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