[yt-dlp.git] / yt_dlp / extractor / lecturio.py

import re

from .common import InfoExtractor
from ..utils import (
    clean_html,
    determine_ext,
    ExtractorError,
    float_or_none,
    int_or_none,
    str_or_none,
    url_or_none,
    urlencode_postdata,
    urljoin,
)


class LecturioBaseIE(InfoExtractor):
    _API_BASE_URL = 'https://app.lecturio.com/api/en/latest/html5/'
    _LOGIN_URL = 'https://app.lecturio.com/en/login'
    _NETRC_MACHINE = 'lecturio'

    def _perform_login(self, username, password):
        # Sets some cookies
        _, urlh = self._download_webpage_handle(
            self._LOGIN_URL, None, 'Downloading login popup')

        def is_logged(url_handle):
            return self._LOGIN_URL not in url_handle.geturl()

        # Already logged in
        if is_logged(urlh):
            return

        login_form = {
            'signin[email]': username,
            'signin[password]': password,
            'signin[remember]': 'on',
        }

        response, urlh = self._download_webpage_handle(
            self._LOGIN_URL, None, 'Logging in',
            data=urlencode_postdata(login_form))

        # Logged in successfully
        if is_logged(urlh):
            return

        errors = self._html_search_regex(
            r'(?s)<ul[^>]+class=["\']error_list[^>]+>(.+?)</ul>', response,
            'errors', default=None)
        if errors:
            raise ExtractorError('Unable to login: %s' % errors, expected=True)
        raise ExtractorError('Unable to log in')


class LecturioIE(LecturioBaseIE):
    _VALID_URL = r'''(?x)
                    https://
                        (?:
                            app\.lecturio\.com/([^/]+/(?P<nt>[^/?#&]+)\.lecture|(?:\#/)?lecture/c/\d+/(?P<id>\d+))|
                            (?:www\.)?lecturio\.de/[^/]+/(?P<nt_de>[^/?#&]+)\.vortrag
                        )
                    '''
    _TESTS = [{
        'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
        'md5': '9a42cf1d8282a6311bf7211bbde26fde',
        'info_dict': {
            'id': '39634',
            'ext': 'mp4',
            'title': 'Important Concepts and Terms — Introduction to Microbiology',
        },
        'skip': 'Requires lecturio account credentials',
    }, {
        'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
        'only_matching': True,
    }, {
        'url': 'https://app.lecturio.com/#/lecture/c/6434/39634',
        'only_matching': True,
    }]

    _CC_LANGS = {
        'Arabic': 'ar',
        'Bulgarian': 'bg',
        'German': 'de',
        'English': 'en',
        'Spanish': 'es',
        'Persian': 'fa',
        'French': 'fr',
        'Japanese': 'ja',
        'Polish': 'pl',
        'Pashto': 'ps',
        'Russian': 'ru',
    }

    def _real_extract(self, url):
        mobj = self._match_valid_url(url)
        nt = mobj.group('nt') or mobj.group('nt_de')
        lecture_id = mobj.group('id')
        display_id = nt or lecture_id
        api_path = 'lectures/' + lecture_id if lecture_id else 'lecture/' + nt + '.json'
        video = self._download_json(
            self._API_BASE_URL + api_path, display_id)
        title = video['title'].strip()
        if not lecture_id:
            pid = video.get('productId') or video.get('uid')
            if pid:
                spid = pid.split('_')
                if spid and len(spid) == 2:
                    lecture_id = spid[1]

        formats = []
        for format_ in video['content']['media']:
            if not isinstance(format_, dict):
                continue
            file_ = format_.get('file')
            if not file_:
                continue
            ext = determine_ext(file_)
            if ext == 'smil':
                # smil contains only broken RTMP formats anyway
                continue
            file_url = url_or_none(file_)
            if not file_url:
                continue
            label = str_or_none(format_.get('label'))
            filesize = int_or_none(format_.get('fileSize'))
            f = {
                'url': file_url,
                'format_id': label,
                'filesize': float_or_none(filesize, invscale=1000)
            }
            if label:
                mobj = re.match(r'(\d+)p\s*\(([^)]+)\)', label)
                if mobj:
                    f.update({
                        'format_id': mobj.group(2),
                        'height': int(mobj.group(1)),
                    })
            formats.append(f)

