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

import re

from .common import InfoExtractor
from .wistia import WistiaIE
from ..utils import (
    ExtractorError,
    clean_html,
    get_element_by_class,
    int_or_none,
    strip_or_none,
    urlencode_postdata,
    urljoin,
)


class TeachableBaseIE(InfoExtractor):
    _NETRC_MACHINE = 'teachable'
    _URL_PREFIX = 'teachable:'

    _SITES = {
        # Only notable ones here
        'v1.upskillcourses.com': 'upskill',
        'gns3.teachable.com': 'gns3',
        'academyhacker.com': 'academyhacker',
        'stackskills.com': 'stackskills',
        'market.saleshacker.com': 'saleshacker',
        'learnability.org': 'learnability',
        'edurila.com': 'edurila',
        'courses.workitdaily.com': 'workitdaily',
    }

    _VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys()))

    def _real_initialize(self):
        self._logged_in = False

    def _login(self, site):
        if self._logged_in:
            return

        username, password = self._get_login_info(netrc_machine=self._SITES.get(site, site))
        if username is None:
            return

        login_page, urlh = self._download_webpage_handle(
            'https://%s/sign_in' % site, None,
            'Downloading %s login page' % site)

        def is_logged(webpage):
            return any(re.search(p, webpage) for p in (
                r'class=["\']user-signout',
                r'<a[^>]+\bhref=["\']/sign_out',
                r'Log\s+[Oo]ut\s*<'))

        if is_logged(login_page):
            self._logged_in = True
            return

        login_url = urlh.url

        login_form = self._hidden_inputs(login_page)

        login_form.update({
            'user[email]': username,
            'user[password]': password,
        })

        post_url = self._search_regex(
            r'<form[^>]+action=(["\'])(?P<url>(?:(?!\1).)+)\1', login_page,
            'post url', default=login_url, group='url')

        if not post_url.startswith('http'):
            post_url = urljoin(login_url, post_url)

        response = self._download_webpage(
            post_url, None, 'Logging in to %s' % site,
            data=urlencode_postdata(login_form),
            headers={
                'Content-Type': 'application/x-www-form-urlencoded',
                'Referer': login_url,
            })

        if '>I accept the new Privacy Policy<' in response:
            raise ExtractorError(
                'Unable to login: %s asks you to accept new Privacy Policy. '
                'Go to https://%s/ and accept.' % (site, site), expected=True)

        # Successful login
        if is_logged(response):
            self._logged_in = True
            return

        message = get_element_by_class('alert', response)
        if message is not None:
            raise ExtractorError(
                'Unable to login: %s' % clean_html(message), expected=True)

        raise ExtractorError('Unable to log in')


class TeachableIE(TeachableBaseIE):
    _WORKING = False
    _VALID_URL = r'''(?x)
                    (?:
                        %shttps?://(?P<site_t>[^/]+)|
                        https?://(?:www\.)?(?P<site>%s)
                    )
                    /courses/[^/]+/lectures/(?P<id>\d+)
                    ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE

    _TESTS = [{
        'url': 'https://gns3.teachable.com/courses/gns3-certified-associate/lectures/6842364',
        'info_dict': {
            'id': 'untlgzk1v7',
            'ext': 'bin',
            'title': 'Overview',
            'description': 'md5:071463ff08b86c208811130ea1c2464c',
            'duration': 736.4,
            'timestamp': 1542315762,
            'upload_date': '20181115',
            'chapter': 'Welcome',
            'chapter_number': 1,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'http://v1.upskillcourses.com/courses/119763/lectures/1747100',
        'only_matching': True,
    }, {
        'url': 'https://gns3.teachable.com/courses/423415/lectures/6885939',
        'only_matching': True,
    }, {
        'url': 'teachable:https://v1.upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
        'only_matching': True,
    }]

    @staticmethod
    def _is_teachable(webpage):
        return 'teachableTracker.linker:autoLink' in webpage and re.search(
            r'<link[^>]+href=["\']https?://(?:process\.fs|assets)\.teachablecdn\.com',
            webpage)

