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://egghead\.io/courses/(?P<id>[^/?#&]+)'
  26     _TEST = {
  27         'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
  28         'playlist_count': 29,
  29         'info_dict': {
  30             'id': '72',
  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.$',
  33         },
  34     }
  35
  36     def _real_extract(self, url):
  37         playlist_id = self._match_id(url)
  38         series_path = 'series/' + playlist_id
  39         lessons = self._call_api(
  40             series_path + '/lessons', playlist_id, 'course lessons')
  41
  42         entries = []
  43         for lesson in lessons:
  44             lesson_url = url_or_none(lesson.get('http_url'))
  45             if not lesson_url:
  46                 continue
  47             lesson_id = lesson.get('id')
  48             if lesson_id:
  49                 lesson_id = compat_str(lesson_id)
  50             entries.append(self.url_result(
  51                 lesson_url, ie=EggheadLessonIE.ie_key(), video_id=lesson_id))
  52
  53         course = self._call_api(
  54             series_path, playlist_id, 'course', False) or {}
  55
  56         playlist_id = course.get('id')
  57         if playlist_id:
  58             playlist_id = compat_str(playlist_id)
  59
  60         return self.playlist_result(
  61             entries, playlist_id, course.get('title'),
  62             course.get('description'))
  63
  64
  65 class EggheadLessonIE(EggheadBaseIE):
  66     IE_DESC = 'egghead.io lesson'
  67     IE_NAME = 'egghead:lesson'
  68     _VALID_URL = r'https://egghead\.io/(?:api/v1/)?lessons/(?P<id>[^/?#&]+)'
  69     _TESTS = [{
  70         'url': 'https://egghead.io/lessons/javascript-linear-data-flow-with-container-style-types-box',
  71         'info_dict': {
  72             'id': '1196',
  73             'display_id': 'javascript-linear-data-flow-with-container-style-types-box',
  74             'ext': 'mp4',
  75             'title': 'Create linear data flow with container style types (Box)',
  76             'description': 'md5:9aa2cdb6f9878ed4c39ec09e85a8150e',
  77             'thumbnail': r're:^https?:.*\.jpg$',
  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             'format': 'bestvideo',
  87         },
  88     }, {
  89         'url': 'https://egghead.io/api/v1/lessons/react-add-redux-to-a-react-application',
  90         'only_matching': True,
  91     }]
  92
  93     def _real_extract(self, url):
  94         display_id = self._match_id(url)
  95
  96         lesson = self._call_api(
  97             'lessons/' + display_id, display_id, 'lesson')
  98
  99         lesson_id = compat_str(lesson['id'])
 100         title = lesson['title']
 101
 102         formats = []
 103         for _, format_url in lesson['media_urls'].items():
 104             format_url = url_or_none(format_url)
 105             if not format_url:
 106                 continue
 107             ext = determine_ext(format_url)
 108             if ext == 'm3u8':
 109                 formats.extend(self._extract_m3u8_formats(
 110                     format_url, lesson_id, 'mp4', m3u8_id='hls', fatal=False))
 111             elif ext == 'mpd':
 112                 formats.extend(self._extract_mpd_formats(
 113                     format_url, lesson_id, mpd_id='dash', fatal=False))
 114             else:
 115                 formats.append({
 116                     'url': format_url,
 117                 })
 118         self._sort_formats(formats)
 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'], compat_str),
 132             'formats': formats,
 133         }