Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/raywenderlich.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .vimeo import VimeoIE
   7 from ..utils import (
   8     extract_attributes,
   9     ExtractorError,
  10     smuggle_url,
  11     unsmuggle_url,
  12     urljoin,
  13 )
  14
  15
  16 class RayWenderlichIE(InfoExtractor):
  17     _VALID_URL = r'https?://videos\.raywenderlich\.com/courses/(?P<course_id>[^/]+)/lessons/(?P<id>\d+)'
  18
  19     _TESTS = [{
  20         'url': 'https://videos.raywenderlich.com/courses/105-testing-in-ios/lessons/1',
  21         'info_dict': {
  22             'id': '248377018',
  23             'ext': 'mp4',
  24             'title': 'Testing In iOS Episode 1: Introduction',
  25             'duration': 133,
  26             'uploader': 'Ray Wenderlich',
  27             'uploader_id': 'user3304672',
  28         },
  29         'params': {
  30             'noplaylist': True,
  31             'skip_download': True,
  32         },
  33         'add_ie': [VimeoIE.ie_key()],
  34         'expected_warnings': ['HTTP Error 403: Forbidden'],
  35     }, {
  36         'url': 'https://videos.raywenderlich.com/courses/105-testing-in-ios/lessons/1',
  37         'info_dict': {
  38             'title': 'Testing in iOS',
  39             'id': '105-testing-in-ios',
  40         },
  41         'params': {
  42             'noplaylist': False,
  43         },
  44         'playlist_count': 29,
  45     }]
  46
  47     def _real_extract(self, url):
  48         url, smuggled_data = unsmuggle_url(url, {})
  49
  50         mobj = re.match(self._VALID_URL, url)
  51         course_id, lesson_id = mobj.group('course_id', 'id')
  52         video_id = '%s/%s' % (course_id, lesson_id)
  53
  54         webpage = self._download_webpage(url, video_id)
  55
  56         no_playlist = self._downloader.params.get('noplaylist')
  57         if no_playlist or smuggled_data.get('force_video', False):
  58             if no_playlist:
  59                 self.to_screen(
  60                     'Downloading just video %s because of --no-playlist'
  61                     % video_id)
  62             if '>Subscribe to unlock' in webpage:
  63                 raise ExtractorError(
  64                     'This content is only available for subscribers',
  65                     expected=True)
  66             vimeo_id = self._search_regex(
  67                 r'data-vimeo-id=["\'](\d+)', webpage, 'video id')
  68             return self.url_result(
  69                 VimeoIE._smuggle_referrer(
  70                     'https://player.vimeo.com/video/%s' % vimeo_id, url),
  71                 ie=VimeoIE.ie_key(), video_id=vimeo_id)
  72
  73         self.to_screen(
  74             'Downloading playlist %s - add --no-playlist to just download video'
  75             % course_id)
  76
  77         lesson_ids = set((lesson_id, ))
  78         for lesson in re.findall(
  79                 r'(<a[^>]+\bclass=["\']lesson-link[^>]+>)', webpage):
  80             attrs = extract_attributes(lesson)
  81             if not attrs:
  82                 continue
  83             lesson_url = attrs.get('href')
  84             if not lesson_url:
  85                 continue
  86             lesson_id = self._search_regex(
  87                 r'/lessons/(\d+)', lesson_url, 'lesson id', default=None)
  88             if not lesson_id:
  89                 continue
  90             lesson_ids.add(lesson_id)
  91
  92         entries = []
  93         for lesson_id in sorted(lesson_ids):
  94             entries.append(self.url_result(
  95                 smuggle_url(urljoin(url, lesson_id), {'force_video': True}),
  96                 ie=RayWenderlichIE.ie_key()))
  97
  98         title = self._search_regex(
  99             r'class=["\']course-title[^>]+>([^<]+)', webpage, 'course title',
 100             default=None)
 101
 102         return self.playlist_result(entries, course_id, title)