]>
Commit | Line | Data |
---|---|---|
1 | import re | |
2 | ||
3 | from .common import InfoExtractor | |
4 | from ..utils import ( | |
5 | ExtractorError, | |
6 | decode_packed_codes, | |
7 | urlencode_postdata, | |
8 | ) | |
9 | ||
10 | ||
11 | class SCTEBaseIE(InfoExtractor): | |
12 | _LOGIN_URL = 'https://www.scte.org/SCTE/Sign_In.aspx' | |
13 | _NETRC_MACHINE = 'scte' | |
14 | ||
15 | def _perform_login(self, username, password): | |
16 | login_popup = self._download_webpage( | |
17 | self._LOGIN_URL, None, 'Downloading login popup') | |
18 | ||
19 | def is_logged(webpage): | |
20 | return any(re.search(p, webpage) for p in ( | |
21 | r'class=["\']welcome\b', r'>Sign Out<')) | |
22 | ||
23 | # already logged in | |
24 | if is_logged(login_popup): | |
25 | return | |
26 | ||
27 | login_form = self._hidden_inputs(login_popup) | |
28 | ||
29 | login_form.update({ | |
30 | 'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInUserName': username, | |
31 | 'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInPassword': password, | |
32 | 'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$RememberMe': 'on', | |
33 | }) | |
34 | ||
35 | response = self._download_webpage( | |
36 | self._LOGIN_URL, None, 'Logging in', | |
37 | data=urlencode_postdata(login_form)) | |
38 | ||
39 | if '|pageRedirect|' not in response and not is_logged(response): | |
40 | error = self._html_search_regex( | |
41 | r'(?s)<[^>]+class=["\']AsiError["\'][^>]*>(.+?)</', | |
42 | response, 'error message', default=None) | |
43 | if error: | |
44 | raise ExtractorError(f'Unable to login: {error}', expected=True) | |
45 | raise ExtractorError('Unable to log in') | |
46 | ||
47 | ||
48 | class SCTEIE(SCTEBaseIE): | |
49 | _WORKING = False | |
50 | _VALID_URL = r'https?://learning\.scte\.org/mod/scorm/view\.php?.*?\bid=(?P<id>\d+)' | |
51 | _TESTS = [{ | |
52 | 'url': 'https://learning.scte.org/mod/scorm/view.php?id=31484', | |
53 | 'info_dict': { | |
54 | 'title': 'Introduction to DOCSIS Engineering Professional', | |
55 | 'id': '31484', | |
56 | }, | |
57 | 'playlist_count': 5, | |
58 | 'skip': 'Requires account credentials', | |
59 | }] | |
60 | ||
61 | def _real_extract(self, url): | |
62 | video_id = self._match_id(url) | |
63 | ||
64 | webpage = self._download_webpage(url, video_id) | |
65 | ||
66 | title = self._search_regex(r'<h1>(.+?)</h1>', webpage, 'title') | |
67 | ||
68 | context_id = self._search_regex(r'context-(\d+)', webpage, video_id) | |
69 | content_base = f'https://learning.scte.org/pluginfile.php/{context_id}/mod_scorm/content/8/' | |
70 | context = decode_packed_codes(self._download_webpage( | |
71 | f'{content_base}mobile/data.js', video_id)) | |
72 | ||
73 | data = self._parse_xml( | |
74 | self._search_regex( | |
75 | r'CreateData\(\s*"(.+?)"', context, 'data').replace(r"\'", "'"), | |
76 | video_id) | |
77 | ||
78 | entries = [] | |
79 | for asset in data.findall('.//asset'): | |
80 | asset_url = asset.get('url') | |
81 | if not asset_url or not asset_url.endswith('.mp4'): | |
82 | continue | |
83 | asset_id = self._search_regex( | |
84 | r'video_([^_]+)_', asset_url, 'asset id', default=None) | |
85 | if not asset_id: | |
86 | continue | |
87 | entries.append({ | |
88 | 'id': asset_id, | |
89 | 'title': title, | |
90 | 'url': content_base + asset_url, | |
91 | }) | |
92 | ||
93 | return self.playlist_result(entries, video_id, title) | |
94 | ||
95 | ||
96 | class SCTECourseIE(SCTEBaseIE): | |
97 | _WORKING = False | |
98 | _VALID_URL = r'https?://learning\.scte\.org/(?:mod/sub)?course/view\.php?.*?\bid=(?P<id>\d+)' | |
99 | _TESTS = [{ | |
100 | 'url': 'https://learning.scte.org/mod/subcourse/view.php?id=31491', | |
101 | 'only_matching': True, | |
102 | }, { | |
103 | 'url': 'https://learning.scte.org/course/view.php?id=3639', | |
104 | 'only_matching': True, | |
105 | }, { | |
106 | 'url': 'https://learning.scte.org/course/view.php?id=3073', | |
107 | 'only_matching': True, | |
108 | }] | |
109 | ||
110 | def _real_extract(self, url): | |
111 | course_id = self._match_id(url) | |
112 | ||
113 | webpage = self._download_webpage(url, course_id) | |
114 | ||
115 | title = self._search_regex( | |
116 | r'<h1>(.+?)</h1>', webpage, 'title', default=None) | |
117 | ||
118 | entries = [] | |
119 | for mobj in re.finditer( | |
120 | r'''(?x) | |
121 | <a[^>]+ | |
122 | href=(["\']) | |
123 | (?P<url> | |
124 | https?://learning\.scte\.org/mod/ | |
125 | (?P<kind>scorm|subcourse)/view\.php?(?:(?!\1).)*? | |
126 | \bid=\d+ | |
127 | ) | |
128 | ''', | |
129 | webpage): | |
130 | item_url = mobj.group('url') | |
131 | if item_url == url: | |
132 | continue | |
133 | ie = (SCTEIE.ie_key() if mobj.group('kind') == 'scorm' | |
134 | else SCTECourseIE.ie_key()) | |
135 | entries.append(self.url_result(item_url, ie=ie)) | |
136 | ||
137 | return self.playlist_result(entries, course_id, title) |