'flv',
  71             'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
  72             'thumbnail': r're:^https?://.*\.jpg',
  73             # duration reported by videomore is incorrect
  74             'duration': int,
  75         },
  76         'add_ie': [VideomoreIE.ie_key()],
  77     }
  78
  79     def _real_extract(self, url):
  80         video_id = self._match_id(url)
  81
  82         webpage = self._download_webpage(url, video_id)
  83
  84         videomore_url = VideomoreIE._extract_url(webpage)
  85         if not videomore_url:
  86             videomore_id = self._search_regex(
  87                 r'getVMCode\s*\(\s*["\']?(\d+)', webpage, 'videomore id',
  88                 default=None)
  89             if videomore_id:
  90                 videomore_url = 'videomore:%s' % videomore_id
  91         if videomore_url:
  92             title = self._og_search_title(webpage)
  93             return {
  94                 '_type': 'url_transparent',
  95                 'url': videomore_url,
  96                 'ie_key': VideomoreIE.ie_key(),
  97                 'title': title,
  98             }
  99
 100         video_url = self._og_search_property('video:iframe', webpage, default=None)
 101
 102         if not video_url:
 103             video_id = self._search_regex(
 104                 r'(?:video_id|crmb_vuid)\s*[:=]\s*["\']?(\d+)',
 105                 webpage, 'video id')
 106             video_url = 'carambatv:%s' % video_id
 107
 108         return self.url_result(video_url, CarambaTVIE.ie_key())