]>
Commit | Line | Data |
---|---|---|
e5de3f6c S |
1 | from __future__ import unicode_literals |
2 | ||
e5de3f6c | 3 | from .common import InfoExtractor |
1cc79574 | 4 | from ..compat import ( |
328f82d5 | 5 | compat_HTTPError, |
15707c7e | 6 | compat_urllib_parse_urlencode, |
e5de3f6c | 7 | compat_urllib_request, |
ff9d5d09 | 8 | compat_urlparse, |
1cc79574 PH |
9 | ) |
10 | from ..utils import ( | |
e5de3f6c | 11 | ExtractorError, |
328f82d5 | 12 | float_or_none, |
3b35c342 | 13 | int_or_none, |
5c2266df | 14 | sanitized_Request, |
17b2d7ca | 15 | unescapeHTML, |
e5de3f6c S |
16 | ) |
17 | ||
18 | ||
19 | class UdemyIE(InfoExtractor): | |
20 | IE_NAME = 'udemy' | |
5eb7db4e S |
21 | _VALID_URL = r'''(?x) |
22 | https?:// | |
23 | www\.udemy\.com/ | |
24 | (?: | |
25 | [^#]+\#/lecture/| | |
26 | lecture/view/?\?lectureId=| | |
27 | [^/]+/learn/v4/t/lecture/ | |
28 | ) | |
29 | (?P<id>\d+) | |
30 | ''' | |
dcd4d95c S |
31 | _LOGIN_URL = 'https://www.udemy.com/join/login-popup/?displayType=ajax&showSkipButton=1' |
32 | _ORIGIN_URL = 'https://www.udemy.com' | |
e5de3f6c S |
33 | _NETRC_MACHINE = 'udemy' |
34 | ||
6563837e | 35 | _TESTS = [{ |
e5de3f6c S |
36 | 'url': 'https://www.udemy.com/java-tutorial/#/lecture/172757', |
37 | 'md5': '98eda5b657e752cf945d8445e261b5c5', | |
38 | 'info_dict': { | |
39 | 'id': '160614', | |
40 | 'ext': 'mp4', | |
41 | 'title': 'Introduction and Installation', | |
42 | 'description': 'md5:c0d51f6f21ef4ec65f091055a5eef876', | |
43 | 'duration': 579.29, | |
44 | }, | |
45 | 'skip': 'Requires udemy account credentials', | |
5eb7db4e S |
46 | }, { |
47 | # new URL schema | |
48 | 'url': 'https://www.udemy.com/electric-bass-right-from-the-start/learn/v4/t/lecture/4580906', | |
49 | 'only_matching': True, | |
6563837e | 50 | }] |
e5de3f6c | 51 | |
ff9d5d09 | 52 | def _enroll_course(self, base_url, webpage, course_id): |
17b2d7ca S |
53 | checkout_url = unescapeHTML(self._search_regex( |
54 | r'href=(["\'])(?P<url>https?://(?:www\.)?udemy\.com/payment/checkout/.+?)\1', | |
55 | webpage, 'checkout url', group='url', default=None)) | |
56 | if checkout_url: | |
57 | raise ExtractorError( | |
f20756fb | 58 | 'Course %s is not free. You have to pay for it before you can download. ' |
17b2d7ca S |
59 | 'Use this URL to confirm purchase: %s' % (course_id, checkout_url), expected=True) |
60 | ||
61 | enroll_url = unescapeHTML(self._search_regex( | |
ff9d5d09 | 62 | r'href=(["\'])(?P<url>(?:https?://(?:www\.)?udemy\.com)?/course/subscribe/.+?)\1', |
17b2d7ca S |
63 | webpage, 'enroll url', group='url', default=None)) |
64 | if enroll_url: | |
ff9d5d09 S |
65 | if not enroll_url.startswith('http'): |
66 | enroll_url = compat_urlparse.urljoin(base_url, enroll_url) | |
17b2d7ca S |
67 | webpage = self._download_webpage(enroll_url, course_id, 'Enrolling in the course') |
68 | if '>You have enrolled in' in webpage: | |
69 | self.to_screen('%s: Successfully enrolled in the course' % course_id) | |
328f82d5 S |
70 | |
71 | def _download_lecture(self, course_id, lecture_id): | |
72 | return self._download_json( | |
73 | 'https://www.udemy.com/api-2.0/users/me/subscribed-courses/%s/lectures/%s?%s' % ( | |
15707c7e | 74 | course_id, lecture_id, compat_urllib_parse_urlencode({ |
328f82d5 S |