        subtitles = {}
        automatic_captions = {}
        captions = video.get('captions') or []
        for cc in captions:
            cc_url = cc.get('url')
            if not cc_url:
                continue
            cc_label = cc.get('translatedCode')
            lang = cc.get('languageCode') or self._search_regex(
                r'/([a-z]{2})_', cc_url, 'lang',
                default=cc_label.split()[0] if cc_label else 'en')
            original_lang = self._search_regex(
                r'/[a-z]{2}_([a-z]{2})_', cc_url, 'original lang',
                default=None)
            sub_dict = (automatic_captions
                        if 'auto-translated' in cc_label or original_lang
                        else subtitles)
            sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({
                'url': cc_url,
            })

        return {
            'id': lecture_id or nt,
            'title': title,
            'formats': formats,
            'subtitles': subtitles,
            'automatic_captions': automatic_captions,
        }


class LecturioCourseIE(LecturioBaseIE):
    _VALID_URL = r'https://app\.lecturio\.com/(?:[^/]+/(?P<nt>[^/?#&]+)\.course|(?:#/)?course/c/(?P<id>\d+))'
    _TESTS = [{
        'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
        'info_dict': {
            'id': 'microbiology-introduction',
            'title': 'Microbiology: Introduction',
            'description': 'md5:13da8500c25880c6016ae1e6d78c386a',
        },
        'playlist_count': 45,
        'skip': 'Requires lecturio account credentials',
    }, {
        'url': 'https://app.lecturio.com/#/course/c/6434',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        nt, course_id = self._match_valid_url(url).groups()
        display_id = nt or course_id
        api_path = 'courses/' + course_id if course_id else 'course/content/' + nt + '.json'
        course = self._download_json(
            self._API_BASE_URL + api_path, display_id)
        entries = []
        for lecture in course.get('lectures', []):
            lecture_id = str_or_none(lecture.get('id'))
            lecture_url = lecture.get('url')
            if lecture_url:
                lecture_url = urljoin(url, lecture_url)
            else:
                lecture_url = 'https://app.lecturio.com/#/lecture/c/%s/%s' % (course_id, lecture_id)
            entries.append(self.url_result(
                lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
        return self.playlist_result(
            entries, display_id, course.get('title'),
            clean_html(course.get('description')))


class LecturioDeCourseIE(LecturioBaseIE):
    _VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P<id>[^/?#&]+)\.kurs'
    _TEST = {
        'url': 'https://www.lecturio.de/jura/grundrechte.kurs',
        'only_matching': True,
    }

    def _real_extract(self, url):
        display_id = self._match_id(url)

        webpage = self._download_webpage(url, display_id)

        entries = []
        for mobj in re.finditer(
                r'(?s)<td[^>]+\bdata-lecture-id=["\'](?P<id>\d+).+?\bhref=(["\'])(?P<url>(?:(?!\2).)+\.vortrag)\b[^>]+>',
                webpage):
            lecture_url = urljoin(url, mobj.group('url'))
            lecture_id = mobj.group('id')
            entries.append(self.url_result(
                lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))

        title = self._search_regex(
            r'<h1[^>]*>([^<]+)', webpage, 'title', default=None)

