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