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

# coding: utf-8
from __future__ import unicode_literals

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 _real_initialize(self):
        self._login()

    def _login(self):
        username, password = self._get_login_info()
        if username is None:
            return

        # 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 = re.match(self._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)
        self._sort_formats(formats)

        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 = re.match(self._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	# coding: utf-8
	2	from __future__ import unicode_literals
	3
	4	import re
	5
	6	from .common import InfoExtractor
dfe0a3a9	7	from ..utils import (
c9fa84d8	8	clean_html,
dfe0a3a9	9	determine_ext,
dfe0a3a9 S	10	ExtractorError,
	11	float_or_none,
	12	int_or_none,
	13	str_or_none,
	14	url_or_none,
	15	urlencode_postdata,
	16	urljoin,
	17	)
	18
	19
	20	class LecturioBaseIE(InfoExtractor):
c9fa84d8	21	_API_BASE_URL = 'https://app.lecturio.com/api/en/latest/html5/'
dfe0a3a9 S	22	_LOGIN_URL = 'https://app.lecturio.com/en/login'
	23	_NETRC_MACHINE = 'lecturio'
	24
	25	def _real_initialize(self):
	26	self._login()
	27
	28	def _login(self):
	29	username, password = self._get_login_info()
	30	if username is None:
	31	return
	32
	33	# Sets some cookies
	34	_, urlh = self._download_webpage_handle(
	35	self._LOGIN_URL, None, 'Downloading login popup')
	36
	37	def is_logged(url_handle):
7947a1f7	38	return self._LOGIN_URL not in url_handle.geturl()
dfe0a3a9 S	39
	40	# Already logged in
	41	if is_logged(urlh):
	42	return
	43
	44	login_form = {
	45	'signin[email]': username,
	46	'signin[password]': password,
	47	'signin[remember]': 'on',
	48	}
	49
	50	response, urlh = self._download_webpage_handle(
	51	self._LOGIN_URL, None, 'Logging in',
	52	data=urlencode_postdata(login_form))
	53
	54	# Logged in successfully
	55	if is_logged(urlh):
	56	return
	57
	58	errors = self._html_search_regex(
	59	r'(?s)<ul[^>]+class=["\']error_list[^>]+>(.+?)</ul>', response,
	60	'errors', default=None)
	61	if errors:
	62	raise ExtractorError('Unable to login: %s' % errors, expected=True)
	63	raise ExtractorError('Unable to log in')
	64
	65
	66	class LecturioIE(LecturioBaseIE):
386d1fea S	67	_VALID_URL = r'''(?x)
	68	https://
	69	(?:
c9fa84d8 RA	70	app\.lecturio\.com/([^/]+/(?P<nt>[^/?#&]+)\.lecture\|(?:\#/)?lecture/c/\d+/(?P<id>\d+))\|
c9fa84d8 RA	71	(?:www\.)?lecturio\.de/[^/]+/(?P<nt_de>[^/?#&]+)\.vortrag
386d1fea S	72	)
	73	'''
	74	_TESTS = [{
dfe0a3a9	75	'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
c9fa84d8	76	'md5': '9a42cf1d8282a6311bf7211bbde26fde',
dfe0a3a9 S	77	'info_dict': {
	78	'id': '39634',
	79	'ext': 'mp4',
c9fa84d8	80	'title': 'Important Concepts and Terms — Introduction to Microbiology',
dfe0a3a9 S	81	},
dfe0a3a9 S	82	'skip': 'Requires lecturio account credentials',
386d1fea S	83	}, {
	84	'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
	85	'only_matching': True,
c9fa84d8 RA	86	}, {
	87	'url': 'https://app.lecturio.com/#/lecture/c/6434/39634',
	88	'only_matching': True,
386d1fea	89	}]
dfe0a3a9 S	90
dfe0a3a9 S	91	_CC_LANGS = {
c9fa84d8 RA	92	'Arabic': 'ar',
c9fa84d8 RA	93	'Bulgarian': 'bg',
dfe0a3a9 S	94	'German': 'de',
	95	'English': 'en',
	96	'Spanish': 'es',
c9fa84d8	97	'Persian': 'fa',
dfe0a3a9	98	'French': 'fr',
c9fa84d8	99	'Japanese': 'ja',
dfe0a3a9	100	'Polish': 'pl',
c9fa84d8	101	'Pashto': 'ps',
dfe0a3a9 S	102	'Russian': 'ru',
	103	}
	104
	105	def _real_extract(self, url):
386d1fea	106	mobj = re.match(self._VALID_URL, url)
c9fa84d8 RA	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)
dfe0a3a9	113	title = video['title'].strip()
c9fa84d8 RA	114	if not lecture_id:
	115	pid = video.get('productId') or video.get('uid')
	116	if pid:
	117	spid = pid.split('_')
	118	if spid and len(spid) == 2:
