]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/alura.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
21 class AluraIE(InfoExtractor
):
22 _VALID_URL
= r
'https?://(?:cursos\.)?alura\.com\.br/course/(?P<course_name>[^/]+)/task/(?P<id>\d+)'
23 _LOGIN_URL
= 'https://cursos.alura.com.br/loginForm?urlAfterLogin=/loginForm'
24 _VIDEO_URL
= 'https://cursos.alura.com.br/course/%s/task/%s/video'
25 _NETRC_MACHINE
= 'alura'
27 'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs/task/60095',
31 'title': 'ReferĂȘncias, ref-set e alter'
33 'skip': 'Requires alura account credentials'},
36 'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs/task/60098',
37 'only_matching': True},
39 'url': 'https://cursos.alura.com.br/course/fundamentos-market-digital/task/55219',
40 'only_matching': True}
43 def _real_extract(self
, url
):
45 video_id
= self
._match
_id
(url
)
46 course
= self
._search
_regex
(self
._VALID
_URL
, url
, 'post url', group
='course_name')
47 video_url
= self
._VIDEO
_URL
% (course
, video_id
)
49 video_dict
= self
._download
_json
(video_url
, video_id
, 'Searching for videos')
52 webpage
= self
._download
_webpage
(url
, video_id
)
53 video_title
= clean_html(self
._search
_regex
(
54 r
'<span[^>]+class=(["\'])task
-body
-header
-title
-text\
1[^
>]*>(?P
<title
>[^
<]+)',
55 webpage, 'title
', group='title
'))
58 for video_obj in video_dict:
59 video_url_m3u8 = video_obj.get('link
')
60 video_format = self._extract_m3u8_formats(
61 video_url_m3u8, None, 'mp4
', entry_protocol='m3u8_native
',
62 m3u8_id='hls
', fatal=False)
63 for f in video_format:
64 m = re.search(r'^
[\w \W
]*-(?P
<res
>\w
*).mp4
[\W \w
]*', f['url
'])
66 if not f.get('height
'):
67 f['height
'] = int('720' if m.group('res
') == 'hd
' else '480')
68 formats.extend(video_format)
70 self._sort_formats(formats)
78 def _real_initialize(self):
82 username, password = self._get_login_info()
87 login_page = self._download_webpage(
88 self._LOGIN_URL, None, 'Downloading login popup
')
90 def is_logged(webpage):
91 return any(re.search(p, webpage) for p in (
92 r'href
=[\"|
\']?
/signout
[\"|
\']',
96 if is_logged(login_page):
99 login_form = self._hidden_inputs(login_page)
102 'username
': username,
103 'password
': password,
106 post_url = self._search_regex(
107 r'<form
[^
>]+class=["|\']signin-form["|
\'] action
=["|\'](?P<url>.+?)["|
\']', login_page,
108 'post url
', default=self._LOGIN_URL, group='url
')
110 if not post_url.startswith('http
'):
111 post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
113 response = self._download_webpage(
114 post_url, None, 'Logging
in',
115 data=urlencode_postdata(login_form),
116 headers={'Content-Type': 'application/x-www-form-urlencoded'})
118 if not is_logged(response):
119 error = self._html_search_regex(
120 r'(?s
)<p
[^
>]+class="alert-message[^"]*">(.+?)</p>',
121 response, 'error message', default=None)
123 raise ExtractorError('Unable to login: %s' % error, expected=True)
124 raise ExtractorError('Unable to log in')
127 class AluraCourseIE(AluraIE):
129 _VALID_URL = r'https?://(?:cursos\.)?alura\.com\.br/course/(?P<id>[^/]+)'
130 _LOGIN_URL = 'https://cursos.alura.com.br/loginForm?urlAfterLogin=/loginForm'
131 _NETRC_MACHINE = 'aluracourse'
133 'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs',
134 'only_matching': True,
138 def suitable(cls, url):
139 return False if AluraIE.suitable(url) else super(AluraCourseIE, cls).suitable(url)
141 def _real_extract(self, url):
143 course_path = self._match_id(url)
144 webpage = self._download_webpage(url, course_path)
146 course_title = self._search_regex(
147 r'<h1.*?>(.*?)<strong>(?P<course_title>.*?)</strong></h[0-9]>', webpage,
148 'course title', default=course_path, group='course_title')
152 for path in re.findall(r'<a\b(?=[^>]* class="[^
"]*(?<=[" ])courseSectionList
-section
[" ])(?=[^>]* href="([^
"]*))', webpage):
153 page_url = urljoin(url, path)
154 section_path = self._download_webpage(page_url, course_path)
155 for path_video in re.findall(r'<a\b(?=[^>]* class="[^
"]*(?<=[" ])task
-menu
-nav
-item
-link
-VIDEO
[" ])(?=[^>]* href="([^
"]*))', section_path):
156 chapter = clean_html(
158 r'<h3[^>]+class=(["\'])task
-menu
-section
-title
-text\
1[^
>]*>(?P
<chapter
>[^
<]+)',
163 chapter_number = int_or_none(
165 r'<span
[^
>]+class=(["\'])task-menu-section-title-number[^>]*>(.*?)<strong>(?P<chapter_number>[^<]+)</strong>',
168 group='chapter_number'))
169 video_url = urljoin(url, path_video)
172 '_type': 'url_transparent',
173 'id': self._match_id(video_url),
175 'id_key': self.ie_key(),
177 'chapter_number': chapter_number
179 entries.append(entry)
180 return self.playlist_result(entries, course_path, course_title)