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