yt_dlp/extractor/carambatv.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     format_field,
   5     float_or_none,
   6     int_or_none,
   7     try_get,
   8 )
   9
  10 from .videomore import VideomoreIE
  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': r'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': format_field(f, 'height', '%sp'),
  45         } for f in video['qualities'] if f.get('fn')]
  46
  47         thumbnail = video.get('splash')
  48         duration = float_or_none(try_get(
  49             video, lambda x: x['annotations'][0]['end_time'], compat_str))
  50
  51         return {
  52             'id': video_id,
  53             'title': title,
  54             'thumbnail': thumbnail,
  55             'duration': duration,
  56             'formats': formats,
  57         }
  58
  59
  60 class CarambaTVPageIE(InfoExtractor):
  61     _VALID_URL = r'https?://carambatv\.ru/(?:[^/]+/)+(?P<id>[^/?#&]+)'
  62     _TEST = {
  63         'url': 'http://carambatv.ru/movie/bad-comedian/razborka-v-manile/',
  64         'md5': 'a49fb0ec2ad66503eeb46aac237d3c86',
  65         'info_dict': {
  66             'id': '475222',
  67             'ext': 'flv',
  68             'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
  69             'thumbnail': r're:^https?://.*\.jpg',
  70             # duration reported by videomore is incorrect
  71             'duration': int,
  72         },
  73         'add_ie': [VideomoreIE.ie_key()],
  74     }
  75
  76     def _real_extract(self, url):
  77         video_id = self._match_id(url)
  78
  79         webpage = self._download_webpage(url, video_id)
  80
  81         videomore_url = VideomoreIE._extract_url(webpage)
  82         if not videomore_url:
  83             videomore_id = self._search_regex(
  84                 r'getVMCode\s*\(\s*["\']?(\d+)', webpage, 'videomore id',
  85                 default=None)
  86             if videomore_id:
  87                 videomore_url = 'videomore:%s' % videomore_id
  88         if videomore_url:
  89             title = self._og_search_title(webpage)
  90             return {
  91                 '_type': 'url_transparent',
  92                 'url': videomore_url,
  93                 'ie_key': VideomoreIE.ie_key(),
  94                 'title': title,
  95             }
  96
  97         video_url = self._og_search_property('video:iframe', webpage, default=None)
  98
  99         if not video_url:
 100             video_id = self._search_regex(
 101                 r'(?:video_id|crmb_vuid)\s*[:=]\s*["\']?(\d+)',
 102                 webpage, 'video id')
 103             video_url = 'carambatv:%s' % video_id
 104
 105         return self.url_result(video_url, CarambaTVIE.ie_key())