yt_dlp/extractor/egghead.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     int_or_none,
   5     try_get,
   6     unified_timestamp,
   7     url_or_none,
   8 )
   9
  10
  11 class EggheadBaseIE(InfoExtractor):
  12     def _call_api(self, path, video_id, resource, fatal=True):
  13         return self._download_json(
  14             'https://app.egghead.io/api/v1/' + path,
  15             video_id, f'Downloading {resource} JSON', fatal=fatal)
  16
  17
  18 class EggheadCourseIE(EggheadBaseIE):
  19     IE_DESC = 'egghead.io course'
  20     IE_NAME = 'egghead:course'
  21     _VALID_URL = r'https?://(?:app\.)?egghead\.io/(?:course|playlist)s/(?P<id>[^/?#&]+)'
  22     _TESTS = [{
  23         'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
  24         'playlist_count': 29,
  25         'info_dict': {
  26             'id': '432655',
  27             'title': 'Professor Frisby Introduces Composable Functional JavaScript',
  28             'description': 're:(?s)^This course teaches the ubiquitous.*You\'ll start composing functionality before you know it.$',
  29         },
  30     }, {
  31         'url': 'https://app.egghead.io/playlists/professor-frisby-introduces-composable-functional-javascript',
  32         'only_matching': True,
  33     }]
  34
  35     def _real_extract(self, url):
  36         playlist_id = self._match_id(url)
  37         series_path = 'series/' + playlist_id
  38         lessons = self._call_api(
  39             series_path + '/lessons', playlist_id, 'course lessons')
  40
  41         entries = []
  42         for lesson in lessons:
  43             lesson_url = url_or_none(lesson.get('http_url'))
  44             if not lesson_url:
  45                 continue
  46             lesson_id = lesson.get('id')
  47             if lesson_id:
  48                 lesson_id = str(lesson_id)
  49             entries.append(self.url_result(
  50                 lesson_url, ie=EggheadLessonIE.ie_key(), video_id=lesson_id))
  51
  52         course = self._call_api(
  53             series_path, playlist_id, 'course', False) or {}
  54
  55         playlist_id = course.get('id')
  56         if playlist_id:
  57             playlist_id = str(playlist_id)
  58
  59         return self.playlist_result(
  60             entries, playlist_id, course.get('title'),
  61             course.get('description'))
  62
  63
  64 class EggheadLessonIE(EggheadBaseIE):
  65     IE_DESC = 'egghead.io lesson'
  66     IE_NAME = 'egghead:lesson'
  67     _VALID_URL = r'https?://(?:app\.)?egghead\.io/(?:api/v1/)?lessons/(?P<id>[^/?#&]+)'
  68     _TESTS = [{
  69         'url': 'https://egghead.io/lessons/javascript-linear-data-flow-with-container-style-types-box',
  70         'info_dict': {
  71             'id': '1196',
  72             'display_id': 'javascript-linear-data-flow-with-container-style-types-box',
  73             'ext': 'mp4',
  74             'title': 'Create linear data flow with container style types (Box)',
  75             'description': 'md5:9aa2cdb6f9878ed4c39ec09e85a8150e',
  76             'thumbnail': r're:^https?:.*\.jpg$',
  77             'timestamp': 1481296768,
  78             'upload_date': '20161209',
  79             'duration': 304,
  80             'view_count': 0,
  81             'tags': 'count:2',
  82         },
  83         'params': {
  84             'skip_download': True,
  85         },
  86     }, {
  87         'url': 'https://egghead.io/api/v1/lessons/react-add-redux-to-a-react-application',
  88         'only_matching': True,
  89     }, {
  90         'url': 'https://app.egghead.io/lessons/javascript-linear-data-flow-with-container-style-types-box',
  91         'only_matching': True,
  92     }]
  93
  94     def _real_extract(self, url):
  95         display_id = self._match_id(url)
  96
  97         lesson = self._call_api(
  98             'lessons/' + display_id, display_id, 'lesson')
  99
 100         lesson_id = str(lesson['id'])
 101         title = lesson['title']
 102
 103         formats = []
 104         for _, format_url in lesson['media_urls'].items():
 105             format_url = url_or_none(format_url)
 106             if not format_url:
 107                 continue
 108             ext = determine_ext(format_url)
 109             if ext == 'm3u8':
 110                 formats.extend(self._extract_m3u8_formats(
 111                     format_url, lesson_id, 'mp4', m3u8_id='hls', fatal=False))
 112             elif ext == 'mpd':
 113                 formats.extend(self._extract_mpd_formats(
 114                     format_url, lesson_id, mpd_id='dash', fatal=False))
 115             else:
 116                 formats.append({
 117                     'url': format_url,
 118                 })
 119
 120         return {
 121             'id': lesson_id,
 122             'display_id': display_id,
 123             'title': title,
 124             'description': lesson.get('summary'),
 125             'thumbnail': lesson.get('thumb_nail'),
 126             'timestamp': unified_timestamp(lesson.get('published_at')),
 127             'duration': int_or_none(lesson.get('duration')),
 128             'view_count': int_or_none(lesson.get('plays_count')),
 129             'tags': try_get(lesson, lambda x: x['tag_list'], list),
 130             'series': try_get(
 131                 lesson, lambda x: x['series']['title'], str),
 132             'formats': formats,
 133         }