        return self.playlist_result(entries, display_id, title)
Commit	Line	Data
dfe0a3a9 S	1	import re
	2
	3	from .common import InfoExtractor
dfe0a3a9	4	from ..utils import (
c9fa84d8	5	clean_html,
dfe0a3a9	6	determine_ext,
dfe0a3a9 S	7	ExtractorError,
	8	float_or_none,
	9	int_or_none,
	10	str_or_none,
	11	url_or_none,
	12	urlencode_postdata,
	13	urljoin,
	14	)
	15
	16
	17	class LecturioBaseIE(InfoExtractor):
c9fa84d8	18	_API_BASE_URL = 'https://app.lecturio.com/api/en/latest/html5/'
dfe0a3a9 S	19	_LOGIN_URL = 'https://app.lecturio.com/en/login'
	20	_NETRC_MACHINE = 'lecturio'
	21
52efa4b3	22	def _perform_login(self, username, password):
dfe0a3a9 S	23	# Sets some cookies
	24	_, urlh = self._download_webpage_handle(
	25	self._LOGIN_URL, None, 'Downloading login popup')
	26
	27	def is_logged(url_handle):
7947a1f7	28	return self._LOGIN_URL not in url_handle.geturl()
dfe0a3a9 S	29
	30	# Already logged in
	31	if is_logged(urlh):
	32	return
	33
	34	login_form = {
	35	'signin[email]': username,
	36	'signin[password]': password,
	37	'signin[remember]': 'on',
	38	}
	39
	40	response, urlh = self._download_webpage_handle(
	41	self._LOGIN_URL, None, 'Logging in',
	42	data=urlencode_postdata(login_form))
	43
	44	# Logged in successfully
	45	if is_logged(urlh):
	46	return
	47
	48	errors = self._html_search_regex(
	49	r'(?s)<ul[^>]+class=["\']error_list[^>]+>(.+?)</ul>', response,
	50	'errors', default=None)
	51	if errors:
	52	raise ExtractorError('Unable to login: %s' % errors, expected=True)
	53	raise ExtractorError('Unable to log in')
	54
	55
	56	class LecturioIE(LecturioBaseIE):
386d1fea S	57	_VALID_URL = r'''(?x)
	58	https://
	59	(?:
c9fa84d8 RA	60	app\.lecturio\.com/([^/]+/(?P<nt>[^/?#&]+)\.lecture\|(?:\#/)?lecture/c/\d+/(?P<id>\d+))\|
c9fa84d8 RA	61	(?:www\.)?lecturio\.de/[^/]+/(?P<nt_de>[^/?#&]+)\.vortrag
386d1fea S	62	)
	63	'''
	64	_TESTS = [{
dfe0a3a9	65	'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
c9fa84d8	66	'md5': '9a42cf1d8282a6311bf7211bbde26fde',
dfe0a3a9 S	67	'info_dict': {
	68	'id': '39634',
	69	'ext': 'mp4',
c9fa84d8	70	'title': 'Important Concepts and Terms — Introduction to Microbiology',
dfe0a3a9 S	71	},
dfe0a3a9 S	72	'skip': 'Requires lecturio account credentials',
386d1fea S	73	}, {
	74	'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
	75	'only_matching': True,
c9fa84d8 RA	76	}, {
	77	'url': 'https://app.lecturio.com/#/lecture/c/6434/39634',
	78	'only_matching': True,
386d1fea	79	}]
dfe0a3a9 S	80
dfe0a3a9 S	81	_CC_LANGS = {
c9fa84d8 RA	82	'Arabic': 'ar',
c9fa84d8 RA	83	'Bulgarian': 'bg',
dfe0a3a9 S	84	'German': 'de',
	85	'English': 'en',
	86	'Spanish': 'es',
c9fa84d8	87	'Persian': 'fa',
dfe0a3a9	88	'French': 'fr',
c9fa84d8	89	'Japanese': 'ja',
dfe0a3a9	90	'Polish': 'pl',
c9fa84d8	91	'Pashto': 'ps',
dfe0a3a9 S	92	'Russian': 'ru',
	93	}
	94
	95	def _real_extract(self, url):
5ad28e7f	96	mobj = self._match_valid_url(url)
c9fa84d8 RA	97	nt = mobj.group('nt') or mobj.group('nt_de')
	98	lecture_id = mobj.group('id')
	99	display_id = nt or lecture_id
	100	api_path = 'lectures/' + lecture_id if lecture_id else 'lecture/' + nt + '.json'
	101	video = self._download_json(
	102	self._API_BASE_URL + api_path, display_id)
dfe0a3a9	103	title = video['title'].strip()
c9fa84d8 RA	104	if not lecture_id:
	105	pid = video.get('productId') or video.get('uid')
	106	if pid:
	107	spid = pid.split('_')
	108	if spid and len(spid) == 2:
	109	lecture_id = spid[1]
dfe0a3a9 S	110
	111	formats = []
	112	for format_ in video['content']['media']:
	113	if not isinstance(format_, dict):
	114	continue
	115	file_ = format_.get('file')
	116	if not file_:
	117	continue
	118	ext = determine_ext(file_)
	119	if ext == 'smil':
	120	# smil contains only broken RTMP formats anyway
	121	continue
	122	file_url = url_or_none(file_)
	123	if not file_url:
	124	continue
	125	label = str_or_none(format_.get('label'))
