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