75 | 'video_only': '', |
76 | 'auto_play': '', | |
77 | 'fields[lecture]': 'title,description,asset', | |
78 | 'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,data', | |
79 | 'instructorPreviewMode': 'False', | |
80 | })), | |
24121bc7 | 81 | lecture_id, 'Downloading lecture JSON') |
328f82d5 | 82 | |
e5de3f6c S |
83 | def _handle_error(self, response): |
84 | if not isinstance(response, dict): | |
85 | return | |
86 | error = response.get('error') | |
87 | if error: | |
88 | error_str = 'Udemy returned error #%s: %s' % (error.get('code'), error.get('message')) | |
89 | error_data = error.get('data') | |
90 | if error_data: | |
91 | error_str += ' - %s' % error_data.get('formErrors') | |
92 | raise ExtractorError(error_str, expected=True) | |
93 | ||
24121bc7 | 94 | def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'): |
e2937118 S |
95 | headers = { |
96 | 'X-Udemy-Snail-Case': 'true', | |
97 | 'X-Requested-With': 'XMLHttpRequest', | |
98 | } | |
99 | for cookie in self._downloader.cookiejar: | |
100 | if cookie.name == 'client_id': | |
101 | headers['X-Udemy-Client-Id'] = cookie.value | |
102 | elif cookie.name == 'access_token': | |
103 | headers['X-Udemy-Bearer-Token'] = cookie.value | |
328f82d5 | 104 | headers['X-Udemy-Authorization'] = 'Bearer %s' % cookie.value |
61c0663c S |
105 | |
106 | if isinstance(url_or_request, compat_urllib_request.Request): | |
107 | for header, value in headers.items(): | |
108 | url_or_request.add_header(header, value) | |
109 | else: | |
5c2266df | 110 | url_or_request = sanitized_Request(url_or_request, headers=headers) |
61c0663c | 111 | |
24121bc7 | 112 | response = super(UdemyIE, self)._download_json(url_or_request, video_id, note) |
61c0663c S |
113 | self._handle_error(response) |
114 | return response | |
e2937118 | 115 | |
e5de3f6c S |
116 | def _real_initialize(self): |
117 | self._login() | |
118 | ||
119 | def _login(self): | |
120 | (username, password) = self._get_login_info() | |
121 | if username is None: | |
78717fc3 | 122 | return |
e5de3f6c S |
123 | |
124 | login_popup = self._download_webpage( | |
dcd4d95c | 125 | self._LOGIN_URL, None, 'Downloading login popup') |
e5de3f6c | 126 | |
d609edf4 S |
127 | def is_logged(webpage): |
128 | return any(p in webpage for p in ['href="https://www.udemy.com/user/logout/', '>Logout<']) | |
129 | ||
130 | # already logged in | |
131 | if is_logged(login_popup): | |
e5de3f6c S |
132 | return |
133 | ||
dcd4d95c | 134 | login_form = self._form_hidden_inputs('login-form', login_popup) |
e5de3f6c | 135 | |
dcd4d95c | 136 | login_form.update({ |
dcd4d95c S |
137 | 'email': username.encode('utf-8'), |
138 | 'password': password.encode('utf-8'), | |
139 | }) | |
140 | ||
5c2266df | 141 | request = sanitized_Request( |
15707c7e | 142 | self._LOGIN_URL, compat_urllib_parse_urlencode(login_form).encode('utf-8')) |
dcd4d95c S |
143 | request.add_header('Referer', self._ORIGIN_URL) |
144 | request.add_header('Origin', self._ORIGIN_URL) | |
145 | ||
146 | response = self._download_webpage( | |
e2937118 | 147 | request, None, 'Logging in as %s' % username) |
e5de3f6c | 148 | |
d609edf4 | 149 | if not is_logged(response): |
dcd4d95c S |
150 | error = self._html_search_regex( |
