2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
17 class SafariBaseIE(InfoExtractor
):
18 _LOGIN_URL
= 'https://learning.oreilly.com/accounts/login/'
19 _NETRC_MACHINE
= 'safari'
21 _API_BASE
= 'https://learning.oreilly.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'
79 (?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/
81 library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?\#&]+)\.html|
82 videos/[^/]+/[^/]+/(?P<reference_id>[^-]+-[^/?\#&]+)
87 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
88 'md5': 'dcc5a425e79f2564148652616af1f2a3',
92 'title': 'Introduction to Hadoop Fundamentals LiveLessons',
93 'timestamp': 1437758058,
94 'upload_date': '20150724',
95 'uploader_id': 'stork',
98 # non-digits in course id
99 'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
100 'only_matching': True,
102 'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html',
103 'only_matching': True,
105 'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314/9780134217314-PYMC_13_00',
106 'only_matching': True,
108 'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838/9780133392838-00_SeriesIntro',
109 'only_matching': True,
112 _PARTNER_ID = '1926081'
113 _UICONF_ID = '29375172'
115 def _real_extract(self, url):
116 mobj = re.match(self._VALID_URL, url)
118 reference_id = mobj.group('reference_id')
120 video_id = reference_id
121 partner_id = self._PARTNER_ID
122 ui_id = self._UICONF_ID
124 video_id = '%s-%s' % (mobj.group('course_id'), mobj.group('part'))
126 webpage, urlh = self._download_webpage_handle(url, video_id)
128 mobj = re.match(self._VALID_URL, urlh.geturl())
129 reference_id = mobj.group('reference_id')
131 reference_id = self._search_regex(
132 r'data-reference-id=(["\'])(?P
<id>(?
:(?
!\
1).)+)\
1',
133 webpage, 'kaltura reference
id', group='id')
134 partner_id = self._search_regex(
135 r'data
-partner
-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
136 webpage, 'kaltura widget id', default=self._PARTNER_ID,
138 ui_id = self._search_regex(
139 r'data-ui-id=(["\'])(?P
<id>(?
:(?
!\
1).)+)\
1',
140 webpage, 'kaltura uiconf
id', default=self._UICONF_ID,
144 'wid
': '_
%s' % partner_id,
146 'flashvars
[referenceId
]': reference_id,
150 kaltura_session = self._download_json(
151 '%s/player
/kaltura_session
/?reference_id
=%s' % (self._API_BASE, reference_id),
152 video_id, 'Downloading kaltura session JSON
',
153 'Unable to download kaltura session JSON
', fatal=False)
155 session = kaltura_session.get('session
')
157 query['flashvars
[ks
]'] = session
159 return self.url_result(update_url_query(
160 'https
://cdnapisec
.kaltura
.com
/html5
/html5lib
/v2
.37
.1/mwEmbedFrame
.php
', query),
164 class SafariApiIE(SafariBaseIE):
165 IE_NAME = 'safari
:api
'
166 _VALID_URL = r'https?
://(?
:www\
.)?
(?
:safaribooksonline|learning\
.oreilly
)\
.com
/api
/v1
/book
/(?P
<course_id
>[^
/]+)/chapter(?
:-content
)?
/(?P
<part
>[^
/?
#&]+)\.html'
169 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
170 'only_matching': True,
172 'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html',
173 'only_matching': True,
176 def _real_extract(self
, url
):
177 mobj
= re
.match(self
._VALID
_URL
, url
)
178 part
= self
._download
_json
(
179 url
, '%s/%s' % (mobj
.group('course_id'), mobj
.group('part')),
180 'Downloading part JSON')
181 return self
.url_result(part
['web_url'], SafariIE
.ie_key())
184 class SafariCourseIE(SafariBaseIE
):
185 IE_NAME
= 'safari:course'
186 IE_DESC
= 'safaribooksonline.com online courses'
188 _VALID_URL
= r
'''(?x)
191 (?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/
197 techbus\.safaribooksonline\.com
203 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
205 'id': '9780133392838',
206 'title': 'Hadoop Fundamentals LiveLessons',
208 'playlist_count': 22,
209 'skip': 'Requires safaribooksonline account credentials',
211 'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
212 'only_matching': True,
214 'url': 'http://techbus.safaribooksonline.com/9780134426365',
215 'only_matching': True,
217 'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314',
218 'only_matching': True,
220 'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838',
221 'only_matching': True,
225 def suitable(cls
, url
):
226 return (False if SafariIE
.suitable(url
) or SafariApiIE
.suitable(url
)
227 else super(SafariCourseIE
, cls
).suitable(url
))
229 def _real_extract(self
, url
):
230 course_id
= self
._match
_id
(url
)
232 course_json
= self
._download
_json
(
233 '%s/book/%s/?override_format=%s' % (self
._API
_BASE
, course_id
, self
._API
_FORMAT
),
234 course_id
, 'Downloading course JSON')
236 if 'chapters' not in course_json
:
237 raise ExtractorError(
238 'No chapters found for course %s' % course_id
, expected
=True)
241 self
.url_result(chapter
, SafariApiIE
.ie_key())
242 for chapter
in course_json
['chapters']]
244 course_title
= course_json
['title']
246 return self
.playlist_result(entries
, course_id
, course_title
)