]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/lynda.py
[cleanup] Add more ruff rules (#10149)
[yt-dlp.git] / yt_dlp / extractor / lynda.py
CommitLineData
c7f8537d 1import re
add96eb9 2import urllib.parse
c7f8537d 3
4from .common import InfoExtractor
1cc79574 5from ..utils import (
16ff7ebc
S
6 ExtractorError,
7 int_or_none,
6e6bc8da 8 urlencode_postdata,
7ee40b5d 9)
c7f8537d 10
11
30cbd4e0 12class LyndaBaseIE(InfoExtractor):
f0128230 13 _SIGNIN_URL = 'https://www.lynda.com/signin/lynda'
bdf16f81
S
14 _PASSWORD_URL = 'https://www.lynda.com/signin/password'
15 _USER_URL = 'https://www.lynda.com/signin/user'
30cbd4e0 16 _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.'
499bfcbf 17 _NETRC_MACHINE = 'lynda'
30cbd4e0 18
bdf16f81
S
19 @staticmethod
20 def _check_error(json_string, key_or_keys):
add96eb9 21 keys = [key_or_keys] if isinstance(key_or_keys, str) else key_or_keys
bdf16f81
S
22 for key in keys:
23 error = json_string.get(key)
24 if error:
add96eb9 25 raise ExtractorError(f'Unable to login: {error}', expected=True)
bdf16f81 26
52efa4b3 27 def _perform_login_step(self, form_html, fallback_action_url, extra_form_data, note, referrer_url):
bdf16f81
S
28 action_url = self._search_regex(
29 r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_html,
30 'post url', default=fallback_action_url, group='url')
31
32 if not action_url.startswith('http'):
add96eb9 33 action_url = urllib.parse.urljoin(self._SIGNIN_URL, action_url)
bdf16f81
S
34
35 form_data = self._hidden_inputs(form_html)
36 form_data.update(extra_form_data)
37
5621c322
S
38 response = self._download_json(
39 action_url, None, note,
40 data=urlencode_postdata(form_data),
41 headers={
42 'Referer': referrer_url,
43 'X-Requested-With': 'XMLHttpRequest',
add96eb9 44 }, expected_status=(418, 500))
bdf16f81 45
5621c322 46 self._check_error(response, ('email', 'password', 'ErrorMessage'))
bdf16f81
S
47
48 return response, action_url
49
52efa4b3 50 def _perform_login(self, username, password):
bdf16f81
S
51 # Step 1: download signin page
52 signin_page = self._download_webpage(
53 self._SIGNIN_URL, None, 'Downloading signin page')
54
3841256c
S
55 # Already logged in
56 if any(re.search(p, signin_page) for p in (
ec85ded8 57 r'isLoggedIn\s*:\s*true', r'logout\.aspx', r'>Log out<')):
3841256c
S
58 return
59
bdf16f81
S
60 # Step 2: submit email
61 signin_form = self._search_regex(
62 r'(?s)(<form[^>]+data-form-name=["\']signin["\'][^>]*>.+?</form>)',
63 signin_page, 'signin form')
64 signin_page, signin_url = self._login_step(
65 signin_form, self._PASSWORD_URL, {'email': username},
66 'Submitting email', self._SIGNIN_URL)
67
68 # Step 3: submit password
69 password_form = signin_page['body']
70 self._login_step(
71 password_form, self._USER_URL, {'email': username, 'password': password},
72 'Submitting password', signin_url)
30cbd4e0
S
73
74
75class LyndaIE(LyndaBaseIE):
a7c26e73
PH
76 IE_NAME = 'lynda'
77 IE_DESC = 'lynda.com videos'
b7c74c04
S
78 _VALID_URL = r'''(?x)
79 https?://
80 (?:www\.)?(?:lynda\.com|educourse\.ga)/
81 (?:
82 (?:[^/]+/){2,3}(?P<course_id>\d+)|
83 player/embed
84 )/
85 (?P<id>\d+)
86 '''
7ee40b5d 87
7ee40b5d 88 _TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
89
a0d64613 90 _TESTS = [{
68d9561c 91 'url': 'https://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
61a98b86 92 # md5 is unstable
ac260dd8 93 'info_dict': {
136db788
S
94 'id': '114408',
95 'ext': 'mp4',
a7c26e73 96 'title': 'Using the exercise files',
add96eb9 97 'duration': 68,
98 },
a0d64613
S
99 }, {
100 'url': 'https://www.lynda.com/player/embed/133770?tr=foo=1;bar=g;fizz=rt&fs=0',
101 'only_matching': True,
8c6919e4
S
102 }, {
103 'url': 'https://educourse.ga/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
104 'only_matching': True,
b7c74c04
S
105 }, {
106 'url': 'https://www.lynda.com/de/Graphic-Design-tutorials/Willkommen-Grundlagen-guten-Gestaltung/393570/393572-4.html',
107 'only_matching': True,
d89a0a80
S
108 }, {