151 | r'(?s)<div[^>]+class="form-errors[^"]*">(.+?)</div>', | |
152 | response, 'error message', default=None) | |
153 | if error: | |
154 | raise ExtractorError('Unable to login: %s' % error, expected=True) | |
e5de3f6c S |
155 | raise ExtractorError('Unable to log in') |
156 | ||
157 | def _real_extract(self, url): | |
810fb84d | 158 | lecture_id = self._match_id(url) |
e5de3f6c | 159 | |
328f82d5 S |
160 | webpage = self._download_webpage(url, lecture_id) |
161 | ||
162 | course_id = self._search_regex( | |
70cab344 | 163 | (r'data-course-id=["\'](\d+)', r'"id"\s*:\s*(\d+)'), |
a7ba57dc | 164 | webpage, 'course id') |
e5de3f6c | 165 | |
328f82d5 S |
166 | try: |
167 | lecture = self._download_lecture(course_id, lecture_id) | |
168 | except ExtractorError as e: | |
169 | # Error could possibly mean we are not enrolled in the course | |
170 | if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: | |
ff9d5d09 | 171 | self._enroll_course(url, webpage, course_id) |
3092fc40 | 172 | lecture = self._download_lecture(course_id, lecture_id) |
328f82d5 S |
173 | else: |
174 | raise | |
175 | ||
176 | title = lecture['title'] | |
177 | description = lecture.get('description') | |
178 | ||
179 | asset = lecture['asset'] | |
180 | ||
181 | asset_type = asset.get('assetType') or asset.get('asset_type') | |
e2937118 S |
182 | if asset_type != 'Video': |
183 | raise ExtractorError( | |
184 | 'Lecture %s is not a video' % lecture_id, expected=True) | |
e5de3f6c | 185 | |
e2937118 | 186 | stream_url = asset.get('streamUrl') or asset.get('stream_url') |
328f82d5 S |
187 | if stream_url: |
188 | youtube_url = self._search_regex( | |
189 | r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url, 'youtube URL', default=None) | |
190 | if youtube_url: | |
191 | return self.url_result(youtube_url, 'Youtube') | |
e5de3f6c S |
192 | |
193 | video_id = asset['id'] | |
e2937118 | 194 | thumbnail = asset.get('thumbnailUrl') or asset.get('thumbnail_url') |
328f82d5 | 195 | duration = float_or_none(asset.get('data', {}).get('duration')) |
328f82d5 S |
196 | |
197 | formats = [] | |
f0e83681 S |
198 | |
199 | def extract_output_format(src): | |
200 | return { | |
201 | 'url': src['url'], | |
202 | 'format_id': '%sp' % (src.get('label') or format_id), | |
203 | 'width': int_or_none(src.get('width')), | |
204 | 'height': int_or_none(src.get('height')), | |
205 | 'vbr': int_or_none(src.get('video_bitrate_in_kbps')), | |
206 | 'vcodec': src.get('video_codec'), | |
207 | 'fps': int_or_none(src.get('frame_rate')), | |
208 | 'abr': int_or_none(src.get('audio_bitrate_in_kbps')), | |
209 | 'acodec': src.get('audio_codec'), | |
210 | 'asr': int_or_none(src.get('audio_sample_rate')), | |
211 | 'tbr': int_or_none(src.get('total_bitrate_in_kbps')), | |
212 | 'filesize': int_or_none(src.get('file_size_in_bytes')), | |
328f82d5 | 213 | } |
f0e83681 S |
214 | |
215 | outputs = asset.get('data', {}).get('outputs') | |
216 | if not isinstance(outputs, dict): | |
217 | outputs = {} | |
218 | ||
219 | for format_id, output in outputs.items(): | |
220 | if isinstance(output, dict) and output.get('url'): | |
221 | formats.append(extract_output_format(output)) | |
222 | ||
223 | download_urls = asset.get('download_urls') | |
224 | if isinstance(download_urls, dict): | |
