yt_dlp/extractor/manoto.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     int_or_none,
   5     traverse_obj
   6 )
   7
   8
   9 _API_URL = 'https://dak1vd5vmi7x6.cloudfront.net/api/v1/publicrole/{}/{}?id={}'
  10
  11
  12 class ManotoTVIE(InfoExtractor):
  13     IE_DESC = 'Manoto TV (Episode)'
  14     _VALID_URL = r'https?://(?:www\.)?manototv\.com/episode/(?P<id>[0-9]+)'
  15     _TESTS = [{
  16         'url': 'https://www.manototv.com/episode/8475',
  17         'info_dict': {
  18             'id': '8475',
  19             'series': 'خانه های رویایی با برادران اسکات',
  20             'season_number': 7,
  21             'episode_number': 25,
  22             'episode_id': 'My Dream Home S7: Carol & John',
  23             'duration': 3600,
  24             'categories': ['سرگرمی'],
  25             'title': 'کارول و جان',
  26             'description': 'md5:d0fff1f8ba5c6775d312a00165d1a97e',
  27             'thumbnail': r're:^https?://.*\.(jpeg|png|jpg)$',
  28             'ext': 'mp4'
  29         },
  30         'params': {
  31             'skip_download': 'm3u8',
  32         }
  33     }, {
  34         'url': 'https://www.manototv.com/episode/12576',
  35         'info_dict': {
  36             'id': '12576',
  37             'series': 'فیلم های ایرانی',
  38             'episode_id': 'Seh Mah Taatili',
  39             'duration': 5400,
  40             'view_count': int,
  41             'categories': ['سرگرمی'],
  42             'title': 'سه ماه تعطیلی',
  43             'description': 'سه ماه تعطیلی فیلمی به کارگردانی و نویسندگی شاپور قریب ساختهٔ سال ۱۳۵۶ است.',
  44             'thumbnail': r're:^https?://.*\.(jpeg|png|jpg)$',
  45             'ext': 'mp4'
  46         },
  47         'params': {
  48             'skip_download': 'm3u8',
  49         }
  50     }]
  51
  52     def _real_extract(self, url):
  53         video_id = self._match_id(url)
  54         episode_json = self._download_json(_API_URL.format('showmodule', 'episodedetails', video_id), video_id)
  55         details = episode_json.get('details', {})
  56         formats = self._extract_m3u8_formats(details.get('videoM3u8Url'), video_id, 'mp4')
  57         self._sort_formats(formats)
  58         return {
  59             'id': video_id,
  60             'series': details.get('showTitle'),
  61             'season_number': int_or_none(details.get('analyticsSeasonNumber')),
  62             'episode_number': int_or_none(details.get('episodeNumber')),
  63             'episode_id': details.get('analyticsEpisodeTitle'),
  64             'duration': int_or_none(details.get('durationInMinutes'), invscale=60),
  65             'view_count': details.get('viewCount'),
  66             'categories': [details.get('videoCategory')],
  67             'title': details.get('episodeTitle'),
  68             'description': clean_html(details.get('episodeDescription')),
  69             'thumbnail': details.get('episodelandscapeImgIxUrl'),
  70             'formats': formats,
  71         }
  72
  73
  74 class ManotoTVShowIE(InfoExtractor):
  75     IE_DESC = 'Manoto TV (Show)'
  76     _VALID_URL = r'https?://(?:www\.)?manototv\.com/show/(?P<id>[0-9]+)'
  77     _TESTS = [{
  78         'url': 'https://www.manototv.com/show/2526',
  79         'playlist_mincount': 68,
  80         'info_dict': {
  81             'id': '2526',
  82             'title': 'فیلم های ایرانی',
  83             'description': 'مجموعه ای از فیلم های سینمای کلاسیک ایران',
  84         },
  85     }]
  86
  87     def _real_extract(self, url):
  88         show_id = self._match_id(url)
  89         show_json = self._download_json(_API_URL.format('showmodule', 'details', show_id), show_id)
  90         show_details = show_json.get('details', {})
  91         title = show_details.get('showTitle')
  92         description = show_details.get('showSynopsis')
  93
  94         series_json = self._download_json(_API_URL.format('showmodule', 'serieslist', show_id), show_id)
  95         playlist_id = str(traverse_obj(series_json, ('details', 'list', 0, 'id')))
  96
  97         playlist_json = self._download_json(_API_URL.format('showmodule', 'episodelist', playlist_id), playlist_id)
  98         playlist = traverse_obj(playlist_json, ('details', 'list')) or []
  99
 100         entries = [
 101             self.url_result(
 102                 'https://www.manototv.com/episode/%s' % item['slideID'], ie=ManotoTVIE.ie_key(), video_id=item['slideID'])
 103             for item in playlist]
 104         return self.playlist_result(entries, show_id, title, description)
 105
 106
 107 class ManotoTVLiveIE(InfoExtractor):
 108     IE_DESC = 'Manoto TV (Live)'
 109     _VALID_URL = r'https?://(?:www\.)?manototv\.com/live/'
 110     _TEST = {
 111         'url': 'https://www.manototv.com/live/',
 112         'info_dict': {
 113             'id': 'live',
 114             'title': 'Manoto TV Live',
 115             'ext': 'mp4',
 116             'is_live': True,
 117         },
 118         'params': {
 119             'skip_download': 'm3u8',
 120         }
 121     }
 122
 123     def _real_extract(self, url):
 124         video_id = 'live'
 125         json = self._download_json(_API_URL.format('livemodule', 'details', ''), video_id)
 126         details = json.get('details', {})
 127         video_url = details.get('liveUrl')
 128         formats = self._extract_m3u8_formats(video_url, video_id, 'mp4', live=True)
 129         self._sort_formats(formats)
 130         return {
 131             'id': video_id,
 132             'title': 'Manoto TV Live',
 133             'is_live': True,
 134             'formats': formats,
 135         }