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