    @classmethod
    def _extract_embed_urls(cls, url, webpage):
        if cls._is_teachable(webpage):
            if re.match(r'https?://[^/]+/(?:courses|p)', url):
                yield f'{cls._URL_PREFIX}{url}'
                raise cls.StopExtraction()

    def _real_extract(self, url):
        mobj = self._match_valid_url(url)
        site = mobj.group('site') or mobj.group('site_t')
        video_id = mobj.group('id')

        self._login(site)

        prefixed = url.startswith(self._URL_PREFIX)
        if prefixed:
            url = url[len(self._URL_PREFIX):]

        webpage = self._download_webpage(url, video_id)

        wistia_urls = WistiaIE._extract_embed_urls(url, webpage)
        if not wistia_urls:
            if any(re.search(p, webpage) for p in (
                    r'class=["\']lecture-contents-locked',
                    r'>\s*Lecture contents locked',
                    r'id=["\']lecture-locked',
                    # https://academy.tailoredtutors.co.uk/courses/108779/lectures/1955313
                    r'class=["\'](?:inner-)?lesson-locked',
                    r'>LESSON LOCKED<')):
                self.raise_login_required('Lecture contents locked')
            raise ExtractorError('Unable to find video URL')

        title = self._og_search_title(webpage, default=None)

        chapter = None
        chapter_number = None
        section_item = self._search_regex(
            r'(?s)(?P<li><li[^>]+\bdata-lecture-id=["\']%s[^>]+>.+?</li>)' % video_id,
            webpage, 'section item', default=None, group='li')
        if section_item:
            chapter_number = int_or_none(self._search_regex(
                r'data-ss-position=["\'](\d+)', section_item, 'section id',
                default=None))
            if chapter_number is not None:
                sections = []
                for s in re.findall(
                        r'(?s)<div[^>]+\bclass=["\']section-title[^>]+>(.+?)</div>', webpage):
                    section = strip_or_none(clean_html(s))
                    if not section:
                        sections = []
                        break
                    sections.append(section)
                if chapter_number <= len(sections):
                    chapter = sections[chapter_number - 1]

        entries = [{
            '_type': 'url_transparent',
            'url': wistia_url,
            'ie_key': WistiaIE.ie_key(),
            'title': title,
            'chapter': chapter,
            'chapter_number': chapter_number,
        } for wistia_url in wistia_urls]

        return self.playlist_result(entries, video_id, title)


class TeachableCourseIE(TeachableBaseIE):
    _VALID_URL = r'''(?x)
                        (?:
                            %shttps?://(?P<site_t>[^/]+)|
                            https?://(?:www\.)?(?P<site>%s)
                        )
                        /(?:courses|p)/(?:enrolled/)?(?P<id>[^/?#&]+)
                    ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
    _TESTS = [{
        'url': 'http://v1.upskillcourses.com/courses/essential-web-developer-course/',
        'info_dict': {
            'id': 'essential-web-developer-course',
            'title': 'The Essential Web Developer Course (Free)',
        },
        'playlist_count': 192,
    }, {
        'url': 'http://v1.upskillcourses.com/courses/119763/',
        'only_matching': True,
    }, {
        'url': 'http://v1.upskillcourses.com/courses/enrolled/119763',
        'only_matching': True,
    }, {
        'url': 'https://gns3.teachable.com/courses/enrolled/423415',
        'only_matching': True,
    }, {
        'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini',
        'only_matching': True,
    }, {
        'url': 'teachable:https://filmsimplified.com/p/davinci-resolve-15-crash-course',
        'only_matching': True,
    }]

    @classmethod
    def suitable(cls, url):
        return False if TeachableIE.suitable(url) else super(
            TeachableCourseIE, cls).suitable(url)

    def _real_extract(self, url):
        mobj = self._match_valid_url(url)
        site = mobj.group('site') or mobj.group('site_t')
        course_id = mobj.group('id')

        self._login(site)

        prefixed = url.startswith(self._URL_PREFIX)
        if prefixed:
            prefix = self._URL_PREFIX
            url = url[len(prefix):]

        webpage = self._download_webpage(url, course_id)

        url_base = 'https://%s/' % site

        entries = []

        for mobj in re.finditer(
                r'(?s)(?P<li><li[^>]+class=(["\'])(?:(?!\2).)*?section-item[^>]+>.+?</li>)',
                webpage):
            li = mobj.group('li')
            if 'fa-youtube-play' not in li and not re.search(r'\d{1,2}:\d{2}', li):
                continue
            lecture_url = self._search_regex(
                r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', li,
                'lecture url', default=None, group='url')
            if not lecture_url:
                continue
            lecture_id = self._search_regex(
                r'/lectures/(\d+)', lecture_url, 'lecture id', default=None)
            title = self._html_search_regex(
                r'<span[^>]+class=["\']lecture-name[^>]+>([^<]+)', li,
                'title', default=None)
            entry_url = urljoin(url_base, lecture_url)
            if prefixed:
                entry_url = self._URL_PREFIX + entry_url
            entries.append(
                self.url_result(
                    entry_url,
                    ie=TeachableIE.ie_key(), video_id=lecture_id,
                    video_title=clean_html(title)))

