2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_str
21 class LecturioBaseIE(InfoExtractor):
22 _API_BASE_URL = 'https://app.lecturio.com/api/en/latest/html5/'
23 _LOGIN_URL = 'https://app.lecturio.com/en/login'
24 _NETRC_MACHINE = 'lecturio'
26 def _real_initialize(self):
30 username, password = self._get_login_info()
35 _, urlh = self._download_webpage_handle(
36 self._LOGIN_URL, None, 'Downloading login popup')
38 def is_logged(url_handle):
39 return self._LOGIN_URL not in compat_str(url_handle.geturl())
46 'signin[email]': username,
47 'signin[password]': password,
48 'signin[remember]': 'on',
51 response, urlh = self._download_webpage_handle(
52 self._LOGIN_URL, None, 'Logging in',
53 data=urlencode_postdata(login_form))
55 # Logged in successfully
59 errors = self._html_search_regex(
60 r'(?s)<ul[^>]+class=["\']error_list[^>]+>(.+?)</ul>', response,
61 'errors', default=None)
63 raise ExtractorError('Unable to login: %s' % errors, expected=True)
64 raise ExtractorError('Unable to log in')
67 class LecturioIE(LecturioBaseIE):
71 app\.lecturio\.com/([^/]+/(?P<nt>[^/?#&]+)\.lecture|(?:\#/)?lecture/c/\d+/(?P<id>\d+))|
72 (?:www\.)?lecturio\.de/[^/]+/(?P<nt_de>[^/?#&]+)\.vortrag
76 'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
77 'md5': '9a42cf1d8282a6311bf7211bbde26fde',
81 'title': 'Important Concepts and Terms — Introduction to Microbiology',
83 'skip': 'Requires lecturio account credentials',
85 'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
86 'only_matching': True,
88 'url': 'https://app.lecturio.com/#/lecture/c/6434/39634',
89 'only_matching': True,
106 def _real_extract(self, url):
107 mobj = re.match(self._VALID_URL, url)
108 nt = mobj.group('nt') or mobj.group('nt_de')
109 lecture_id = mobj.group('id')
110 display_id = nt or lecture_id
111 api_path = 'lectures/' + lecture_id if lecture_id else 'lecture/' + nt + '.json'
112 video = self._download_json(
113 self._API_BASE_URL + api_path, display_id)
114 title = video['title'].strip()
116 pid = video.get('productId') or video.get('uid')
118 spid = pid.split('_')
119 if spid and len(spid) == 2:
123 for format_ in video['content']['media']:
124 if not isinstance(format_, dict):
126 file_ = format_.get('file')
129 ext = determine_ext(file_)
131 # smil contains only broken RTMP formats anyway
133 file_url = url_or_none(file_)
136 label = str_or_none(format_.get('label'))
137 filesize = int_or_none(format_.get('fileSize'))
141 'filesize': float_or_none(filesize, invscale=1000)
144 mobj = re.match(r'(\d+)p\s*\(([^)]+)\)', label)
147 'format_id': mobj.group(2),
148 'height': int(mobj.group(1)),
151 self._sort_formats(formats)
154 automatic_captions = {}
155 captions = video.get('captions') or []
157 cc_url = cc.get('url')
160 cc_label = cc.get('translatedCode')
161 lang = cc.get('languageCode') or self._search_regex(
162 r'/([a-z]{2})_', cc_url, 'lang',
163 default=cc_label.split()[0] if cc_label else 'en')
164 original_lang = self._search_regex(
165 r'/[a-z]{2}_([a-z]{2})_', cc_url, 'original lang',
167 sub_dict = (automatic_captions
168 if 'auto-translated' in cc_label or original_lang
170 sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({
175 'id': lecture_id or nt,
178 'subtitles': subtitles,
179 'automatic_captions': automatic_captions,
183 class LecturioCourseIE(LecturioBaseIE):
184 _VALID_URL = r'https://app\.lecturio\.com/(?:[^/]+/(?P<nt>[^/?#&]+)\.course|(?:#/)?course/c/(?P<id>\d+))'
186 'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
188 'id': 'microbiology-introduction',
189 'title': 'Microbiology: Introduction',
190 'description': 'md5:13da8500c25880c6016ae1e6d78c386a',
192 'playlist_count': 45,
193 'skip': 'Requires lecturio account credentials',
195 'url': 'https://app.lecturio.com/#/course/c/6434',
196 'only_matching': True,
199 def _real_extract(self, url):
200 nt, course_id = re.match(self._VALID_URL, url).groups()
201 display_id = nt or course_id
202 api_path = 'courses/' + course_id if course_id else 'course/content/' + nt + '.json'
203 course = self._download_json(
204 self._API_BASE_URL + api_path, display_id)
206 for lecture in course.get('lectures', []):
207 lecture_id = str_or_none(lecture.get('id'))
208 lecture_url = lecture.get('url')
210 lecture_url = urljoin(url, lecture_url)
212 lecture_url = 'https://app.lecturio.com/#/lecture/c/%s/%s' % (course_id, lecture_id)
213 entries.append(self.url_result(
214 lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
215 return self.playlist_result(
216 entries, display_id, course.get('title'),
217 clean_html(course.get('description')))
220 class LecturioDeCourseIE(LecturioBaseIE):
221 _VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P<id>[^/?#&]+)\.kurs'
223 'url': 'https://www.lecturio.de/jura/grundrechte.kurs',
224 'only_matching': True,
227 def _real_extract(self, url):
228 display_id = self._match_id(url)
230 webpage = self._download_webpage(url, display_id)
233 for mobj in re.finditer(
234 r'(?s)<td[^>]+\bdata-lecture-id=["\'](?P<id>\d+).+?\bhref=(["\'])(?P<url>(?:(?!\2).)+\.vortrag)\b[^>]+>',
236 lecture_url = urljoin(url, mobj.group('url'))
237 lecture_id = mobj.group('id')
238 entries.append(self.url_result(
239 lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
241 title = self._search_regex(
242 r'<h1[^>]*>([^<]+)', webpage, 'title', default=None)
244 return self.playlist_result(entries, display_id, title)