2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
19 class SafariBaseIE(InfoExtractor
):
20 _LOGIN_URL
= 'https://learning.oreilly.com/accounts/login/'
21 _NETRC_MACHINE
= 'safari'
23 _API_BASE
= 'https://learning.oreilly.com/api/v1'
28 def _real_initialize(self
):
32 username
, password
= self
._get
_login
_info
()
36 _
, urlh
= self
._download
_webpage
_handle
(
37 'https://learning.oreilly.com/accounts/login-check/', None,
38 'Downloading login page')
41 return 'learning.oreilly.com/home/' in urlh
.geturl()
47 redirect_url
= urlh
.geturl()
48 parsed_url
= compat_urlparse
.urlparse(redirect_url
)
49 qs
= compat_parse_qs(parsed_url
.query
)
50 next_uri
= compat_urlparse
.urljoin(
51 'https://api.oreilly.com', qs
['next'][0])
53 auth
, urlh
= self
._download
_json
_handle
(
54 'https://www.oreilly.com/member/auth/login/', None, 'Logging in',
58 'redirect_uri': next_uri
,
59 }).encode(), headers
={
60 'Content-Type': 'application/json',
61 'Referer': redirect_url
,
62 }, expected_status
=400)
64 credentials
= auth
.get('credentials')
65 if (not auth
.get('logged_in') and not auth
.get('redirect_uri')
68 'Unable to login: %s' % credentials
, expected
=True)
70 # oreilly serves two same instances of the following cookies
71 # in Set-Cookie header and expects first one to be actually set
72 for cookie
in ('groot_sessionid', 'orm-jwt', 'orm-rt'):
73 self
._apply
_first
_set
_cookie
_header
(urlh
, cookie
)
75 _
, urlh
= self
._download
_webpage
_handle
(
76 auth
.get('redirect_uri') or next_uri
, None, 'Completing login',)
82 raise ExtractorError('Unable to log in')
85 class SafariIE(SafariBaseIE
):
87 IE_DESC
= 'safaribooksonline.com online video'
90 (?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/
92 library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?\#&]+)\.html|
93 videos/[^/]+/[^/]+/(?P<reference_id>[^-]+-[^/?\#&]+)
98 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
99 'md5': 'dcc5a425e79f2564148652616af1f2a3',
103 'title': 'Introduction to Hadoop Fundamentals LiveLessons',
104 'timestamp': 1437758058,
105 'upload_date': '20150724',
106 'uploader_id': 'stork',
109 # non-digits in course id
110 'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
111 'only_matching': True,
113 'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html',
114 'only_matching': True,
116 'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314/9780134217314-PYMC_13_00',
117 'only_matching': True,
119 'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838/9780133392838-00_SeriesIntro',
120 'only_matching': True,
122 'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/00_SeriesIntro.html',
123 'only_matching': True,
126 _PARTNER_ID
= '1926081'
127 _UICONF_ID
= '29375172'
129 def _real_extract(self
, url
):
130 mobj
= self
._match
_valid
_url
(url
)
132 reference_id
= mobj
.group('reference_id')
134 video_id
= reference_id
135 partner_id
= self
._PARTNER
_ID
136 ui_id
= self
._UICONF
_ID
138 video_id
= '%s-%s' % (mobj
.group('course_id'), mobj
.group('part'))
140 webpage
, urlh
= self
._download
_webpage
_handle
(url
, video_id
)
142 mobj
= re
.match(self
._VALID
_URL
, urlh
.geturl())
143 reference_id
= mobj
.group('reference_id')
145 reference_id
= self
._search
_regex
(
146 r
'data-reference-id=(["\'])(?P
<id>(?
:(?
!\
1).)+)\
1',
147 webpage, 'kaltura reference
id', group='id')
148 partner_id = self._search_regex(
149 r'data
-partner
-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
150 webpage, 'kaltura widget id', default=self._PARTNER_ID,
152 ui_id = self._search_regex(
153 r'data-ui-id=(["\'])(?P
<id>(?
:(?
!\
1).)+)\
1',
154 webpage, 'kaltura uiconf
id', default=self._UICONF_ID,
158 'wid
': '_
%s' % partner_id,
160 'flashvars
[referenceId
]': reference_id,
164 kaltura_session = self._download_json(
165 '%s/player
/kaltura_session
/?reference_id
=%s' % (self._API_BASE, reference_id),
166 video_id, 'Downloading kaltura session JSON
',
167 'Unable to download kaltura session JSON
', fatal=False,
168 headers={'Accept': 'application/json'})
170 session = kaltura_session.get('session
')
172 query['flashvars
[ks
]'] = session
174 return self.url_result(update_url_query(
175 'https
://cdnapisec
.kaltura
.com
/html5
/html5lib
/v2
.37
.1/mwEmbedFrame
.php
', query),
179 class SafariApiIE(SafariBaseIE):
180 IE_NAME = 'safari
:api
'
181 _VALID_URL = r'https?
://(?
:www\
.)?
(?
:safaribooksonline|
(?
:learning\
.)?oreilly
)\
.com
/api
/v1
/book
/(?P
<course_id
>[^
/]+)/chapter(?
:-content
)?
/(?P
<part
>[^
/?
#&]+)\.html'
184 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
185 'only_matching': True,
187 'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html',
188 'only_matching': True,
191 def _real_extract(self
, url
):
192 mobj
= self
._match
_valid
_url
(url
)
193 part
= self
._download
_json
(
194 url
, '%s/%s' % (mobj
.group('course_id'), mobj
.group('part')),
195 'Downloading part JSON')
196 return self
.url_result(part
['web_url'], SafariIE
.ie_key())
199 class SafariCourseIE(SafariBaseIE
):
200 IE_NAME
= 'safari:course'
201 IE_DESC
= 'safaribooksonline.com online courses'
203 _VALID_URL
= r
'''(?x)
206 (?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/
212 techbus\.safaribooksonline\.com
218 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
220 'id': '9780133392838',
221 'title': 'Hadoop Fundamentals LiveLessons',
223 'playlist_count': 22,
224 'skip': 'Requires safaribooksonline account credentials',
226 'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
227 'only_matching': True,
229 'url': 'http://techbus.safaribooksonline.com/9780134426365',
230 'only_matching': True,
232 'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314',
233 'only_matching': True,
235 'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838',
236 'only_matching': True,
238 'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
239 'only_matching': True,
243 def suitable(cls
, url
):
244 return (False if SafariIE
.suitable(url
) or SafariApiIE
.suitable(url
)
245 else super(SafariCourseIE
, cls
).suitable(url
))
247 def _real_extract(self
, url
):
248 course_id
= self
._match
_id
(url
)
250 course_json
= self
._download
_json
(
251 '%s/book/%s/?override_format=%s' % (self
._API
_BASE
, course_id
, self
._API
_FORMAT
),
252 course_id
, 'Downloading course JSON')
254 if 'chapters' not in course_json
:
255 raise ExtractorError(
256 'No chapters found for course %s' % course_id
, expected
=True)
259 self
.url_result(chapter
, SafariApiIE
.ie_key())
260 for chapter
in course_json
['chapters']]
262 course_title
= course_json
['title']
264 return self
.playlist_result(entries
, course_id
, course_title
)