109 # Status="NotFound", Message="Transcript not found"
110 'url': 'https://www.lynda.com/ASP-NET-tutorials/What-you-should-know/5034180/2811512-4.html',
111 'only_matching': True,
a0d64613 112 }]
7ee40b5d 113
6edfc40a
S
114 def _raise_unavailable(self, video_id):
115 self.raise_login_required(
add96eb9 116 f'Video {video_id} is only available for members')
6edfc40a 117
c7f8537d 118 def _real_extract(self, url):
5ad28e7f 119 mobj = self._match_valid_url(url)
6edfc40a
S
120 video_id = mobj.group('id')
121 course_id = mobj.group('course_id')
122
123 query = {
124 'videoId': video_id,
125 'type': 'video',
126 }
c7f8537d 127
ea8ed40b 128 video = self._download_json(
6edfc40a
S
129 'https://www.lynda.com/ajax/player', video_id,
130 'Downloading video JSON', fatal=False, query=query)
131
132 # Fallback scenario
133 if not video:
134 query['courseId'] = course_id
135
136 play = self._download_json(
add96eb9 137 f'https://www.lynda.com/ajax/course/{course_id}/{video_id}/play', video_id, 'Downloading play JSON')
6edfc40a
S
138
139 if not play:
140 self._raise_unavailable(video_id)
141
142 formats = []
143 for formats_dict in play:
144 urls = formats_dict.get('urls')
145 if not isinstance(urls, dict):
146 continue
147 cdn = formats_dict.get('name')
148 for format_id, format_url in urls.items():
149 if not format_url:
150 continue
151 formats.append({
152 'url': format_url,
add96eb9 153 'format_id': f'{cdn}-{format_id}' if cdn else format_id,
6edfc40a
S
154 'height': int_or_none(format_id),
155 })
6edfc40a
S
156
157 conviva = self._download_json(
158 'https://www.lynda.com/ajax/player/conviva', video_id,
159 'Downloading conviva JSON', query=query)
160
161 return {
162 'id': video_id,
163 'title': conviva['VideoTitle'],
164 'description': conviva.get('VideoDescription'),
165 'release_year': int_or_none(conviva.get('ReleaseYear')),
166 'duration': int_or_none(conviva.get('Duration')),
167 'creator': conviva.get('Author'),
168 'formats': formats,
169 }
c7f8537d 170
ea8ed40b 171 if 'Status' in video:
30cbd4e0 172 raise ExtractorError(
add96eb9 173 'lynda returned error: {}'.format(video['Message']), expected=True)
c7f8537d 174
ea8ed40b 175 if video.get('HasAccess') is False:
6edfc40a 176 self._raise_unavailable(video_id)
c7f8537d 177
add96eb9 178 video_id = str(video.get('ID') or video_id)
ea8ed40b
S
179 duration = int_or_none(video.get('DurationInSeconds'))
180 title = video['Title']
c7f8537d 181
16ff7ebc
S
182 formats = []
183
ea8ed40b 184 fmts = video.get('Formats')
16ff7ebc 185 if fmts:
ea8ed40b
S
186 formats.extend([{
187 'url': f['Url'],
188 'ext': f.get('Extension'),
189 'width': int_or_none(f.get('Width')),
190 'height': int_or_none(f.get('Height')),
191 'filesize': int_or_none(f.get('FileSize')),
add96eb9 192 'format_id': str(f.get('Resolution')) if f.get('Resolution') else None,
ea8ed40b
S
193 } for f in fmts if f.get('Url')])
194
195 prioritized_streams = video.get('PrioritizedStreams')
16ff7ebc 196 if prioritized_streams:
5a11b793 197 for prioritized_stream_id, prioritized_stream in prioritized_streams.items():
ea8ed40b
S
198 formats.extend([{
199 'url': video_url,
ea8aefd1 200 'height': int_or_none(format_id),
add96eb9 201 'format_id': f'{prioritized_stream_id}-{format_id}',
ea8ed40b 202 } for format_id, video_url in prioritized_stream.items()])
c7f8537d 203
a57e8ce6 204 self._check_formats(formats, video_id)
7ee40b5d 205
ea8ed40b 206 subtitles = self.extract_subtitles(video_id)
7ee40b5d 207
c7f8537d 208 return {
209 'id': video_id,
210 'title': title,
211 'duration': duration,
62bcfa8c 212 'subtitles': subtitles,
add96eb9 213 'formats': formats,
c7f8537d 214 }
7ee40b5d 215
311c3938
JMF
216 def _fix_subtitles(self, subs):
217 srt = ''
7594be85 218 seq_counter = 0
add96eb9 219 for seq_current, seq_next in zip(subs, subs[1:]):
311c3938
JMF
220 m_current = re.match(self._TIMECODE_REGEX, seq_current['Timecode'])
221 if m_current is None:
222 continue
311c3938
JMF
223 m_next = re.match(self._TIMECODE_REGEX, seq_next['Timecode'])