225 | video = download_urls.get('Video') | |
226 | if isinstance(video, list): | |
227 | for format_ in video: | |
228 | video_url = format_.get('file') | |
229 | if not video_url: | |
230 | continue | |
231 | format_id = format_.get('label') | |
232 | f = { | |
233 | 'url': format_['file'], | |
234 | 'height': int_or_none(format_id), | |
235 | } | |
236 | if format_id: | |
237 | # Some videos contain additional metadata (e.g. | |
238 | # https://www.udemy.com/ios9-swift/learn/#/lecture/3383208) | |
239 | output = outputs.get(format_id) | |
240 | if isinstance(output, dict): | |
241 | output_format = extract_output_format(output) | |
242 | output_format.update(f) | |
243 | f = output_format | |
244 | else: | |
245 | f['format_id'] = '%sp' % format_id | |
246 | formats.append(f) | |
3b35c342 S |
247 | |
248 | self._sort_formats(formats) | |
e5de3f6c | 249 | |
e5de3f6c S |
250 | return { |
251 | 'id': video_id, | |
252 | 'title': title, | |
253 | 'description': description, | |
254 | 'thumbnail': thumbnail, | |
255 | 'duration': duration, | |
256 | 'formats': formats | |
257 | } | |
258 | ||
259 | ||
260 | class UdemyCourseIE(UdemyIE): | |
261 | IE_NAME = 'udemy:course' | |
328f82d5 | 262 | _VALID_URL = r'https?://www\.udemy\.com/(?P<id>[\da-z-]+)' |
6563837e | 263 | _TESTS = [] |
e5de3f6c S |
264 | |
265 | @classmethod | |
266 | def suitable(cls, url): | |
267 | return False if UdemyIE.suitable(url) else super(UdemyCourseIE, cls).suitable(url) | |
268 | ||
269 | def _real_extract(self, url): | |
328f82d5 S |
270 | course_path = self._match_id(url) |
271 | ||
272 | webpage = self._download_webpage(url, course_path) | |
e5de3f6c | 273 | |
61c0663c | 274 | response = self._download_json( |
e2937118 S |
275 | 'https://www.udemy.com/api-1.1/courses/%s' % course_path, |
276 | course_path, 'Downloading course JSON') | |
e5de3f6c | 277 | |
328f82d5 S |
278 | course_id = response['id'] |
279 | course_title = response.get('title') | |
e5de3f6c | 280 | |
ff9d5d09 | 281 | self._enroll_course(url, webpage, course_id) |
e5de3f6c | 282 | |
61c0663c | 283 | response = self._download_json( |
e2937118 S |
284 | 'https://www.udemy.com/api-1.1/courses/%s/curriculum' % course_id, |
285 | course_id, 'Downloading course curriculum') | |
e5de3f6c | 286 | |
4d402db5 | 287 | entries = [] |
5bafcf65 | 288 | chapter, chapter_number = None, None |
4d402db5 S |
289 | for asset in response: |
290 | asset_type = asset.get('assetType') or asset.get('asset_type') | |
291 | if asset_type == 'Video': | |
292 | asset_id = asset.get('id') | |
293 | if asset_id: | |
294 | entry = { | |
295 | '_type': 'url_transparent', | |
296 | 'url': 'https://www.udemy.com/%s/#/lecture/%s' % (course_path, asset['id']), | |
297 | 'ie_key': UdemyIE.ie_key(), | |
298 | } | |
5bafcf65 S |
299 | if chapter_number: |
300 | entry['chapter_number'] = chapter_number | |
4d402db5 S |
301 | if chapter: |
302 | entry['chapter'] = chapter | |
303 | entries.append(entry) | |
304 | elif asset.get('type') == 'chapter': | |
5bafcf65 | 305 | chapter_number = asset.get('index') or asset.get('object_index') |
4d402db5 | 306 | chapter = asset.get('title') |
e5de3f6c | 307 | |
5f6a1245 | 308 | return self.playlist_result(entries, course_id, course_title) |