	126	filesize = int_or_none(format_.get('fileSize'))
c9fa84d8	127	f = {
dfe0a3a9 S	128	'url': file_url,
	129	'format_id': label,
	130	'filesize': float_or_none(filesize, invscale=1000)
c9fa84d8 RA	131	}
	132	if label:
	133	mobj = re.match(r'(\d+)p\s*\(([^)]+)\)', label)
	134	if mobj:
	135	f.update({
	136	'format_id': mobj.group(2),
	137	'height': int(mobj.group(1)),
	138	})
	139	formats.append(f)
dfe0a3a9 S	140
	141	subtitles = {}
	142	automatic_captions = {}
c9fa84d8 RA	143	captions = video.get('captions') or []
	144	for cc in captions:
	145	cc_url = cc.get('url')
dfe0a3a9 S	146	if not cc_url:
dfe0a3a9 S	147	continue
c9fa84d8 RA	148	cc_label = cc.get('translatedCode')
c9fa84d8 RA	149	lang = cc.get('languageCode') or self._search_regex(
0a05cfab S	150	r'/([a-z]{2})_', cc_url, 'lang',
	151	default=cc_label.split()[0] if cc_label else 'en')
	152	original_lang = self._search_regex(
	153	r'/[a-z]{2}_([a-z]{2})_', cc_url, 'original lang',
	154	default=None)
	155	sub_dict = (automatic_captions
	156	if 'auto-translated' in cc_label or original_lang
	157	else subtitles)
dfe0a3a9 S	158	sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({
	159	'url': cc_url,
	160	})
	161
	162	return {
c9fa84d8	163	'id': lecture_id or nt,
dfe0a3a9 S	164	'title': title,
	165	'formats': formats,
	166	'subtitles': subtitles,
	167	'automatic_captions': automatic_captions,
	168	}
	169
	170
	171	class LecturioCourseIE(LecturioBaseIE):
c9fa84d8 RA	172	_VALID_URL = r'https://app\.lecturio\.com/(?:[^/]+/(?P<nt>[^/?#&]+)\.course\|(?:#/)?course/c/(?P<id>\d+))'
c9fa84d8 RA	173	_TESTS = [{
dfe0a3a9 S	174	'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
	175	'info_dict': {
	176	'id': 'microbiology-introduction',
	177	'title': 'Microbiology: Introduction',
c9fa84d8	178	'description': 'md5:13da8500c25880c6016ae1e6d78c386a',
dfe0a3a9 S	179	},
	180	'playlist_count': 45,
	181	'skip': 'Requires lecturio account credentials',
c9fa84d8 RA	182	}, {
	183	'url': 'https://app.lecturio.com/#/course/c/6434',
	184	'only_matching': True,
	185	}]
dfe0a3a9 S	186
dfe0a3a9 S	187	def _real_extract(self, url):
5ad28e7f	188	nt, course_id = self._match_valid_url(url).groups()
c9fa84d8 RA	189	display_id = nt or course_id
	190	api_path = 'courses/' + course_id if course_id else 'course/content/' + nt + '.json'
	191	course = self._download_json(
	192	self._API_BASE_URL + api_path, display_id)
dfe0a3a9	193	entries = []
c9fa84d8 RA	194	for lecture in course.get('lectures', []):
	195	lecture_id = str_or_none(lecture.get('id'))
	196	lecture_url = lecture.get('url')
	197	if lecture_url:
	198	lecture_url = urljoin(url, lecture_url)
	199	else:
	200	lecture_url = 'https://app.lecturio.com/#/lecture/c/%s/%s' % (course_id, lecture_id)
dfe0a3a9 S	201	entries.append(self.url_result(
dfe0a3a9 S	202	lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
c9fa84d8 RA	203	return self.playlist_result(
	204	entries, display_id, course.get('title'),
	205	clean_html(course.get('description')))
386d1fea S	206
	207
	208	class LecturioDeCourseIE(LecturioBaseIE):
	209	_VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P<id>[^/?#&]+)\.kurs'
	210	_TEST = {
	211	'url': 'https://www.lecturio.de/jura/grundrechte.kurs',
	212	'only_matching': True,
	213	}
	214
	215	def _real_extract(self, url):
	216	display_id = self._match_id(url)
	217
	218	webpage = self._download_webpage(url, display_id)
	219
	220	entries = []
	221	for mobj in re.finditer(
	222	r'(?s)<td[^>]+\bdata-lecture-id=["\'](?P<id>\d+).+?\bhref=(["\'])(?P<url>(?:(?!\2).)+\.vortrag)\b[^>]+>',
	223	webpage):
	224	lecture_url = urljoin(url, mobj.group('url'))
	225	lecture_id = mobj.group('id')
	226	entries.append(self.url_result(
	227	lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
	228
	229	title = self._search_regex(
	230	r'<h1[^>]*>([^<]+)', webpage, 'title', default=None)
	231
	232	return self.playlist_result(entries, display_id, title)