yt_dlp/extractor/packtpub.py

   1 import json
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     # compat_str,
   6     compat_HTTPError,
   7 )
   8 from ..utils import (
   9     clean_html,
  10     ExtractorError,
  11     # remove_end,
  12     str_or_none,
  13     strip_or_none,
  14     unified_timestamp,
  15     # urljoin,
  16 )
  17
  18
  19 class PacktPubBaseIE(InfoExtractor):
  20     # _PACKT_BASE = 'https://www.packtpub.com'
  21     _STATIC_PRODUCTS_BASE = 'https://static.packt-cdn.com/products/'
  22
  23
  24 class PacktPubIE(PacktPubBaseIE):
  25     _VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>[^/]+)/(?P<id>[^/]+)(?:/(?P<display_id>[^/?&#]+))?'
  26
  27     _TESTS = [{
  28         'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro',
  29         'md5': '1e74bd6cfd45d7d07666f4684ef58f70',
  30         'info_dict': {
  31             'id': '20530',
  32             'ext': 'mp4',
  33             'title': 'Project Intro',
  34             'thumbnail': r're:(?i)^https?://.*\.jpg',
  35             'timestamp': 1490918400,
  36             'upload_date': '20170331',
  37         },
  38     }, {
  39         'url': 'https://subscription.packtpub.com/video/web_development/9781787122215/20528/20530/project-intro',
  40         'only_matching': True,
  41     }, {
  42         'url': 'https://subscription.packtpub.com/video/programming/9781838988906/p1/video1_1/business-card-project',
  43         'only_matching': True,
  44     }]
  45     _NETRC_MACHINE = 'packtpub'
  46     _TOKEN = None
  47
  48     def _perform_login(self, username, password):
  49         try:
  50             self._TOKEN = self._download_json(
  51                 'https://services.packtpub.com/auth-v1/users/tokens', None,
  52                 'Downloading Authorization Token', data=json.dumps({
  53                     'username': username,
  54                     'password': password,
  55                 }).encode())['data']['access']
  56         except ExtractorError as e:
  57             if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401, 404):
  58                 message = self._parse_json(e.cause.read().decode(), None)['message']
  59                 raise ExtractorError(message, expected=True)
  60             raise
  61
  62     def _real_extract(self, url):
  63         course_id, chapter_id, video_id, display_id = self._match_valid_url(url).groups()
  64
  65         headers = {}
  66         if self._TOKEN:
  67             headers['Authorization'] = 'Bearer ' + self._TOKEN
  68         try:
  69             video_url = self._download_json(
  70                 'https://services.packtpub.com/products-v1/products/%s/%s/%s' % (course_id, chapter_id, video_id), video_id,
  71                 'Downloading JSON video', headers=headers)['data']
  72         except ExtractorError as e:
  73             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
  74                 self.raise_login_required('This video is locked')
  75             raise
  76
  77         # TODO: find a better way to avoid duplicating course requests
  78         # metadata = self._download_json(
  79         #     '%s/products/%s/chapters/%s/sections/%s/metadata'
  80         #     % (self._MAPT_REST, course_id, chapter_id, video_id),
  81         #     video_id)['data']
  82
  83         # title = metadata['pageTitle']
  84         # course_title = metadata.get('title')
  85         # if course_title:
  86         #     title = remove_end(title, ' - %s' % course_title)
  87         # timestamp = unified_timestamp(metadata.get('publicationDate'))
  88         # thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath'))
  89
  90         return {
  91             'id': video_id,
  92             'url': video_url,
  93             'title': display_id or video_id,  # title,
  94             # 'thumbnail': thumbnail,
  95             # 'timestamp': timestamp,
  96         }
  97
  98
  99 class PacktPubCourseIE(PacktPubBaseIE):
 100     _VALID_URL = r'(?P<url>https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P<id>\d+))'
 101     _TESTS = [{
 102         'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215',
 103         'info_dict': {
 104             'id': '9781787122215',
 105             'title': 'Learn Nodejs by building 12 projects [Video]',
 106             'description': 'md5:489da8d953f416e51927b60a1c7db0aa',
 107         },
 108         'playlist_count': 90,
 109     }, {
 110         'url': 'https://subscription.packtpub.com/video/web_development/9781787122215',
 111         'only_matching': True,
 112     }]
 113
 114     @classmethod
 115     def suitable(cls, url):
 116         return False if PacktPubIE.suitable(url) else super(
 117             PacktPubCourseIE, cls).suitable(url)
 118
 119     def _real_extract(self, url):
 120         mobj = self._match_valid_url(url)
 121         url, course_id = mobj.group('url', 'id')
 122
 123         course = self._download_json(
 124             self._STATIC_PRODUCTS_BASE + '%s/toc' % course_id, course_id)
 125         metadata = self._download_json(
 126             self._STATIC_PRODUCTS_BASE + '%s/summary' % course_id,
 127             course_id, fatal=False) or {}
 128
 129         entries = []
 130         for chapter_num, chapter in enumerate(course['chapters'], 1):
 131             chapter_id = str_or_none(chapter.get('id'))
 132             sections = chapter.get('sections')
 133             if not chapter_id or not isinstance(sections, list):
 134                 continue
 135             chapter_info = {
 136                 'chapter': chapter.get('title'),
 137                 'chapter_number': chapter_num,
 138                 'chapter_id': chapter_id,
 139             }
 140             for section in sections:
 141                 section_id = str_or_none(section.get('id'))
 142                 if not section_id or section.get('contentType') != 'video':
 143                     continue
 144                 entry = {
 145                     '_type': 'url_transparent',
 146                     'url': '/'.join([url, chapter_id, section_id]),
 147                     'title': strip_or_none(section.get('title')),
 148                     'description': clean_html(section.get('summary')),
 149                     'thumbnail': metadata.get('coverImage'),
 150                     'timestamp': unified_timestamp(metadata.get('publicationDate')),
 151                     'ie_key': PacktPubIE.ie_key(),
 152                 }
 153                 entry.update(chapter_info)
 154                 entries.append(entry)
 155
 156         return self.playlist_result(
 157             entries, course_id, metadata.get('title'),
 158             clean_html(metadata.get('about')))