]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/safari.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from .brightcove
import BrightcoveLegacyIE
19 class SafariBaseIE(InfoExtractor
):
20 _LOGIN_URL
= 'https://www.safaribooksonline.com/accounts/login/'
21 _SUCCESSFUL_LOGIN_REGEX
= r
'<a href="/accounts/logout/"[^>]*>Sign Out</a>'
22 _NETRC_MACHINE
= 'safari'
24 _API_BASE
= 'https://www.safaribooksonline.com/api/v1'
29 def _real_initialize(self
):
33 # We only need to log in once for courses or individual videos
37 (username
, password
) = self
._get
_login
_info
()
41 headers
= std_headers
.copy()
42 if 'Referer' not in headers
:
43 headers
['Referer'] = self
._LOGIN
_URL
44 login_page_request
= sanitized_Request(self
._LOGIN
_URL
, headers
=headers
)
46 login_page
= self
._download
_webpage
(
47 login_page_request
, None,
48 'Downloading login form')
50 csrf
= self
._html
_search
_regex
(
51 r
"name='csrfmiddlewaretoken'\s+value='([^']+)'",
52 login_page
, 'csrf token')
55 'csrfmiddlewaretoken': csrf
,
57 'password1': password
,
62 request
= sanitized_Request(
63 self
._LOGIN
_URL
, urlencode_postdata(login_form
), headers
=headers
)
64 login_page
= self
._download
_webpage
(
65 request
, None, 'Logging in as %s' % username
)
67 if re
.search(self
._SUCCESSFUL
_LOGIN
_REGEX
, login_page
) is None:
69 'Login failed; make sure your credentials are correct and try again.',
72 SafariBaseIE
.LOGGED_IN
= True
74 self
.to_screen('Login successful')
77 class SafariIE(SafariBaseIE
):
79 IE_DESC
= 'safaribooksonline.com online video'
80 _VALID_URL
= r
'''(?x)https?://
81 (?:www\.)?safaribooksonline\.com/
87 (?:chapter(?:-content)?/)?
88 (?P<part>part\d+)\.html
92 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
93 'md5': 'dcc5a425e79f2564148652616af1f2a3',
97 'title': 'Introduction to Hadoop Fundamentals LiveLessons',
98 'timestamp': 1437758058,
99 'upload_date': '20150724',
100 'uploader_id': 'stork',
103 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
104 'only_matching': True,
106 # non-digits in course id
107 'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
108 'only_matching': True,
111 def _real_extract(self
, url
):
112 mobj
= re
.match(self
._VALID
_URL
, url
)
113 course_id
= mobj
.group('course_id')
114 part
= mobj
.group('part')
116 webpage
= self
._download
_webpage
(url
, '%s/%s' % (course_id
, part
))
117 reference_id
= self
._search
_regex
(r
'data-reference-id="([^"]+)"', webpage
, 'kaltura reference id')
118 partner_id
= self
._search
_regex
(r
'data-partner-id="([^"]+)"', webpage
, 'kaltura widget id')
119 ui_id
= self
._search
_regex
(r
'data-ui-id="([^"]+)"', webpage
, 'kaltura uiconf id')
122 'wid': '_%s' % partner_id
,
124 'flashvars[referenceId]': reference_id
,
128 kaltura_session
= self
._download
_json
(
129 '%s/player/kaltura_session/?reference_id=%s' % (self
._API
_BASE
, reference_id
),
130 course_id
, 'Downloading kaltura session JSON',
131 'Unable to download kaltura session JSON', fatal
=False)
133 session
= kaltura_session
.get('session')
135 query
['flashvars[ks]'] = session
137 return self
.url_result(update_url_query(
138 'https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', query
),
142 class SafariCourseIE(SafariBaseIE
):
143 IE_NAME
= 'safari:course'
144 IE_DESC
= 'safaribooksonline.com online courses'
146 _VALID_URL
= r
'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>[^/]+)/?(?:[#?]|$)'
149 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
151 'id': '9780133392838',
152 'title': 'Hadoop Fundamentals LiveLessons',
154 'playlist_count': 22,
155 'skip': 'Requires safaribooksonline account credentials',
157 'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
158 'only_matching': True,
161 def _real_extract(self
, url
):
162 course_id
= self
._match
_id
(url
)
164 course_json
= self
._download
_json
(
165 '%s/book/%s/?override_format=%s' % (self
._API
_BASE
, course_id
, self
._API
_FORMAT
),
166 course_id
, 'Downloading course JSON')
168 if 'chapters' not in course_json
:
169 raise ExtractorError(
170 'No chapters found for course %s' % course_id
, expected
=True)
173 self
.url_result(chapter
, 'Safari')
174 for chapter
in course_json
['chapters']]
176 course_title
= course_json
['title']
178 return self
.playlist_result(entries
, course_id
, course_title
)