yt_dlp/extractor/egghead.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str
   6 from ..utils import (
   7     determine_ext,
   8     int_or_none,
   9     try_get,
  10     unified_timestamp,
  11     url_or_none,
  12 )
  13
  14
  15 class EggheadBaseIE(InfoExtractor):
  16     def _call_api(self, path, video_id, resource, fatal=True):
  17         return self._download_json(
  18             'https://app.egghead.io/api/v1/' + path,
  19             video_id, 'Downloading %s JSON' % resource, fatal=fatal)
  20
  21
  22 class EggheadCourseIE(EggheadBaseIE):
  23     IE_DESC = 'egghead.io course'
  24     IE_NAME = 'egghead:course'
  25     _VALID_URL = r'https://(?:app\.)?egghead\.io/(?:course|playlist)s/(?P<id>[^/?#&]+)'
  26     _TESTS = [{
  27         'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
  28         'playlist_count': 29,
  29         'info_dict': {
  30             'id': '432655',
  31             'title': 'Professor Frisby Introduces Composable Functional JavaScript',
  32             'description': 're:(?s)^This course teaches the ubiquitous.*You\'ll start composing functionality before you know it.$',
  33         },
  34     }, {
  35         'url': 'https://app.egghead.io/playlists/professor-frisby-introduces-composable-functional-javascript',
  36         'only_matching': True,
  37     }]
  38
  39     def _real_extract(self, url):
  40         playlist_id = self._match_id(url)
  41         series_path = 'series/' + playlist_id
  42         lessons = self._call_api(
  43             series_path + '/lessons', playlist_id, 'course lessons')
  44
  45         entries = []
  46         for lesson in lessons:
  47             lesson_url = url_or_none(lesson.get('http_url'))
  48             if not lesson_url:
  49                 continue
  50             lesson_id = lesson.get('id')
  51             if lesson_id:
  52                 lesson_id = compat_str(lesson_id)
  53             entries.append(self.url_result(
  54                 lesson_url, ie=EggheadLessonIE.ie_key(), video_id=lesson_id))
  55
  56         course = self._call_api(
  57             series_path, playlist_id, 'course', False) or {}
  58
  59         playlist_id = course.get('id')
  60         if playlist_id:
  61             playlist_id = compat_str(playlist_id)
  62
  63         return self.playlist_result(
  64             entries, playlist_id, course.get('title'),
  65             course.get('description'))
  66
  67
  68 class EggheadLessonIE(EggheadBaseIE):
  69     IE_DESC = 'egghead.io lesson'
  70     IE_NAME = 'egghead:lesson'
  71     _VALID_URL = r'https://(?:app\.)?egghead\.io/(?:api/v1/)?lessons/(?P<id>[^/?#&]+)'
  72     _TESTS = [{
  73         'url': 'https://egghead.io/lessons/javascript-linear-data-flow-with-container-style-types-box',
  74         'info_dict': {
  75             'id': '1196',
  76             'display_id': 'javascript-linear-data-flow-with-container-style-types-box',
  77             'ext': 'mp4',
  78             'title': 'Create linear data flow with container style types (Box)',
  79             'description': 'md5:9aa2cdb6f9878ed4c39ec09e85a8150e',
  80             'thumbnail': r're:^https?:.*\.jpg$',
  81             'timestamp': 1481296768,
  82             'upload_date': '20161209',
  83             'duration': 304,
  84             'view_count': 0,
  85             'tags': 'count:2',
  86         },
  87         'params': {
  88             'skip_download': True,
  89             'format': 'bestvideo',
  90         },
  91     }, {
  92         'url': 'https://egghead.io/api/v1/lessons/react-add-redux-to-a-react-application',
  93         'only_matching': True,
  94     }, {
  95         'url': 'https://app.egghead.io/lessons/javascript-linear-data-flow-with-container-style-types-box',
  96         'only_matching': True,
  97     }]
  98
  99     def _real_extract(self, url):
 100         display_id = self._match_id(url)
 101
 102         lesson = self._call_api(
 103             'lessons/' + display_id, display_id, 'lesson')
 104
 105         lesson_id = compat_str(lesson['id'])
 106         title = lesson['title']
 107
 108         formats = []
 109         for _, format_url in lesson['media_urls'].items():
 110             format_url = url_or_none(format_url)
 111             if not format_url:
 112                 continue
 113             ext = determine_ext(format_url)
 114             if ext == 'm3u8':
 115                 formats.extend(self._extract_m3u8_formats(
 116                     format_url, lesson_id, 'mp4', m3u8_id='hls', fatal=False))
 117             elif ext == 'mpd':
 118                 formats.extend(self._extract_mpd_formats(
 119                     format_url, lesson_id, mpd_id='dash', fatal=False))
 120             else:
 121                 formats.append({
 122                     'url': format_url,
 123                 })
 124         self._sort_formats(formats)
 125
 126         return {
 127             'id': lesson_id,
 128             'display_id': display_id,
 129             'title': title,
 130             'description': lesson.get('summary'),
 131             'thumbnail': lesson.get('thumb_nail'),
 132             'timestamp': unified_timestamp(lesson.get('published_at')),
 133             'duration': int_or_none(lesson.get('duration')),
 134             'view_count': int_or_none(lesson.get('plays_count')),
 135             'tags': try_get(lesson, lambda x: x['tag_list'], list),
 136             'series': try_get(
 137                 lesson, lambda x: x['series']['title'], compat_str),
 138             'formats': formats,
 139         }