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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from .brightcove import BrightcoveLegacyIE
   8
   9 from ..utils import (
  10     ExtractorError,
  11     sanitized_Request,
  12     smuggle_url,
  13     std_headers,
  14     urlencode_postdata,
  15 )
  16
  17
  18 class SafariBaseIE(InfoExtractor):
  19     _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
  20     _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>'
  21     _NETRC_MACHINE = 'safari'
  22
  23     _API_BASE = 'https://www.safaribooksonline.com/api/v1/book'
  24     _API_FORMAT = 'json'
  25
  26     LOGGED_IN = False
  27
  28     def _real_initialize(self):
  29         # We only need to log in once for courses or individual videos
  30         if not self.LOGGED_IN:
  31             self._login()
  32             SafariBaseIE.LOGGED_IN = True
  33
  34     def _login(self):
  35         (username, password) = self._get_login_info()
  36         if username is None:
  37             self.raise_login_required('safaribooksonline.com account is required')
  38
  39         headers = std_headers.copy()
  40         if 'Referer' not in headers:
  41             headers['Referer'] = self._LOGIN_URL
  42         login_page_request = sanitized_Request(self._LOGIN_URL, headers=headers)
  43
  44         login_page = self._download_webpage(
  45             login_page_request, None,
  46             'Downloading login form')
  47
  48         csrf = self._html_search_regex(
  49             r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
  50             login_page, 'csrf token')
  51
  52         login_form = {
  53             'csrfmiddlewaretoken': csrf,
  54             'email': username,
  55             'password1': password,
  56             'login': 'Sign In',
  57             'next': '',
  58         }
  59
  60         request = sanitized_Request(
  61             self._LOGIN_URL, urlencode_postdata(login_form), headers=headers)
  62         login_page = self._download_webpage(
  63             request, None, 'Logging in as %s' % username)
  64
  65         if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
  66             raise ExtractorError(
  67                 'Login failed; make sure your credentials are correct and try again.',
  68                 expected=True)
  69
  70         self.to_screen('Login successful')
  71
  72
  73 class SafariIE(SafariBaseIE):
  74     IE_NAME = 'safari'
  75     IE_DESC = 'safaribooksonline.com online video'
  76     _VALID_URL = r'''(?x)https?://
  77                             (?:www\.)?safaribooksonline\.com/
  78                                 (?:
  79                                     library/view/[^/]+|
  80                                     api/v1/book
  81                                 )/
  82                                 (?P<course_id>[^/]+)/
  83                                     (?:chapter(?:-content)?/)?
  84                                 (?P<part>part\d+)\.html
  85     '''
  86
  87     _TESTS = [{
  88         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
  89         'md5': '5b0c4cc1b3c1ba15dda7344085aa5592',
  90         'info_dict': {
  91             'id': '2842601850001',
  92             'ext': 'mp4',
  93             'title': 'Introduction',
  94         },
  95         'skip': 'Requires safaribooksonline account credentials',
  96     }, {
  97         'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
  98         'only_matching': True,
  99     }, {
 100         # non-digits in course id
 101         'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
 102         'only_matching': True,
 103     }]
 104
 105     def _real_extract(self, url):
 106         mobj = re.match(self._VALID_URL, url)
 107         course_id = mobj.group('course_id')
 108         part = mobj.group('part')
 109
 110         webpage = self._download_webpage(
 111             '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part),
 112             part)
 113
 114         bc_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
 115         if not bc_url:
 116             raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True)
 117
 118         return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'BrightcoveLegacy')
 119
 120
 121 class SafariCourseIE(SafariBaseIE):
 122     IE_NAME = 'safari:course'
 123     IE_DESC = 'safaribooksonline.com online courses'
 124
 125     _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>[^/]+)/?(?:[#?]|$)'
 126
 127     _TESTS = [{
 128         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
 129         'info_dict': {
 130             'id': '9780133392838',
 131             'title': 'Hadoop Fundamentals LiveLessons',
 132         },
 133         'playlist_count': 22,
 134         'skip': 'Requires safaribooksonline account credentials',
 135     }, {
 136         'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
 137         'only_matching': True,
 138     }]
 139
 140     def _real_extract(self, url):
 141         course_id = self._match_id(url)
 142
 143         course_json = self._download_json(
 144             '%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
 145             course_id, 'Downloading course JSON')
 146
 147         if 'chapters' not in course_json:
 148             raise ExtractorError(
 149                 'No chapters found for course %s' % course_id, expected=True)
 150
 151         entries = [
 152             self.url_result(chapter, 'Safari')
 153             for chapter in course_json['chapters']]
 154
 155         course_title = course_json['title']
 156
 157         return self.playlist_result(entries, course_id, course_title)