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

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_str,
   9     compat_HTTPError,
  10 )
  11 from ..utils import (
  12     clean_html,
  13     ExtractorError,
  14     remove_end,
  15     strip_or_none,
  16     unified_timestamp,
  17     urljoin,
  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         try:
  49             self._TOKEN = self._download_json(
  50                 self._MAPT_REST + '/users/tokens', None,
  51                 'Downloading Authorization Token', data=json.dumps({
  52                     'email': username,
  53                     'password': password,
  54                 }).encode())['data']['access']
  55         except ExtractorError as e:
  56             if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401, 404):
  57                 message = self._parse_json(e.cause.read().decode(), None)['message']
  58                 raise ExtractorError(message, expected=True)
  59             raise
  60
  61     def _handle_error(self, response):
  62         if response.get('status') != 'success':
  63             raise ExtractorError(
  64                 '% said: %s' % (self.IE_NAME, response['message']),
  65                 expected=True)
  66
  67     def _download_json(self, *args, **kwargs):
  68         response = super(PacktPubIE, self)._download_json(*args, **kwargs)
  69         self._handle_error(response)
  70         return response
  71
  72     def _real_extract(self, url):
  73         mobj = re.match(self._VALID_URL, url)
  74         course_id, chapter_id, video_id = mobj.group(
  75             'course_id', 'chapter_id', 'id')
  76
  77         headers = {}
  78         if self._TOKEN:
  79             headers['Authorization'] = 'Bearer ' + self._TOKEN
  80         video = self._download_json(
  81             '%s/users/me/products/%s/chapters/%s/sections/%s'
  82             % (self._MAPT_REST, course_id, chapter_id, video_id), video_id,
  83             'Downloading JSON video', headers=headers)['data']
  84
  85         content = video.get('content')
  86         if not content:
  87             self.raise_login_required('This video is locked')
  88
  89         video_url = content['file']
  90
  91         metadata = self._download_json(
  92             '%s/products/%s/chapters/%s/sections/%s/metadata'
  93             % (self._MAPT_REST, course_id, chapter_id, video_id),
  94             video_id)['data']
  95
  96         title = metadata['pageTitle']
  97         course_title = metadata.get('title')
  98         if course_title:
  99             title = remove_end(title, ' - %s' % course_title)
 100         timestamp = unified_timestamp(metadata.get('publicationDate'))
 101         thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath'))
 102
 103         return {
 104             'id': video_id,
 105             'url': video_url,
 106             'title': title,
 107             'thumbnail': thumbnail,
 108             'timestamp': timestamp,
 109         }
 110
 111
 112 class PacktPubCourseIE(PacktPubBaseIE):
 113     _VALID_URL = r'(?P<url>https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<id>\d+))'
 114     _TEST = {
 115         'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215',
 116         'info_dict': {
 117             'id': '9781787122215',
 118             'title': 'Learn Nodejs by building 12 projects [Video]',
 119         },
 120         'playlist_count': 90,
 121     }
 122
 123     @classmethod
 124     def suitable(cls, url):
 125         return False if PacktPubIE.suitable(url) else super(
 126             PacktPubCourseIE, cls).suitable(url)
 127
 128     def _real_extract(self, url):
 129         mobj = re.match(self._VALID_URL, url)
 130         url, course_id = mobj.group('url', 'id')
 131
 132         course = self._download_json(
 133             '%s/products/%s/metadata' % (self._MAPT_REST, course_id),
 134             course_id)['data']
 135
 136         entries = []
 137         for chapter_num, chapter in enumerate(course['tableOfContents'], 1):
 138             if chapter.get('type') != 'chapter':
 139                 continue
 140             children = chapter.get('children')
 141             if not isinstance(children, list):
 142                 continue
 143             chapter_info = {
 144                 'chapter': chapter.get('title'),
 145                 'chapter_number': chapter_num,
 146                 'chapter_id': chapter.get('id'),
 147             }
 148             for section in children:
 149                 if section.get('type') != 'section':
 150                     continue
 151                 section_url = section.get('seoUrl')
 152                 if not isinstance(section_url, compat_str):
 153                     continue
 154                 entry = {
 155                     '_type': 'url_transparent',
 156                     'url': urljoin(url + '/', section_url),
 157                     'title': strip_or_none(section.get('title')),
 158                     'description': clean_html(section.get('summary')),
 159                     'ie_key': PacktPubIE.ie_key(),
 160                 }
 161                 entry.update(chapter_info)
 162                 entries.append(entry)
 163
 164         return self.playlist_result(entries, course_id, course.get('title'))