_ Git - youtube-dl/blob - youtube_dl/extractor/packtpub.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     clean_html,
   9     ExtractorError,
  10     remove_end,
  11     strip_or_none,
  12     unified_timestamp,
  13     urljoin,
  14 )
  15
  16
  17 class PacktPubBaseIE(InfoExtractor):
  18     _PACKT_BASE = 'https://www.packtpub.com'
  19     _MAPT_REST = '%s/mapt-rest' % _PACKT_BASE
  20
  21
  22 class PacktPubIE(PacktPubBaseIE):
  23     _VALID_URL = r'https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>\d+)/(?P<id>\d+)'
  24
  25     _TEST = {
  26         'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro',
  27         'md5': '1e74bd6cfd45d7d07666f4684ef58f70',
  28         'info_dict': {
  29             'id': '20530',
  30             'ext': 'mp4',
  31             'title': 'Project Intro',
  32             'thumbnail': r're:(?i)^https?://.*\.jpg',
  33             'timestamp': 1490918400,
  34             'upload_date': '20170331',
  35         },
  36     }
  37
  38     def _handle_error(self, response):
  39         if response.get('status') != 'success':
  40             raise ExtractorError(
  41                 '% said: %s' % (self.IE_NAME, response['message']),
  42                 expected=True)
  43
  44     def _download_json(self, *args, **kwargs):
  45         response = super(PacktPubIE, self)._download_json(*args, **kwargs)
  46         self._handle_error(response)
  47         return response
  48
  49     def _real_extract(self, url):
  50         mobj = re.match(self._VALID_URL, url)
  51         course_id, chapter_id, video_id = mobj.group(
  52             'course_id', 'chapter_id', 'id')
  53
  54         video = self._download_json(
  55             '%s/users/me/products/%s/chapters/%s/sections/%s'
  56             % (self._MAPT_REST, course_id, chapter_id, video_id), video_id,
  57             'Downloading JSON video')['data']
  58
  59         content = video.get('content')
  60         if not content:
  61             raise ExtractorError('This video is locked', expected=True)
  62
  63         video_url = content['file']
  64
  65         metadata = self._download_json(
  66             '%s/products/%s/chapters/%s/sections/%s/metadata'
  67             % (self._MAPT_REST, course_id, chapter_id, video_id),
  68             video_id)['data']
  69
  70         title = metadata['pageTitle']
  71         course_title = metadata.get('title')
  72         if course_title:
  73             title = remove_end(title, ' - %s' % course_title)
  74         timestamp = unified_timestamp(metadata.get('publicationDate'))
  75         thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath'))
  76
  77         return {
  78             'id': video_id,
  79             'url': video_url,
  80             'title': title,
  81             'thumbnail': thumbnail,
  82             'timestamp': timestamp,
  83         }
  84
  85
  86 class PacktPubCourseIE(PacktPubBaseIE):
  87     _VALID_URL = r'(?P<url>https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<id>\d+))'
  88     _TEST = {
  89         'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215',
  90         'info_dict': {
  91             'id': '9781787122215',
  92             'title': 'Learn Nodejs by building 12 projects [Video]',
  93         },
  94         'playlist_count': 90,
  95     }
  96
  97     @classmethod
  98     def suitable(cls, url):
  99         return False if PacktPubIE.suitable(url) else super(
 100             PacktPubCourseIE, cls).suitable(url)
 101
 102     def _real_extract(self, url):
 103         mobj = re.match(self._VALID_URL, url)
 104         url, course_id = mobj.group('url', 'id')
 105
 106         course = self._download_json(
 107             '%s/products/%s/metadata' % (self._MAPT_REST, course_id),
 108             course_id)['data']
 109
 110         entries = []
 111         for chapter_num, chapter in enumerate(course['tableOfContents'], 1):
 112             if chapter.get('type') != 'chapter':
 113                 continue
 114             children = chapter.get('children')
 115             if not isinstance(children, list):
 116                 continue
 117             chapter_info = {
 118                 'chapter': chapter.get('title'),
 119                 'chapter_number': chapter_num,
 120                 'chapter_id': chapter.get('id'),
 121             }
 122             for section in children:
 123                 if section.get('type') != 'section':
 124                     continue
 125                 section_url = section.get('seoUrl')
 126                 if not isinstance(section_url, compat_str):
 127                     continue
 128                 entry = {
 129                     '_type': 'url_transparent',
 130                     'url': urljoin(url + '/', section_url),
 131                     'title': strip_or_none(section.get('title')),
 132                     'description': clean_html(section.get('summary')),
 133                     'ie_key': PacktPubIE.ie_key(),
 134                 }
 135                 entry.update(chapter_info)
 136                 entries.append(entry)
 137
 138         return self.playlist_result(entries, course_id, course.get('title'))