        course_title = self._html_search_regex(
            (r'(?s)<img[^>]+class=["\']course-image[^>]+>\s*<h\d>(.+?)</h',
             r'(?s)<h\d[^>]+class=["\']course-title[^>]+>(.+?)</h'),
            webpage, 'course title', fatal=False)

        return self.playlist_result(entries, course_id, course_title)
Commit	Line	Data
7fc60f4e S	1	import re
	2
	3	from .common import InfoExtractor
	4	from .wistia import WistiaIE
7fc60f4e	5	from ..utils import (
7fc60f4e	6	ExtractorError,
e897bd82	7	clean_html,
7fc60f4e	8	get_element_by_class,
e897bd82	9	int_or_none,
4560adc8	10	strip_or_none,
7fc60f4e S	11	urlencode_postdata,
	12	urljoin,
	13	)
	14
	15
5ee7ae5c S	16	class TeachableBaseIE(InfoExtractor):
	17	_NETRC_MACHINE = 'teachable'
	18	_URL_PREFIX = 'teachable:'
	19
	20	_SITES = {
	21	# Only notable ones here
08a27407	22	'v1.upskillcourses.com': 'upskill',
38fa761a	23	'gns3.teachable.com': 'gns3',
5ee7ae5c S	24	'academyhacker.com': 'academyhacker',
	25	'stackskills.com': 'stackskills',
	26	'market.saleshacker.com': 'saleshacker',
	27	'learnability.org': 'learnability',
	28	'edurila.com': 'edurila',
eecf788b	29	'courses.workitdaily.com': 'workitdaily',
5ee7ae5c S	30	}
	31
	32	_VALID_URL_SUB_TUPLE = (_URL_PREFIX, '\|'.join(re.escape(site) for site in _SITES.keys()))
7fc60f4e S	33
7fc60f4e S	34	def _real_initialize(self):
5ee7ae5c	35	self._logged_in = False
7fc60f4e	36
5ee7ae5c S	37	def _login(self, site):
	38	if self._logged_in:
	39	return
	40
52efa4b3	41	username, password = self._get_login_info(netrc_machine=self._SITES.get(site, site))
7fc60f4e S	42	if username is None:
	43	return
	44
	45	login_page, urlh = self._download_webpage_handle(
5ee7ae5c S	46	'https://%s/sign_in' % site, None,
5ee7ae5c S	47	'Downloading %s login page' % site)
7fc60f4e	48
74bc2994 S	49	def is_logged(webpage):
	50	return any(re.search(p, webpage) for p in (
	51	r'class=["\']user-signout',
	52	r'<a[^>]+\bhref=["\']/sign_out',
	53	r'Log\s+[Oo]ut\s*<'))
	54
	55	if is_logged(login_page):
	56	self._logged_in = True
	57	return
	58
3d2623a8	59	login_url = urlh.url
7fc60f4e S	60
	61	login_form = self._hidden_inputs(login_page)
	62
	63	login_form.update({
	64	'user[email]': username,
	65	'user[password]': password,
	66	})
	67
	68	post_url = self._search_regex(
	69	r'<form[^>]+action=(["\'])(?P<url>(?:(?!\1).)+)\1', login_page,
	70	'post url', default=login_url, group='url')
	71
	72	if not post_url.startswith('http'):
	73	post_url = urljoin(login_url, post_url)
	74
	75	response = self._download_webpage(
5ee7ae5c	76	post_url, None, 'Logging in to %s' % site,
7fc60f4e S	77	data=urlencode_postdata(login_form),
	78	headers={
	79	'Content-Type': 'application/x-www-form-urlencoded',
	80	'Referer': login_url,
	81	})
	82
5ee7ae5c S	83	if '>I accept the new Privacy Policy<' in response:
	84	raise ExtractorError(
	85	'Unable to login: %s asks you to accept new Privacy Policy. '
	86	'Go to https://%s/ and accept.' % (site, site), expected=True)
	87
7fc60f4e	88	# Successful login
74bc2994	89	if is_logged(response):
5ee7ae5c	90	self._logged_in = True
7fc60f4e S	91	return
	92
	93	message = get_element_by_class('alert', response)
	94	if message is not None:
	95	raise ExtractorError(
	96	'Unable to login: %s' % clean_html(message), expected=True)
	97
	98	raise ExtractorError('Unable to log in')
	99
	100
5ee7ae5c	101	class TeachableIE(TeachableBaseIE):
df773c3d	102	_WORKING = False
5ee7ae5c S	103	_VALID_URL = r'''(?x)
	104	(?:
	105	%shttps?://(?P<site_t>[^/]+)\|
	106	https?://(?:www\.)?(?P<site>%s)
	107	)
	108	/courses/[^/]+/lectures/(?P<id>\d+)
	109	''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
