yt_dlp/extractor/manoto.py

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