224 if m_next is None:
62bcfa8c 225 continue
311c3938
JMF
226 appear_time = m_current.group('timecode')
227 disappear_time = m_next.group('timecode')
7594be85
S
228 text = seq_current['Caption'].strip()
229 if text:
230 seq_counter += 1
add96eb9 231 srt += f'{seq_counter}\r\n{appear_time} --> {disappear_time}\r\n{text}\r\n\r\n'
311c3938
JMF
232 if srt:
233 return srt
234
ea8ed40b 235 def _get_subtitles(self, video_id):
add96eb9 236 url = f'https://www.lynda.com/ajax/player?videoId={video_id}&type=transcript'
d89a0a80
S
237 subs = self._download_webpage(
238 url, video_id, 'Downloading subtitles JSON', fatal=False)
239 if not subs or 'Status="NotFound"' in subs:
240 return {}
241 subs = self._parse_json(subs, video_id, fatal=False)
242 if not subs:
243 return {}
75ba0efb
S
244 fixed_subs = self._fix_subtitles(subs)
245 if fixed_subs:
246 return {'en': [{'ext': 'srt', 'data': fixed_subs}]}
d89a0a80 247 return {}
c7f8537d 248
249
30cbd4e0 250class LyndaCourseIE(LyndaBaseIE):
a7c26e73
PH
251 IE_NAME = 'lynda:course'
252 IE_DESC = 'lynda.com online courses'
c7f8537d 253
254 # Course link equals to welcome/introduction video link of same course
255 # We will recognize it as course link
b7c74c04
S
256 _VALID_URL = r'https?://(?:www|m)\.(?:lynda\.com|educourse\.ga)/(?P<coursepath>(?:[^/]+/){2,3}(?P<courseid>\d+))-2\.html'
257
258 _TESTS = [{
259 'url': 'https://www.lynda.com/Graphic-Design-tutorials/Grundlagen-guten-Gestaltung/393570-2.html',
260 'only_matching': True,
261 }, {
262 'url': 'https://www.lynda.com/de/Graphic-Design-tutorials/Grundlagen-guten-Gestaltung/393570-2.html',
263 'only_matching': True,
264 }]
c7f8537d 265
266 def _real_extract(self, url):
5ad28e7f 267 mobj = self._match_valid_url(url)
c7f8537d 268 course_path = mobj.group('coursepath')
269 course_id = mobj.group('courseid')
5f6a1245 270
add96eb9 271 item_template = f'https://www.lynda.com/{course_path}/%s-4.html'
f2980fdd 272
71bb0161 273 course = self._download_json(
add96eb9 274 f'https://www.lynda.com/ajax/player?courseId={course_id}&type=course',
f2980fdd
S
275 course_id, 'Downloading course JSON', fatal=False)
276
277 if not course:
278 webpage = self._download_webpage(url, course_id)
279 entries = [
280 self.url_result(
281 item_template % video_id, ie=LyndaIE.ie_key(),
282 video_id=video_id)
283 for video_id in re.findall(
284 r'data-video-id=["\'](\d+)', webpage)]
285 return self.playlist_result(
286 entries, course_id,
287 self._og_search_title(webpage, fatal=False),
288 self._og_search_description(webpage))
c7f8537d 289
71bb0161 290 if course.get('Status') == 'NotFound':
30cbd4e0 291 raise ExtractorError(
add96eb9 292 f'Course {course_id} does not exist', expected=True)
c7f8537d 293
294 unaccessible_videos = 0
00322ad4 295 entries = []
c7f8537d 296
16ff7ebc
S
297 # Might want to extract videos right here from video['Formats'] as it seems 'Formats' is not provided
298 # by single video API anymore
299
71bb0161
S
300 for chapter in course['Chapters']:
301 for video in chapter.get('Videos', []):
302 if video.get('HasAccess') is False:
c7f8537d 303 unaccessible_videos += 1
304 continue
00322ad4
S
305 video_id = video.get('ID')
306 if video_id:
307 entries.append({
308 '_type': 'url_transparent',
f2980fdd 309 'url': item_template % video_id,
00322ad4
S
310 'ie_key': LyndaIE.ie_key(),
311 'chapter': chapter.get('Title'),
312 'chapter_number': int_or_none(chapter.get('ChapterIndex')),
add96eb9 313 'chapter_id': str(chapter.get('ID')),
00322ad4 314 })
c7f8537d 315
316 if unaccessible_videos > 0:
6a39ee13 317 self.report_warning(
add96eb9 318 f'{unaccessible_videos} videos are only available for members (or paid members) '
319 f'and will not be downloaded. {self._ACCOUNT_CREDENTIALS_HINT}')
c7f8537d 320
71bb0161 321 course_title = course.get('Title')
04343588 322 course_description = course.get('Description')
c7f8537d 323
04343588 324 return self.playlist_result(entries, course_id, course_title, course_description)