]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/packtpub.py
bb668c99953254a0cb5e36389d9b97b4e21c67d8
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
21 class PacktPubBaseIE(InfoExtractor
):
22 _PACKT_BASE
= 'https://www.packtpub.com'
23 _MAPT_REST
= '%s/mapt-rest' % _PACKT_BASE
26 class PacktPubIE(PacktPubBaseIE
):
27 _VALID_URL
= r
'https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>\d+)/(?P<id>\d+)'
30 'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro',
31 'md5': '1e74bd6cfd45d7d07666f4684ef58f70',
35 'title': 'Project Intro',
36 'thumbnail': r
're:(?i)^https?://.*\.jpg',
37 'timestamp': 1490918400,
38 'upload_date': '20170331',
41 _NETRC_MACHINE
= 'packtpub'
44 def _real_initialize(self
):
45 (username
, password
) = self
._get
_login
_info
()
48 webpage
= self
._download
_webpage
(self
._PACKT
_BASE
, None)
49 login_form
= self
._form
_hidden
_inputs
(
50 'packt-user-login-form', webpage
)
55 self
._download
_webpage
(
56 self
._PACKT
_BASE
, None, 'Logging in as %s' % username
,
57 data
=urlencode_postdata(login_form
))
59 self
._TOKEN
= self
._download
_json
(
60 '%s/users/tokens/sessions' % self
._MAPT
_REST
, None,
61 'Downloading Authorization Token')['data']['token']
62 except ExtractorError
as e
:
63 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
in (401, 404):
64 message
= self
._parse
_json
(e
.cause
.read().decode(), None)['message']
65 raise ExtractorError(message
, expected
=True)
68 def _handle_error(self
, response
):
69 if response
.get('status') != 'success':
71 '% said: %s' % (self
.IE_NAME
, response
['message']),
74 def _download_json(self
, *args
, **kwargs
):
75 response
= super(PacktPubIE
, self
)._download
_json
(*args
, **kwargs
)
76 self
._handle
_error
(response
)
79 def _real_extract(self
, url
):
80 mobj
= re
.match(self
._VALID
_URL
, url
)
81 course_id
, chapter_id
, video_id
= mobj
.group(
82 'course_id', 'chapter_id', 'id')
86 headers
['Authorization'] = self
._TOKEN
87 video
= self
._download
_json
(
88 '%s/users/me/products/%s/chapters/%s/sections/%s'
89 % (self
._MAPT
_REST
, course_id
, chapter_id
, video_id
), video_id
,
90 'Downloading JSON video', headers
=headers
)['data']
92 content
= video
.get('content')
94 self
.raise_login_required('This video is locked')
96 video_url
= content
['file']
98 metadata
= self
._download
_json
(
99 '%s/products/%s/chapters/%s/sections/%s/metadata'
100 % (self
._MAPT
_REST
, course_id
, chapter_id
, video_id
),
103 title
= metadata
['pageTitle']
104 course_title
= metadata
.get('title')
106 title
= remove_end(title
, ' - %s' % course_title
)
107 timestamp
= unified_timestamp(metadata
.get('publicationDate'))
108 thumbnail
= urljoin(self
._PACKT
_BASE
, metadata
.get('filepath'))
114 'thumbnail': thumbnail
,
115 'timestamp': timestamp
,
119 class PacktPubCourseIE(PacktPubBaseIE
):
120 _VALID_URL
= r
'(?P<url>https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<id>\d+))'
122 'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215',
124 'id': '9781787122215',
125 'title': 'Learn Nodejs by building 12 projects [Video]',
127 'playlist_count': 90,
131 def suitable(cls
, url
):
132 return False if PacktPubIE
.suitable(url
) else super(
133 PacktPubCourseIE
, cls
).suitable(url
)
135 def _real_extract(self
, url
):
136 mobj
= re
.match(self
._VALID
_URL
, url
)
137 url
, course_id
= mobj
.group('url', 'id')
139 course
= self
._download
_json
(
140 '%s/products/%s/metadata' % (self
._MAPT
_REST
, course_id
),
144 for chapter_num
, chapter
in enumerate(course
['tableOfContents'], 1):
145 if chapter
.get('type') != 'chapter':
147 children
= chapter
.get('children')
148 if not isinstance(children
, list):
151 'chapter': chapter
.get('title'),
152 'chapter_number': chapter_num
,
153 'chapter_id': chapter
.get('id'),
155 for section
in children
:
156 if section
.get('type') != 'section':
158 section_url
= section
.get('seoUrl')
159 if not isinstance(section_url
, compat_str
):
162 '_type': 'url_transparent',
163 'url': urljoin(url
+ '/', section_url
),
164 'title': strip_or_none(section
.get('title')),
165 'description': clean_html(section
.get('summary')),
166 'ie_key': PacktPubIE
.ie_key(),
168 entry
.update(chapter_info
)
169 entries
.append(entry
)
171 return self
.playlist_result(entries
, course_id
, course
.get('title'))