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 BrightcoveIE
   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     _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to supply credentials for safaribooksonline.com'
  24     _NETRC_MACHINE = 'safari'
  25
  26     _API_BASE = 'https://www.safaribooksonline.com/api/v1/book'
  27     _API_FORMAT = 'json'
  28
  29     LOGGED_IN = False
  30
  31     def _real_initialize(self):
  32         # We only need to log in once for courses or individual videos
  33         if not self.LOGGED_IN:
  34             self._login()
  35             SafariBaseIE.LOGGED_IN = True
  36
  37     def _login(self):
  38         (username, password) = self._get_login_info()
  39         if username is None:
  40             raise ExtractorError(
  41                 self._ACCOUNT_CREDENTIALS_HINT,
  42                 expected=True)
  43
  44         headers = std_headers
  45         if 'Referer' not in headers:
  46             headers['Referer'] = self._LOGIN_URL
  47
  48         login_page = self._download_webpage(
  49             self._LOGIN_URL, None,
  50             'Downloading login form')
  51
  52         csrf = self._html_search_regex(
  53             r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
  54             login_page, 'csrf token')
  55
  56         login_form = {
  57             'csrfmiddlewaretoken': csrf,
  58             'email': username,
  59             'password1': password,
  60             'login': 'Sign In',
  61             'next': '',
  62         }
  63
  64         request = compat_urllib_request.Request(
  65             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers)
  66         login_page = self._download_webpage(
  67             request, None, 'Logging in as %s' % username)
  68
  69         if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
  70             raise ExtractorError(
  71                 'Login failed; make sure your credentials are correct and try again.',
  72                 expected=True)
  73
  74         self.to_screen('Login successful')
  75
  76
  77 class SafariIE(SafariBaseIE):
  78     IE_NAME = 'safari'
  79     IE_DESC = 'safaribooksonline.com online video'
  80     _VALID_URL = r'''(?x)https?://
  81                             (?:www\.)?safaribooksonline\.com/
  82                                 (?:
  83                                     library/view/[^/]+|
  84                                     api/v1/book
  85                                 )/
  86                                 (?P<course_id>[^/]+)/
  87                                     (?:chapter(?:-content)?/)?
  88                                 (?P<part>part\d+)\.html
  89     '''
  90
  91     _TESTS = [{
  92         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
  93         'md5': '5b0c4cc1b3c1ba15dda7344085aa5592',
  94         'info_dict': {
  95             'id': '2842601850001',
  96             'ext': 'mp4',
  97             'title': 'Introduction',
  98         },
  99         'skip': 'Requires safaribooksonline account credentials',
 100     }, {
 101         'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
 102         'only_matching': True,
 103     }, {
 104         # non-digits in course id
 105         'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
 106         'only_matching': True,
 107     }]
 108
 109     def _real_extract(self, url):
 110         mobj = re.match(self._VALID_URL, url)
 111         course_id = mobj.group('course_id')
 112         part = mobj.group('part')
 113
 114         webpage = self._download_webpage(
 115             '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part),
 116             part)
 117
 118         bc_url = BrightcoveIE._extract_brightcove_url(webpage)
 119         if not bc_url:
 120             raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True)
 121
 122         return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'Brightcove')
 123
 124
 125 class SafariCourseIE(SafariBaseIE):
 126     IE_NAME = 'safari:course'
 127     IE_DESC = 'safaribooksonline.com online courses'
 128
 129     _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>[^/]+)/?(?:[#?]|$)'
 130
 131     _TESTS = [{
 132         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
 133         'info_dict': {
 134             'id': '9780133392838',
 135             'title': 'Hadoop Fundamentals LiveLessons',
 136         },
 137         'playlist_count': 22,
 138         'skip': 'Requires safaribooksonline account credentials',
 139     }, {
 140         'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
 141         'only_matching': True,
 142     }]
 143
 144     def _real_extract(self, url):
 145         course_id = self._match_id(url)
 146
 147         course_json = self._download_json(
 148             '%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
 149             course_id, 'Downloading course JSON')
 150
 151         if 'chapters' not in course_json:
 152             raise ExtractorError(
 153                 'No chapters found for course %s' % course_id, expected=True)
 154
 155         entries = [
 156             self.url_result(chapter, 'Safari')
 157             for chapter in course_json['chapters']]
 158
 159         course_title = course_json['title']
 160
 161         return self.playlist_result(entries, course_id, course_title)