2 from __future__ import unicode_literals
6 from .common import InfoExtractor
17 class SafariBaseIE(InfoExtractor):
18 _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
19 _NETRC_MACHINE = 'safari'
21 _API_BASE = 'https://www.safaribooksonline.com/api/v1'
26 def _real_initialize(self):
30 (username, password) = self._get_login_info()
34 headers = std_headers.copy()
35 if 'Referer' not in headers:
36 headers['Referer'] = self._LOGIN_URL
38 login_page = self._download_webpage(
39 self._LOGIN_URL, None, 'Downloading login form', headers=headers)
41 def is_logged(webpage):
42 return any(re.search(p, webpage) for p in (
43 r'href=["\']/accounts/logout/', r'>Sign Out<'))
45 if is_logged(login_page):
49 csrf = self._html_search_regex(
50 r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
51 login_page, 'csrf token')
54 'csrfmiddlewaretoken': csrf,
56 'password1': password,
61 request = sanitized_Request(
62 self._LOGIN_URL, urlencode_postdata(login_form), headers=headers)
63 login_page = self._download_webpage(
64 request, None, 'Logging in')
66 if not is_logged(login_page):
68 'Login failed; make sure your credentials are correct and try again.',
74 class SafariIE(SafariBaseIE):
76 IE_DESC = 'safaribooksonline.com online video'
77 _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?#&]+)\.html'
80 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
81 'md5': 'dcc5a425e79f2564148652616af1f2a3',
85 'title': 'Introduction to Hadoop Fundamentals LiveLessons',
86 'timestamp': 1437758058,
87 'upload_date': '20150724',
88 'uploader_id': 'stork',
91 # non-digits in course id
92 'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
93 'only_matching': True,
95 'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html',
96 'only_matching': True,
99 def _real_extract(self, url):
100 mobj = re.match(self._VALID_URL, url)
101 video_id = '%s/%s' % (mobj.group('course_id'), mobj.group('part'))
103 webpage = self._download_webpage(url, video_id)
104 reference_id = self._search_regex(
105 r'data-reference-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
106 webpage, 'kaltura reference id', group='id')
107 partner_id = self._search_regex(
108 r'data-partner-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
109 webpage, 'kaltura widget id', group='id')
110 ui_id = self._search_regex(
111 r'data-ui-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
112 webpage, 'kaltura uiconf id', group='id')
115 'wid': '_%s' % partner_id,
117 'flashvars[referenceId]': reference_id,
121 kaltura_session = self._download_json(
122 '%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id),
123 video_id, 'Downloading kaltura session JSON',
124 'Unable to download kaltura session JSON', fatal=False)
126 session = kaltura_session.get('session')
128 query['flashvars[ks]'] = session
130 return self.url_result(update_url_query(
131 'https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', query),
135 class SafariApiIE(SafariBaseIE):
136 IE_NAME = 'safari:api'
137 _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
140 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
141 'only_matching': True,
143 'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html',
144 'only_matching': True,
147 def _real_extract(self, url):
148 mobj = re.match(self._VALID_URL, url)
149 part = self._download_json(
150 url, '%s/%s' % (mobj.group('course_id'), mobj.group('part')),
151 'Downloading part JSON')
152 return self.url_result(part['web_url'], SafariIE.ie_key())
155 class SafariCourseIE(SafariBaseIE):
156 IE_NAME = 'safari:course'
157 IE_DESC = 'safaribooksonline.com online courses'
159 _VALID_URL = r'''(?x)
162 (?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)|
163 techbus\.safaribooksonline\.com
165 /(?P<id>[^/]+)/?(?:[#?]|$)
169 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
171 'id': '9780133392838',
172 'title': 'Hadoop Fundamentals LiveLessons',
174 'playlist_count': 22,
175 'skip': 'Requires safaribooksonline account credentials',
177 'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
178 'only_matching': True,
180 'url': 'http://techbus.safaribooksonline.com/9780134426365',
181 'only_matching': True,
184 def _real_extract(self, url):
185 course_id = self._match_id(url)
187 course_json = self._download_json(
188 '%s/book/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
189 course_id, 'Downloading course JSON')
191 if 'chapters' not in course_json:
192 raise ExtractorError(
193 'No chapters found for course %s' % course_id, expected=True)
196 self.url_result(chapter, SafariApiIE.ie_key())
197 for chapter in course_json['chapters']]
199 course_title = course_json['title']
201 return self.playlist_result(entries, course_id, course_title)