	119	lecture_id = spid[1]
dfe0a3a9 S	120
	121	formats = []
	122	for format_ in video['content']['media']:
	123	if not isinstance(format_, dict):
	124	continue
	125	file_ = format_.get('file')
	126	if not file_:
	127	continue
	128	ext = determine_ext(file_)
	129	if ext == 'smil':
	130	# smil contains only broken RTMP formats anyway
	131	continue
	132	file_url = url_or_none(file_)
	133	if not file_url:
	134	continue
	135	label = str_or_none(format_.get('label'))
	136	filesize = int_or_none(format_.get('fileSize'))
c9fa84d8	137	f = {
dfe0a3a9 S	138	'url': file_url,
	139	'format_id': label,
	140	'filesize': float_or_none(filesize, invscale=1000)
c9fa84d8 RA	141	}
	142	if label:
	143	mobj = re.match(r'(\d+)p\s*\(([^)]+)\)', label)
	144	if mobj:
	145	f.update({
	146	'format_id': mobj.group(2),
	147	'height': int(mobj.group(1)),
	148	})
	149	formats.append(f)
dfe0a3a9 S	150	self._sort_formats(formats)
	151
	152	subtitles = {}
	153	automatic_captions = {}
c9fa84d8 RA	154	captions = video.get('captions') or []
	155	for cc in captions:
	156	cc_url = cc.get('url')
dfe0a3a9 S	157	if not cc_url:
dfe0a3a9 S	158	continue
c9fa84d8 RA	159	cc_label = cc.get('translatedCode')
c9fa84d8 RA	160	lang = cc.get('languageCode') or self._search_regex(
0a05cfab S	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',
	165	default=None)
	166	sub_dict = (automatic_captions
	167	if 'auto-translated' in cc_label or original_lang
	168	else subtitles)
dfe0a3a9 S	169	sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({
	170	'url': cc_url,
	171	})
	172
	173	return {
c9fa84d8	174	'id': lecture_id or nt,
dfe0a3a9 S	175	'title': title,
	176	'formats': formats,
	177	'subtitles': subtitles,
	178	'automatic_captions': automatic_captions,
	179	}
	180
	181
	182	class LecturioCourseIE(LecturioBaseIE):
c9fa84d8 RA	183	_VALID_URL = r'https://app\.lecturio\.com/(?:[^/]+/(?P<nt>[^/?#&]+)\.course\|(?:#/)?course/c/(?P<id>\d+))'
c9fa84d8 RA	184	_TESTS = [{
dfe0a3a9 S	185	'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
	186	'info_dict': {
	187	'id': 'microbiology-introduction',
	188	'title': 'Microbiology: Introduction',
c9fa84d8	189	'description': 'md5:13da8500c25880c6016ae1e6d78c386a',
dfe0a3a9 S	190	},
	191	'playlist_count': 45,
	192	'skip': 'Requires lecturio account credentials',
c9fa84d8 RA	193	}, {
	194	'url': 'https://app.lecturio.com/#/course/c/6434',
	195	'only_matching': True,
	196	}]
dfe0a3a9 S	197
dfe0a3a9 S	198	def _real_extract(self, url):
c9fa84d8 RA	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)
dfe0a3a9	204	entries = []
c9fa84d8 RA	205	for lecture in course.get('lectures', []):
	206	lecture_id = str_or_none(lecture.get('id'))
	207	lecture_url = lecture.get('url')
	208	if lecture_url:
	209	lecture_url = urljoin(url, lecture_url)
	210	else:
	211	lecture_url = 'https://app.lecturio.com/#/lecture/c/%s/%s' % (course_id, lecture_id)
dfe0a3a9 S	212	entries.append(self.url_result(
dfe0a3a9 S	213	lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
c9fa84d8 RA	214	return self.playlist_result(
	215	entries, display_id, course.get('title'),
	216	clean_html(course.get('description')))
386d1fea S	217
	218
	219	class LecturioDeCourseIE(LecturioBaseIE):
	220	_VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P<id>[^/?#&]+)\.kurs'
	221	_TEST = {
	222	'url': 'https://www.lecturio.de/jura/grundrechte.kurs',
	223	'only_matching': True,
	224	}
	225
	226	def _real_extract(self, url):
	227	display_id = self._match_id(url)
	228
	229	webpage = self._download_webpage(url, display_id)
	230
	231	entries = []
	232	for mobj in re.finditer(
	233	r'(?s)<td[^>]+\bdata-lecture-id=["\'](?P<id>\d+).+?\bhref=(["\'])(?P<url>(?:(?!\2).)+\.vortrag)\b[^>]+>',
	234	webpage):
	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))
	239
	240	title = self._search_regex(
	241	r'<h1[^>]*>([^<]+)', webpage, 'title', default=None)
	242
	243	return self.playlist_result(entries, display_id, title)