yt_dlp/extractor/egghead.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     determine_ext,
   5     int_or_none,
   6     try_get,
   7     unified_timestamp,
   8     url_or_none,
   9 )
  10
  11
  12 class EggheadBaseIE(InfoExtractor):
  13     def _call_api(self, path, video_id, resource, fatal=True):
  14         return self._download_json(
  15             'https://app.egghead.io/api/v1/' + path,
  16             video_id, 'Downloading %s JSON' % resource, fatal=fatal)
  17
  18
  19 class EggheadCourseIE(EggheadBaseIE):
  20     IE_DESC = 'egghead.io course'
  21     IE_NAME = 'egghead:course'
  22     _VALID_URL = r'https://(?:app\.)?egghead\.io/(?:course|playlist)s/(?P<id>[^/?#&]+)'
  23     _TESTS = [{
  24         'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
  25         'playlist_count': 29,
  26         'info_dict': {
  27             'id': '432655',
  28             'title': 'Professor Frisby Introduces Composable Functional JavaScript',
  29             'description': 're:(?s)^This course teaches the ubiquitous.*You\'ll start composing functionality before you know it.$',
  30         },
  31     }, {
  32         'url': 'https://app.egghead.io/playlists/professor-frisby-introduces-composable-functional-javascript',
  33         'only_matching': True,
  34     }]
  35
  36     def _real_extract(self, url):
  37         playlist_id = self._match_id(url)
  38         series_path = 'series/' + playlist_id
  39         lessons = self._call_api(
  40             series_path + '/lessons', playlist_id, 'course lessons')
  41
  42         entries = []
  43         for lesson in lessons:
  44             lesson_url = url_or_none(lesson.get('http_url'))
  45             if not lesson_url:
  46                 continue
  47             lesson_id = lesson.get('id')
  48             if lesson_id:
  49                 lesson_id = compat_str(lesson_id)
  50             entries.append(self.url_result(
  51                 lesson_url, ie=EggheadLessonIE.ie_key(), video_id=lesson_id))
  52
  53         course = self._call_api(
  54             series_path, playlist_id, 'course', False) or {}
  55
  56         playlist_id = course.get('id')
  57         if playlist_id:
  58             playlist_id = compat_str(playlist_id)
  59
  60         return self.playlist_result(
  61             entries, playlist_id, course.get('title'),
  62             course.get('description'))
  63
  64
  65 class EggheadLessonIE(EggheadBaseIE):
  66     IE_DESC = 'egghead.io lesson'
  67     IE_NAME = 'egghead:lesson'
  68     _VALID_URL = r'https://(?:app\.)?egghead\.io/(?:api/v1/)?lessons/(?P<id>[^/?#&]+)'
  69     _TESTS = [{
  70         'url': 'https://egghead.io/lessons/javascript-linear-data-flow-with-container-style-types-box',
  71         'info_dict': {
  72             'id': '1196',
  73             'display_id': 'javascript-linear-data-flow-with-container-style-types-box',
  74             'ext': 'mp4',
  75             'title': 'Create linear data flow with container style types (Box)',
  76             'description': 'md5:9aa2cdb6f9878ed4c39ec09e85a8150e',
  77             'thumbnail': r're:^https?:.*\.jpg$',
  78             'timestamp': 1481296768,
  79             'upload_date': '20161209',
  80             'duration': 304,
  81             'view_count': 0,
  82             'tags': 'count:2',
  83         },
  84         'params': {
  85             'skip_download': True,
  86         },
  87     }, {
  88         'url': 'https://egghead.io/api/v1/lessons/react-add-redux-to-a-react-application',
  89         'only_matching': True,
  90     }, {
  91         'url': 'https://app.egghead.io/lessons/javascript-linear-data-flow-with-container-style-types-box',
  92         'only_matching': True,
  93     }]
  94
  95     def _real_extract(self, url):
  96         display_id = self._match_id(url)
  97
  98         lesson = self._call_api(
  99             'lessons/' + display_id, display_id, 'lesson')
 100
 101         lesson_id = compat_str(lesson['id'])
 102         title = lesson['title']
 103
 104         formats = []
 105         for _, format_url in lesson['media_urls'].items():
 106             format_url = url_or_none(format_url)
 107             if not format_url:
 108                 continue
 109             ext = determine_ext(format_url)
 110             if ext == 'm3u8':
 111                 formats.extend(self._extract_m3u8_formats(
 112                     format_url, lesson_id, 'mp4', m3u8_id='hls', fatal=False))
 113             elif ext == 'mpd':
 114                 formats.extend(self._extract_mpd_formats(
 115                     format_url, lesson_id, mpd_id='dash', fatal=False))
 116             else:
 117                 formats.append({
 118                     'url': format_url,
 119                 })
 120
 121         return {
 122             'id': lesson_id,
 123             'display_id': display_id,
 124             'title': title,
 125             'description': lesson.get('summary'),
 126             'thumbnail': lesson.get('thumb_nail'),
 127             'timestamp': unified_timestamp(lesson.get('published_at')),
 128             'duration': int_or_none(lesson.get('duration')),
 129             'view_count': int_or_none(lesson.get('plays_count')),
 130             'tags': try_get(lesson, lambda x: x['tag_list'], list),
 131             'series': try_get(
 132                 lesson, lambda x: x['series']['title'], compat_str),
 133             'formats': formats,
 134         }