2 from __future__ import unicode_literals
6 from .common import InfoExtractor
20 class LecturioBaseIE(InfoExtractor):
21 _API_BASE_URL = 'https://app.lecturio.com/api/en/latest/html5/'
22 _LOGIN_URL = 'https://app.lecturio.com/en/login'
23 _NETRC_MACHINE = 'lecturio'
25 def _real_initialize(self):
29 username, password = self._get_login_info()
34 _, urlh = self._download_webpage_handle(
35 self._LOGIN_URL, None, 'Downloading login popup')
37 def is_logged(url_handle):
38 return self._LOGIN_URL not in url_handle.geturl()
45 'signin[email]': username,
46 'signin[password]': password,
47 'signin[remember]': 'on',
50 response, urlh = self._download_webpage_handle(
51 self._LOGIN_URL, None, 'Logging in',
52 data=urlencode_postdata(login_form))
54 # Logged in successfully
58 errors = self._html_search_regex(
59 r'(?s)<ul[^>]+class=["\']error_list[^>]+>(.+?)</ul>', response,
60 'errors', default=None)
62 raise ExtractorError('Unable to login: %s' % errors, expected=True)
63 raise ExtractorError('Unable to log in')
66 class LecturioIE(LecturioBaseIE):
70 app\.lecturio\.com/([^/]+/(?P<nt>[^/?#&]+)\.lecture|(?:\#/)?lecture/c/\d+/(?P<id>\d+))|
71 (?:www\.)?lecturio\.de/[^/]+/(?P<nt_de>[^/?#&]+)\.vortrag
75 'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
76 'md5': '9a42cf1d8282a6311bf7211bbde26fde',
80 'title': 'Important Concepts and Terms — Introduction to Microbiology',
82 'skip': 'Requires lecturio account credentials',
84 'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
85 'only_matching': True,
87 'url': 'https://app.lecturio.com/#/lecture/c/6434/39634',
88 'only_matching': True,
105 def _real_extract(self, url):
106 mobj = re.match(self._VALID_URL, url)
107 nt = mobj.group('nt') or mobj.group('nt_de')
108 lecture_id = mobj.group('id')
109 display_id = nt or lecture_id
110 api_path = 'lectures/' + lecture_id if lecture_id else 'lecture/' + nt + '.json'
111 video = self._download_json(
112 self._API_BASE_URL + api_path, display_id)
113 title = video['title'].strip()
115 pid = video.get('productId') or video.get('uid')
117 spid = pid.split('_')
118 if spid and len(spid) == 2:
122 for format_ in video['content']['media']:
123 if not isinstance(format_, dict):
125 file_ = format_.get('file')
128 ext = determine_ext(file_)
130 # smil contains only broken RTMP formats anyway
132 file_url = url_or_none(file_)
135 label = str_or_none(format_.get('label'))
136 filesize = int_or_none(format_.get('fileSize'))
140 'filesize': float_or_none(filesize, invscale=1000)
143 mobj = re.match(r'(\d+)p\s*\(([^)]+)\)', label)
146 'format_id': mobj.group(2),
147 'height': int(mobj.group(1)),
150 self._sort_formats(formats)
153 automatic_captions = {}
154 captions = video.get('captions') or []
156 cc_url = cc.get('url')
159 cc_label = cc.get('translatedCode')
160 lang = cc.get('languageCode') or self._search_regex(
161 r'/([a-z]{2})_', cc_url, 'lang',
162 default=cc_label.split()[0] if cc_label else 'en')
163 original_lang = self._search_regex(
164 r'/[a-z]{2}_([a-z]{2})_', cc_url, 'original lang',
166 sub_dict = (automatic_captions
167 if 'auto-translated' in cc_label or original_lang
169 sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({
174 'id': lecture_id or nt,
177 'subtitles': subtitles,
178 'automatic_captions': automatic_captions,
182 class LecturioCourseIE(LecturioBaseIE):
183 _VALID_URL = r'https://app\.lecturio\.com/(?:[^/]+/(?P<nt>[^/?#&]+)\.course|(?:#/)?course/c/(?P<id>\d+))'
185 'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
187 'id': 'microbiology-introduction',
188 'title': 'Microbiology: Introduction',
189 'description': 'md5:13da8500c25880c6016ae1e6d78c386a',
191 'playlist_count': 45,
192 'skip': 'Requires lecturio account credentials',
194 'url': 'https://app.lecturio.com/#/course/c/6434',
195 'only_matching': True,
198 def _real_extract(self, url):
199 nt, course_id = re.match(self._VALID_URL, url).groups()
200 display_id = nt or course_id
201 api_path = 'courses/' + course_id if course_id else 'course/content/' + nt + '.json'
202 course = self._download_json(
203 self._API_BASE_URL + api_path, display_id)
205 for lecture in course.get('lectures', []):
206 lecture_id = str_or_none(lecture.get('id'))
207 lecture_url = lecture.get('url')
209 lecture_url = urljoin(url, lecture_url)
211 lecture_url = 'https://app.lecturio.com/#/lecture/c/%s/%s' % (course_id, lecture_id)
212 entries.append(self.url_result(
213 lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
214 return self.playlist_result(
215 entries, display_id, course.get('title'),
216 clean_html(course.get('description')))
219 class LecturioDeCourseIE(LecturioBaseIE):
220 _VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P<id>[^/?#&]+)\.kurs'
222 'url': 'https://www.lecturio.de/jura/grundrechte.kurs',
223 'only_matching': True,
226 def _real_extract(self, url):
227 display_id = self._match_id(url)
229 webpage = self._download_webpage(url, display_id)
232 for mobj in re.finditer(
233 r'(?s)<td[^>]+\bdata-lecture-id=["\'](?P<id>\d+).+?\bhref=(["\'])(?P<url>(?:(?!\2).)+\.vortrag)\b[^>]+>',
235 lecture_url = urljoin(url, mobj.group('url'))
236 lecture_id = mobj.group('id')
237 entries.append(self.url_result(
238 lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
240 title = self._search_regex(
241 r'<h1[^>]*>([^<]+)', webpage, 'title', default=None)
243 return self.playlist_result(entries, display_id, title)