1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
|
# coding: utf-8
from __future__ import unicode_literals
from itertools import zip_longest
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
srt_subtitles_timecode,
try_get,
urlencode_postdata,
urljoin,
)
class LinkedInLearningBaseIE(InfoExtractor):
_NETRC_MACHINE = 'linkedin'
_LOGIN_URL = 'https://www.linkedin.com/uas/login?trk=learning'
def _call_api(self, course_slug, fields, video_slug=None, resolution=None):
query = {
'courseSlug': course_slug,
'fields': fields,
'q': 'slugs',
}
sub = ''
if video_slug:
query.update({
'videoSlug': video_slug,
'resolution': '_%s' % resolution,
})
sub = ' %dp' % resolution
api_url = 'https://www.linkedin.com/learning-api/detailedCourses'
return self._download_json(
api_url, video_slug, 'Downloading%s JSON metadata' % sub, headers={
'Csrf-Token': self._get_cookies(api_url)['JSESSIONID'].value,
}, query=query)['elements'][0]
def _get_urn_id(self, video_data):
urn = video_data.get('urn')
if urn:
mobj = re.search(r'urn:li:lyndaCourse:\d+,(\d+)', urn)
if mobj:
return mobj.group(1)
def _get_video_id(self, video_data, course_slug, video_slug):
return self._get_urn_id(video_data) or '%s/%s' % (course_slug, video_slug)
def _real_initialize(self):
email, password = self._get_login_info()
if email is None:
return
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
action_url = urljoin(self._LOGIN_URL, self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page, 'post url',
default='https://www.linkedin.com/uas/login-submit', group='url'))
data = self._hidden_inputs(login_page)
data.update({
'session_key': email,
'session_password': password,
})
login_submit_page = self._download_webpage(
action_url, None, 'Logging in',
data=urlencode_postdata(data))
error = self._search_regex(
r'<span[^>]+class="error"[^>]*>\s*(.+?)\s*</span>',
login_submit_page, 'error', default=None)
if error:
raise ExtractorError(error, expected=True)
class LinkedInLearningIE(LinkedInLearningBaseIE):
IE_NAME = 'linkedin:learning'
_VALID_URL = r'https?://(?:www\.)?linkedin\.com/learning/(?P<course_slug>[^/]+)/(?P<id>[^/?#]+)'
_TEST = {
'url': 'https://www.linkedin.com/learning/programming-foundations-fundamentals/welcome?autoplay=true',
'md5': 'a1d74422ff0d5e66a792deb996693167',
'info_dict': {
'id': '90426',
'ext': 'mp4',
'title': 'Welcome',
'timestamp': 1430396150.82,
'upload_date': '20150430',
},
}
def json2srt(self, transcript_lines, duration=None):
srt_data = ''
for line, (line_dict, next_dict) in enumerate(zip_longest(transcript_lines, transcript_lines[1:])):
start_time, caption = line_dict['transcriptStartAt'] / 1000, line_dict['caption']
end_time = next_dict['transcriptStartAt'] / 1000 if next_dict else duration or start_time + 1
srt_data += '%d\n%s --> %s\n%s\n\n' % (line + 1, srt_subtitles_timecode(start_time),
srt_subtitles_timecode(end_time),
caption)
return srt_data
def _real_extract(self, url):
course_slug, video_slug = self._match_valid_url(url).groups()
video_data = None
formats = []
for width, height in ((640, 360), (960, 540), (1280, 720)):
video_data = self._call_api(
course_slug, 'selectedVideo', video_slug, height)['selectedVideo']
video_url_data = video_data.get('url') or {}
progressive_url = video_url_data.get('progressiveUrl')
if progressive_url:
formats.append({
'format_id': 'progressive-%dp' % height,
'url': progressive_url,
'ext': 'mp4',
'height': height,
'width': width,
'source_preference': 1,
})
title = video_data['title']
audio_url = video_data.get('audio', {}).get('progressiveUrl')
if audio_url:
formats.append({
'abr': 64,
'ext': 'm4a',
'format_id': 'audio',
'url': audio_url,
'vcodec': 'none',
})
streaming_url = video_url_data.get('streamingUrl')
if streaming_url:
formats.extend(self._extract_m3u8_formats(
streaming_url, video_slug, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False))
# It seems like this would be correctly handled by default
# However, unless someone can confirm this, the old
# behaviour is being kept as-is
self._sort_formats(formats, ('res', 'source_preference'))
subtitles = {}
duration = int_or_none(video_data.get('durationInSeconds'))
transcript_lines = try_get(video_data, lambda x: x['transcript']['lines'], expected_type=list)
if transcript_lines:
subtitles['en'] = [{
'ext': 'srt',
'data': self.json2srt(transcript_lines, duration)
}]
return {
'id': self._get_video_id(video_data, course_slug, video_slug),
'title': title,
'formats': formats,
'thumbnail': video_data.get('defaultThumbnail'),
'timestamp': float_or_none(video_data.get('publishedOn'), 1000),
'duration': duration,
'subtitles': subtitles,
}
class LinkedInLearningCourseIE(LinkedInLearningBaseIE):
IE_NAME = 'linkedin:learning:course'
_VALID_URL = r'https?://(?:www\.)?linkedin\.com/learning/(?P<id>[^/?#]+)'
_TEST = {
'url': 'https://www.linkedin.com/learning/programming-foundations-fundamentals',
'info_dict': {
'id': 'programming-foundations-fundamentals',
'title': 'Programming Foundations: Fundamentals',
'description': 'md5:76e580b017694eb89dc8e8923fff5c86',
},
'playlist_mincount': 61,
}
@classmethod
def suitable(cls, url):
return False if LinkedInLearningIE.suitable(url) else super(LinkedInLearningCourseIE, cls).suitable(url)
def _real_extract(self, url):
course_slug = self._match_id(url)
course_data = self._call_api(course_slug, 'chapters,description,title')
entries = []
for chapter_number, chapter in enumerate(course_data.get('chapters', []), 1):
chapter_title = chapter.get('title')
chapter_id = self._get_urn_id(chapter)
for video in chapter.get('videos', []):
video_slug = video.get('slug')
if not video_slug:
continue
entries.append({
'_type': 'url_transparent',
'id': self._get_video_id(video, course_slug, video_slug),
'title': video.get('title'),
'url': 'https://www.linkedin.com/learning/%s/%s' % (course_slug, video_slug),
'chapter': chapter_title,
'chapter_number': chapter_number,
'chapter_id': chapter_id,
'ie_key': LinkedInLearningIE.ie_key(),
})
return self.playlist_result(
entries, course_slug,
course_data.get('title'),
course_data.get('description'))
|
