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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6
   7 from .common import InfoExtractor
   8 from .brightcove import BrightcoveIE
   9
  10 from ..compat import (
  11     compat_urllib_parse,
  12     compat_urllib_request,
  13 )
  14 from ..utils import (
  15     ExtractorError,
  16     smuggle_url,
  17     std_headers,
  18 )
  19
  20
  21 class SafariBaseIE(InfoExtractor):
  22     _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
  23     _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]+>Sign Out</a>'
  24     _ACCOUNT_CREDENTIALS_HINT = ('Use --username and --password options to '
  25                                  'supply credentials for safaribooksonline.com ')
  26     _NETRC_MACHINE = 'safaribooksonline'
  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 SafariBaseIE.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             raise ExtractorError(
  40                 self._ACCOUNT_CREDENTIALS_HINT,
  41                 expected=True)
  42
  43         headers = std_headers
  44         if 'Referer' not in headers:
  45             headers['Referer'] = self._LOGIN_URL
  46
  47         login_page = self._download_webpage(
  48             self._LOGIN_URL, None,
  49             'Downloading login form')
  50
  51         csrf = self._html_search_regex(
  52             r"<input +type='hidden' +name='csrfmiddlewaretoken' +value='([^']+)' +/>",
  53             login_page, 'csrf token')
  54
  55         login_form = {
  56             'csrfmiddlewaretoken': csrf,
  57             'email': username,
  58             'password1': password,
  59             'login': 'Sign In',
  60             'next': '',
  61         }
  62
  63         request = compat_urllib_request.Request(
  64             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers)
  65         login_page = self._download_webpage(
  66             request, None, 'Logging in as %s' % username)
  67
  68         if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
  69             raise ExtractorError('Login failed; make sure your credentials are correct and '
  70                                  'try again.', expected=True)
  71
  72         self.to_screen('Login successful')
  73
  74
  75 class SafariIE(SafariBaseIE):
  76     IE_NAME = 'safari'
  77     IE_DESC = 'safaribooksonline.com online video'
  78     _VALID_URL = (r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/'
  79                   '(?P<id>\d+)/(?P<part>part\d+)\.html')
  80     _TEST = {
  81         'url': ('https://www.safaribooksonline.com/library/view/'
  82                 'hadoop-fundamentals-livelessons/9780133392838/part00.html'),
  83         'md5': '5b0c4cc1b3c1ba15dda7344085aa5592',
  84         'info_dict': {
  85             'id': '9780133392838',
  86             'ext': 'mp4',
  87             'title': 'Introduction',
  88         }
  89     }
  90
  91     def _real_extract(self, url):
  92         mobj = re.match(self._VALID_URL, url)
  93         part = mobj.group('part')
  94
  95         webpage = self._download_webpage(url, part)
  96         bc_url = BrightcoveIE._extract_brightcove_url(webpage)
  97         if not bc_url:
  98             raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True)
  99
 100         return {
 101             '_type': 'url',
 102             'url': smuggle_url(bc_url, {'Referer': url}),
 103             'ie_key': 'Brightcove'
 104         }
 105
 106
 107 class SafariCourseIE(SafariBaseIE):
 108     IE_NAME = 'safari:course'
 109     IE_DESC = 'safaribooksonline.com online courses'
 110
 111     _VALID_URL = (r'https?://(?:www\.)?safaribooksonline\.com/library/view/'
 112                   '(?P<course_path>[^/]+)/(?P<id>\d+)/?$')
 113
 114     _API_BASE = 'https://www.safaribooksonline.com/api/v1/book'
 115     _API_FORMAT = 'json'
 116
 117     def _real_extract(self, url):
 118         mobj = re.match(self._VALID_URL, url)
 119         course_path = mobj.group('course_path')
 120         course_id = mobj.group('id')
 121
 122         webpage = self._download_webpage(
 123             '%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
 124             course_path, 'Downloading course JSON')
 125
 126         course_json = json.loads(webpage)
 127
 128         if 'chapters' not in course_json:
 129             raise ExtractorError('No chapters found for course %s' % course_id, expected=True)
 130
 131         num_parts = len(course_json['chapters'])
 132         parts = ['%02d' % part for part in range(num_parts)]
 133
 134         entries = [
 135             self.url_result(
 136                 'https://www.safaribooksonline.com/library/view/%s/%s/part%s.html' % (course_path,
 137                                                                                       course_id,
 138                                                                                       part_id),
 139                 'Safari')
 140             for part_id in parts]
 141
 142         course_title = course_json['title']
 143
 144         return self.playlist_result(entries, course_id, course_title)