]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/safari.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from .brightcove
import BrightcoveLegacyIE
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'
23 _API_BASE
= 'https://www.safaribooksonline.com/api/v1/book'
28 def _real_initialize(self
):
29 # We only need to log in once for courses or individual videos
30 if not self
.LOGGED_IN
:
32 SafariBaseIE
.LOGGED_IN
= True
35 (username
, password
) = self
._get
_login
_info
()
37 self
.raise_login_required('safaribooksonline.com account is required')
40 if 'Referer' not in headers
:
41 headers
['Referer'] = self
._LOGIN
_URL
43 login_page
= self
._download
_webpage
(
44 self
._LOGIN
_URL
, None,
45 'Downloading login form')
47 csrf
= self
._html
_search
_regex
(
48 r
"name='csrfmiddlewaretoken'\s+value='([^']+)'",
49 login_page
, 'csrf token')
52 'csrfmiddlewaretoken': csrf
,
54 'password1': password
,
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
)
64 if re
.search(self
._SUCCESSFUL
_LOGIN
_REGEX
, login_page
) is None:
66 'Login failed; make sure your credentials are correct and try again.',
69 self
.to_screen('Login successful')
72 class SafariIE(SafariBaseIE
):
74 IE_DESC
= 'safaribooksonline.com online video'
75 _VALID_URL
= r
'''(?x)https?://
76 (?:www\.)?safaribooksonline\.com/
82 (?:chapter(?:-content)?/)?
83 (?P<part>part\d+)\.html
87 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
88 'md5': '5b0c4cc1b3c1ba15dda7344085aa5592',
90 'id': '2842601850001',
92 'title': 'Introduction',
94 'skip': 'Requires safaribooksonline account credentials',
96 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
97 'only_matching': True,
99 # non-digits in course id
100 'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
101 'only_matching': True,
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')
109 webpage
= self
._download
_webpage
(
110 '%s/%s/chapter-content/%s.html' % (self
._API
_BASE
, course_id
, part
),
113 bc_url
= BrightcoveLegacyIE
._extract
_brightcove
_url
(webpage
)
115 raise ExtractorError('Could not extract Brightcove URL from %s' % url
, expected
=True)
117 return self
.url_result(smuggle_url(bc_url
, {'Referer': url
}), 'BrightcoveLegacy')
120 class SafariCourseIE(SafariBaseIE
):
121 IE_NAME
= 'safari:course'
122 IE_DESC
= 'safaribooksonline.com online courses'
124 _VALID_URL
= r
'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>[^/]+)/?(?:[#?]|$)'
127 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
129 'id': '9780133392838',
130 'title': 'Hadoop Fundamentals LiveLessons',
132 'playlist_count': 22,
133 'skip': 'Requires safaribooksonline account credentials',
135 'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
136 'only_matching': True,
139 def _real_extract(self
, url
):
140 course_id
= self
._match
_id
(url
)
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')
146 if 'chapters' not in course_json
:
147 raise ExtractorError(
148 'No chapters found for course %s' % course_id
, expected
=True)
151 self
.url_result(chapter
, 'Safari')
152 for chapter
in course_json
['chapters']]
154 course_title
= course_json
['title']
156 return self
.playlist_result(entries
, course_id
, course_title
)