yt_dlp/extractor/zype.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_HTTPError
   5 from ..utils import (
   6     dict_get,
   7     ExtractorError,
   8     int_or_none,
   9     js_to_json,
  10     parse_iso8601,
  11 )
  12
  13
  14 class ZypeIE(InfoExtractor):
  15     _ID_RE = r'[\da-fA-F]+'
  16     _COMMON_RE = r'//player\.zype\.com/embed/%s\.(?:js|json|html)\?.*?(?:access_token|(?:ap[ip]|player)_key)='
  17     _VALID_URL = r'https?:%s[^&]+' % (_COMMON_RE % ('(?P<id>%s)' % _ID_RE))
  18     _EMBED_REGEX = [fr'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?{_COMMON_RE % _ID_RE}.+?)\1']
  19     _TEST = {
  20         'url': 'https://player.zype.com/embed/5b400b834b32992a310622b9.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ&autoplay=false&controls=true&da=false',
  21         'md5': 'eaee31d474c76a955bdaba02a505c595',
  22         'info_dict': {
  23             'id': '5b400b834b32992a310622b9',
  24             'ext': 'mp4',
  25             'title': 'Smoky Barbecue Favorites',
  26             'thumbnail': r're:^https?://.*\.jpe?g',
  27             'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
  28             'timestamp': 1504915200,
  29             'upload_date': '20170909',
  30         },
  31     }
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35
  36         try:
  37             response = self._download_json(re.sub(
  38                 r'\.(?:js|html)\?', '.json?', url), video_id)['response']
  39         except ExtractorError as e:
  40             if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401, 403):
  41                 raise ExtractorError(self._parse_json(
  42                     e.cause.read().decode(), video_id)['message'], expected=True)
  43             raise
  44
  45         body = response['body']
  46         video = response['video']
  47         title = video['title']
  48
  49         subtitles = {}
  50
  51         if isinstance(body, dict):
  52             formats = []
  53             for output in body.get('outputs', []):
  54                 output_url = output.get('url')
  55                 if not output_url:
  56                     continue
  57                 name = output.get('name')
  58                 if name == 'm3u8':
  59                     formats, subtitles = self._extract_m3u8_formats_and_subtitles(
  60                         output_url, video_id, 'mp4',
  61                         'm3u8_native', m3u8_id='hls', fatal=False)
  62                 else:
  63                     f = {
  64                         'format_id': name,
  65                         'tbr': int_or_none(output.get('bitrate')),
  66                         'url': output_url,
  67                     }
  68                     if name in ('m4a', 'mp3'):
  69                         f['vcodec'] = 'none'
  70                     else:
  71                         f.update({
  72                             'height': int_or_none(output.get('height')),
  73                             'width': int_or_none(output.get('width')),
  74                         })
  75                     formats.append(f)
  76             text_tracks = body.get('subtitles') or []
  77         else:
  78             m3u8_url = self._search_regex(
  79                 r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1',
  80                 body, 'm3u8 url', group='url', default=None)
  81             if not m3u8_url:
  82                 source = self._search_regex(
  83                     r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', body, 'source')
  84
  85                 def get_attr(key):
  86                     return self._search_regex(
  87                         r'\b%s\s*:\s*([\'"])(?P<val>(?:(?!\1).)+)\1' % key,
  88                         source, key, group='val')
  89
  90                 if get_attr('integration') == 'verizon-media':
  91                     m3u8_url = 'https://content.uplynk.com/%s.m3u8' % get_attr('id')
  92             formats, subtitles = self._extract_m3u8_formats_and_subtitles(
  93                 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
  94             text_tracks = self._search_regex(
  95                 r'textTracks\s*:\s*(\[[^]]+\])',
  96                 body, 'text tracks', default=None)
  97             if text_tracks:
  98                 text_tracks = self._parse_json(
  99                     text_tracks, video_id, js_to_json, False)
 100         self._sort_formats(formats)
 101
 102         if text_tracks:
 103             for text_track in text_tracks:
 104                 tt_url = dict_get(text_track, ('file', 'src'))
 105                 if not tt_url:
 106                     continue
 107                 subtitles.setdefault(text_track.get('label') or 'English', []).append({
 108                     'url': tt_url,
 109                 })
 110
 111         thumbnails = []
 112         for thumbnail in video.get('thumbnails', []):
 113             thumbnail_url = thumbnail.get('url')
 114             if not thumbnail_url:
 115                 continue
 116             thumbnails.append({
 117                 'url': thumbnail_url,
 118                 'width': int_or_none(thumbnail.get('width')),
 119                 'height': int_or_none(thumbnail.get('height')),
 120             })
 121
 122         return {
 123             'id': video_id,
 124             'display_id': video.get('friendly_title'),
 125             'title': title,
 126             'thumbnails': thumbnails,
 127             'description': dict_get(video, ('description', 'ott_description', 'short_description')),
 128             'timestamp': parse_iso8601(video.get('published_at')),
 129             'duration': int_or_none(video.get('duration')),
 130             'view_count': int_or_none(video.get('request_count')),
 131             'average_rating': int_or_none(video.get('rating')),
 132             'season_number': int_or_none(video.get('season')),
 133             'episode_number': int_or_none(video.get('episode')),
 134             'formats': formats,
 135             'subtitles': subtitles,
 136         }