_ 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 (
   7     compat_str,
   8     compat_HTTPError,
   9 )
  10 from ..utils import (
  11     clean_html,
  12     ExtractorError,
  13     remove_end,
  14     strip_or_none,
  15     unified_timestamp,
  16     urljoin,
  17     urlencode_postdata,
  18 )
  19
  20
  21 class PacktPubBaseIE(InfoExtractor):
  22     _PACKT_BASE = 'https://www.packtpub.com'
  23     _MAPT_REST = '%s/mapt-rest' % _PACKT_BASE
  24
  25
  26 class PacktPubIE(PacktPubBaseIE):
  27     _VALID_URL = r'https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>\d+)/(?P<id>\d+)'
  28
  29     _TEST = {
  30         'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro',
  31         'md5': '1e74bd6cfd45d7d07666f4684ef58f70',
  32         'info_dict': {
  33             'id': '20530',
  34             'ext': 'mp4',
  35             'title': 'Project Intro',
  36             'thumbnail': r're:(?i)^https?://.*\.jpg',
  37             'timestamp': 1490918400,
  38             'upload_date': '20170331',
  39         },
  40     }
  41     _NETRC_MACHINE = 'packtpub'
  42     _TOKEN = None
  43
  44     def _real_initialize(self):
  45         (username, password) = self._get_login_info()
  46         if username is None:
  47             return
  48         webpage = self._download_webpage(self._PACKT_BASE, None)
  49         login_form = self._form_hidden_inputs(
  50             'packt-user-login-form', webpage)
  51         login_form.update({
  52             'email': username,
  53             'password': password,
  54         })
  55         self._download_webpage(
  56             self._PACKT_BASE, None, 'Logging in as %s' % username,
  57             data=urlencode_postdata(login_form))
  58         try:
  59             self._TOKEN = self._download_json(
  60                 '%s/users/tokens/sessions' % self._MAPT_REST, None,
  61                 'Downloading Authorization Token')['data']['token']
  62         except ExtractorError as e:
  63             if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 404):
  64                 message = self._parse_json(e.cause.read().decode(), None)['message']
  65                 raise ExtractorError(message, expected=True)
  66             raise
  67
  68     def _handle_error(self, response):
  69         if response.get('status') != 'success':
  70             raise ExtractorError(
  71                 '% said: %s' % (self.IE_NAME, response['message']),
  72                 expected=True)
  73
  74     def _download_json(self, *args, **kwargs):
  75         response = super(PacktPubIE, self)._download_json(*args, **kwargs)
  76         self._handle_error(response)
  77         return response
  78
  79     def _real_extract(self, url):
  80         mobj = re.match(self._VALID_URL, url)
  81         course_id, chapter_id, video_id = mobj.group(
  82             'course_id', 'chapter_id', 'id')
  83
  84         headers = {}
  85         if self._TOKEN:
  86             headers['Authorization'] = self._TOKEN
  87         video = self._download_json(
  88             '%s/users/me/products/%s/chapters/%s/sections/%s'
  89             % (self._MAPT_REST, course_id, chapter_id, video_id), video_id,
  90             'Downloading JSON video', headers=headers)['data']
  91
  92         content = video.get('content')
  93         if not content:
  94             self.raise_login_required('This video is locked')
  95
  96         video_url = content['file']
  97
  98         metadata = self._download_json(
  99             '%s/products/%s/chapters/%s/sections/%s/metadata'
 100             % (self._MAPT_REST, course_id, chapter_id, video_id),
 101             video_id)['data']
 102
 103         title = metadata['pageTitle']
 104         course_title = metadata.get('title')
 105         if course_title:
 106             title = remove_end(title, ' - %s' % course_title)
 107         timestamp = unified_timestamp(metadata.get('publicationDate'))
 108         thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath'))
 109
 110         return {
 111             'id': video_id,
 112             'url': video_url,
 113             'title': title,
 114             'thumbnail': thumbnail,
 115             'timestamp': timestamp,
 116         }
 117
 118
 119 class PacktPubCourseIE(PacktPubBaseIE):
 120     _VALID_URL = r'(?P<url>https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<id>\d+))'
 121     _TEST = {
 122         'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215',
 123         'info_dict': {
 124             'id': '9781787122215',
 125             'title': 'Learn Nodejs by building 12 projects [Video]',
 126         },
 127         'playlist_count': 90,
 128     }
 129
 130     @classmethod
 131     def suitable(cls, url):
 132         return False if PacktPubIE.suitable(url) else super(
 133             PacktPubCourseIE, cls).suitable(url)
 134
 135     def _real_extract(self, url):
 136         mobj = re.match(self._VALID_URL, url)
 137         url, course_id = mobj.group('url', 'id')
 138
 139         course = self._download_json(
 140             '%s/products/%s/metadata' % (self._MAPT_REST, course_id),
 141             course_id)['data']
 142
 143         entries = []
 144         for chapter_num, chapter in enumerate(course['tableOfContents'], 1):
 145             if chapter.get('type') != 'chapter':
 146                 continue
 147             children = chapter.get('children')
 148             if not isinstance(children, list):
 149                 continue
 150             chapter_info = {
 151                 'chapter': chapter.get('title'),
 152                 'chapter_number': chapter_num,
 153                 'chapter_id': chapter.get('id'),
 154             }
 155             for section in children:
 156                 if section.get('type') != 'section':
 157                     continue
 158                 section_url = section.get('seoUrl')
 159                 if not isinstance(section_url, compat_str):
 160                     continue
 161                 entry = {
 162                     '_type': 'url_transparent',
 163                     'url': urljoin(url + '/', section_url),
 164                     'title': strip_or_none(section.get('title')),
 165                     'description': clean_html(section.get('summary')),
 166                     'ie_key': PacktPubIE.ie_key(),
 167                 }
 168                 entry.update(chapter_info)
 169                 entries.append(entry)
 170
 171         return self.playlist_result(entries, course_id, course.get('title'))