youtube_dl/extractor/lynda.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import ExtractorError
   8
   9
  10 class LyndaIE(InfoExtractor):
  11     IE_NAME = 'lynda'
  12     IE_DESC = 'lynda.com videos'
  13     _VALID_URL = r'https?://www\.lynda\.com/[^/]+/[^/]+/\d+/(\d+)-\d\.html'
  14
  15     _TEST = {
  16         'url': 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
  17         'file': '114408.mp4',
  18         'md5': 'ecfc6862da89489161fb9cd5f5a6fac1',
  19         u"info_dict": {
  20             'title': 'Using the exercise files',
  21             'duration': 68
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         mobj = re.match(self._VALID_URL, url)
  27         video_id = mobj.group(1)
  28
  29         page = self._download_webpage('http://www.lynda.com/ajax/player?videoId=%s&type=video' % video_id,
  30                                       video_id, 'Downloading video JSON')
  31         video_json = json.loads(page)
  32
  33         if 'Status' in video_json and video_json['Status'] == 'NotFound':
  34             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  35
  36         if video_json['HasAccess'] is False:
  37             raise ExtractorError('Video %s is only available for members' % video_id, expected=True)
  38
  39         video_id = video_json['ID']
  40         duration = video_json['DurationInSeconds']
  41         title = video_json['Title']
  42
  43         formats = [{'url': fmt['Url'],
  44                     'ext': fmt['Extension'],
  45                     'width': fmt['Width'],
  46                     'height': fmt['Height'],
  47                     'filesize': fmt['FileSize'],
  48                     'format_id': fmt['Resolution']
  49                     } for fmt in video_json['Formats']]
  50
  51         self._sort_formats(formats)
  52
  53         return {
  54             'id': video_id,
  55             'title': title,
  56             'duration': duration,
  57             'formats': formats
  58         }
  59
  60
  61 class LyndaCourseIE(InfoExtractor):
  62     IE_NAME = 'lynda:course'
  63     IE_DESC = 'lynda.com online courses'
  64
  65     # Course link equals to welcome/introduction video link of same course
  66     # We will recognize it as course link
  67     _VALID_URL = r'https?://(?:www|m)\.lynda\.com/(?P<coursepath>[^/]+/[^/]+/(?P<courseid>\d+))-\d\.html'
  68
  69     def _real_extract(self, url):
  70         mobj = re.match(self._VALID_URL, url)
  71         course_path = mobj.group('coursepath')
  72         course_id = mobj.group('courseid')
  73
  74         page = self._download_webpage('http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
  75                                       course_id, 'Downloading course JSON')
  76         course_json = json.loads(page)
  77
  78         if 'Status' in course_json and course_json['Status'] == 'NotFound':
  79             raise ExtractorError('Course %s does not exist' % course_id, expected=True)
  80
  81         unaccessible_videos = 0
  82         videos = []
  83
  84         for chapter in course_json['Chapters']:
  85             for video in chapter['Videos']:
  86                 if video['HasAccess'] is not True:
  87                     unaccessible_videos += 1
  88                     continue
  89                 videos.append(video['ID'])
  90
  91         if unaccessible_videos > 0:
  92             self._downloader.report_warning('%s videos are only available for members and will not be downloaded' % unaccessible_videos)
  93
  94         entries = [
  95             self.url_result('http://www.lynda.com/%s/%s-4.html' %
  96                             (course_path, video_id),
  97                             'Lynda')
  98             for video_id in videos]
  99
 100         course_title = course_json['Title']
 101
 102         return self.playlist_result(entries, course_id, course_title)