yt_dlp/extractor/itprotv.py

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