yt_dlp/extractor/itprotv.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     str_or_none,
   7     traverse_obj,
   8     urljoin,
   9 )
  10
  11
  12 class ITProTVBaseIE(InfoExtractor):
  13     _ENDPOINTS = {
  14         'course': 'course?url={}&brand=00002560-0000-3fa9-0000-1d61000035f3',
  15         'episode': 'brand/00002560-0000-3fa9-0000-1d61000035f3/episode?url={}',
  16     }
  17
  18     def _call_api(self, ep, item_id, webpage):
  19         return self._download_json(
  20             f'https://api.itpro.tv/api/urza/v3/consumer-web/{self._ENDPOINTS[ep].format(item_id)}',
  21             item_id, note=f'Fetching {ep} data API',
  22             headers={'Authorization': f'Bearer {self._fetch_jwt(webpage)}'})[ep]
  23
  24     def _fetch_jwt(self, webpage):
  25         return self._search_regex(r'{"passedToken":"([\w-]+\.[\w-]+\.[\w-]+)",', webpage, 'jwt')
  26
  27     def _check_if_logged_in(self, webpage):
  28         if re.match(r'{\s*member\s*:\s*null', webpage):
  29             self.raise_login_required()
  30
  31
  32 class ITProTVIE(ITProTVBaseIE):
  33     _VALID_URL = r'https?://app\.itpro\.tv/course/(?P<course>[\w-]+)/(?P<id>[\w-]+)'
  34     _TESTS = [{
  35         'url': 'https://app.itpro.tv/course/guided-tour/introductionitprotv',
  36         'md5': 'bca4a28c2667fd1a63052e71a94bb88c',
  37         'info_dict': {
  38             'id': 'introductionitprotv',
  39             'ext': 'mp4',
  40             'title': 'An Introduction to ITProTV 101',
  41             'thumbnail': 'https://itprotv-image-bucket.s3.amazonaws.com/getting-started/itprotv-101-introduction-PGM.11_39_56_02.Still001.png',
  42             'description': 'md5:b175c2c3061ce35a4dd33865b2c1da4e',
  43             'duration': 269,
  44             'series': 'ITProTV 101',
  45             'series_id': 'guided-tour',
  46             'availability': 'needs_auth',
  47             'chapter': 'ITProTV 101',
  48             'chapter_number': 1,
  49             'chapter_id': '5dbb3de426b46c0010b5d1b6',
  50         },
  51     },
  52         {
  53         'url': 'https://app.itpro.tv/course/beyond-tech/job-interview-tips',
  54         'md5': '101a299b98c47ccf4c67f9f0951defa8',
  55         'info_dict': {
  56             'id': 'job-interview-tips',
  57             'ext': 'mp4',
  58             'title': 'Job Interview Tips',
  59             'thumbnail': 'https://s3.amazonaws.com:443/production-itprotv-thumbnails/2f370bf5-294d-4bbe-ab80-c0b5781630ea.png',
  60             'description': 'md5:30d8ba483febdf89ec85623aad3c3cb6',
  61             'duration': 267,
  62             'series': 'Beyond Tech',
  63             'series_id': 'beyond-tech',
  64             'availability': 'needs_auth',
  65             'chapter': 'Job Development',
  66             'chapter_number': 2,
  67             'chapter_id': '5f7c78d424330c000edf04d9',
  68         },
  69     }]
  70
  71     def _real_extract(self, url):
  72         episode_id, course_name = self._match_valid_url(url).group('id', 'course')
  73         webpage = self._download_webpage(url, episode_id)
  74         self._check_if_logged_in(webpage)
  75         course = self._call_api('course', course_name, webpage)
  76         episode = self._call_api('episode', episode_id, webpage)
  77
  78         chapter_number, chapter = next((
  79             (i, topic) for i, topic in enumerate(course.get('topics') or [], 1)
  80             if traverse_obj(topic, 'id') == episode.get('topic')), {})
  81
  82         return {
  83             'id': episode_id,
  84             'title': episode.get('title'),
  85             'description': episode.get('description'),
  86             'thumbnail': episode.get('thumbnail'),
  87             'formats': [
  88                 {'url': episode[f'jwVideo{h}Embed'], 'height': h}
  89                 for h in (320, 480, 720, 1080) if episode.get(f'jwVideo{h}Embed')
  90             ],
  91             'duration': int_or_none(episode.get('length')),
  92             'series': course.get('name'),
  93             'series_id': course.get('url'),
  94             'chapter': str_or_none(chapter.get('title')),
  95             'chapter_number': chapter_number,
  96             'chapter_id': str_or_none(chapter.get('id')),
  97             'subtitles': {
  98                 'en': [{'ext': 'vtt', 'data': episode['enCaptionData']}],
  99             } if episode.get('enCaptionData') else None,
 100         }
 101
 102
 103 class ITProTVCourseIE(ITProTVBaseIE):
 104     _VALID_URL = r'https?://app\.itpro\.tv/course/(?P<id>[\w-]+)/?(?:$|[#?])'
 105     _TESTS = [
 106         {
 107             'url': 'https://app.itpro.tv/course/guided-tour',
 108             'info_dict': {
 109                 'id': 'guided-tour',
 110                 'description': 'md5:b175c2c3061ce35a4dd33865b2c1da4e',
 111                 'title': 'ITProTV 101',
 112             },
 113             'playlist_count': 6,
 114         },
 115         {
 116             'url': 'https://app.itpro.tv/course/beyond-tech',
 117             'info_dict': {
 118                 'id': 'beyond-tech',
 119                 'description': 'md5:44cd99855e7f81a15ce1269bd0621fed',
 120                 'title': 'Beyond Tech',
 121             },
 122             'playlist_count': 15,
 123         },
 124     ]
 125
 126     def _real_extract(self, url):
 127         course_id = self._match_id(url)
 128         webpage = self._download_webpage(url, course_id)
 129         self._check_if_logged_in(webpage)
 130         course = self._call_api('course', course_id, webpage)
 131
 132         entries = [self.url_result(
 133             urljoin(url, f'{course_id}/{episode["url"]}'), ITProTVIE,
 134             episode['url'], episode.get('title'), url_transparent=True)
 135             for episode in course['episodes']]
 136
 137         return self.playlist_result(
 138             entries, course_id, course.get('name'), course.get('description'))