7fc60f4e S	110
7fc60f4e S	111	_TESTS = [{
6e47200b	112	'url': 'https://gns3.teachable.com/courses/gns3-certified-associate/lectures/6842364',
7fc60f4e	113	'info_dict': {
6e47200b S	114	'id': 'untlgzk1v7',
	115	'ext': 'bin',
	116	'title': 'Overview',
	117	'description': 'md5:071463ff08b86c208811130ea1c2464c',
	118	'duration': 736.4,
	119	'timestamp': 1542315762,
	120	'upload_date': '20181115',
	121	'chapter': 'Welcome',
	122	'chapter_number': 1,
7fc60f4e S	123	},
	124	'params': {
	125	'skip_download': True,
	126	},
	127	}, {
08a27407	128	'url': 'http://v1.upskillcourses.com/courses/119763/lectures/1747100',
7fc60f4e	129	'only_matching': True,
5ee7ae5c	130	}, {
38fa761a	131	'url': 'https://gns3.teachable.com/courses/423415/lectures/6885939',
5ee7ae5c S	132	'only_matching': True,
5ee7ae5c S	133	}, {
08a27407	134	'url': 'teachable:https://v1.upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
5ee7ae5c	135	'only_matching': True,
7fc60f4e S	136	}]
7fc60f4e S	137
5ee7ae5c S	138	@staticmethod
	139	def _is_teachable(webpage):
	140	return 'teachableTracker.linker:autoLink' in webpage and re.search(
29f7c58a	141	r'<link[^>]+href=["\']https?://(?:process\.fs\|assets)\.teachablecdn\.com',
5ee7ae5c S	142	webpage)
5ee7ae5c S	143
bfd973ec	144	@classmethod
	145	def _extract_embed_urls(cls, url, webpage):
	146	if cls._is_teachable(webpage):
	147	if re.match(r'https?://[^/]+/(?:courses\|p)', url):
	148	yield f'{cls._URL_PREFIX}{url}'
	149	raise cls.StopExtraction()
5ee7ae5c	150
7fc60f4e	151	def _real_extract(self, url):
5ad28e7f	152	mobj = self._match_valid_url(url)
5ee7ae5c S	153	site = mobj.group('site') or mobj.group('site_t')
	154	video_id = mobj.group('id')
	155
	156	self._login(site)
	157
	158	prefixed = url.startswith(self._URL_PREFIX)
	159	if prefixed:
	160	url = url[len(self._URL_PREFIX):]
7fc60f4e S	161
	162	webpage = self._download_webpage(url, video_id)
	163
bfd973ec	164	wistia_urls = WistiaIE._extract_embed_urls(url, webpage)
00d798b7	165	if not wistia_urls:
7fc60f4e S	166	if any(re.search(p, webpage) for p in (
	167	r'class=["\']lecture-contents-locked',
	168	r'>\s*Lecture contents locked',
f8a12427 S	169	r'id=["\']lecture-locked',
	170	# https://academy.tailoredtutors.co.uk/courses/108779/lectures/1955313
	171	r'class=["\'](?:inner-)?lesson-locked',
	172	r'>LESSON LOCKED<')):
7fc60f4e	173	self.raise_login_required('Lecture contents locked')
941e359e	174	raise ExtractorError('Unable to find video URL')
7fc60f4e S	175
	176	title = self._og_search_title(webpage, default=None)
	177
4560adc8 S	178	chapter = None
	179	chapter_number = None
	180	section_item = self._search_regex(
	181	r'(?s)(?P<li><li[^>]+\bdata-lecture-id=["\']%s[^>]+>.+?</li>)' % video_id,
	182	webpage, 'section item', default=None, group='li')
	183	if section_item:
	184	chapter_number = int_or_none(self._search_regex(
	185	r'data-ss-position=["\'](\d+)', section_item, 'section id',
	186	default=None))
	187	if chapter_number is not None:
	188	sections = []
	189	for s in re.findall(
	190	r'(?s)<div[^>]+\bclass=["\']section-title[^>]+>(.+?)</div>', webpage):
	191	section = strip_or_none(clean_html(s))
	192	if not section:
	193	sections = []
	194	break
	195	sections.append(section)
	196	if chapter_number <= len(sections):
	197	chapter = sections[chapter_number - 1]
	198
00d798b7	199	entries = [{
7fc60f4e S	200	'_type': 'url_transparent',
	201	'url': wistia_url,
	202	'ie_key': WistiaIE.ie_key(),
	203	'title': title,
4560adc8 S	204	'chapter': chapter,
4560adc8 S	205	'chapter_number': chapter_number,
00d798b7 S	206	} for wistia_url in wistia_urls]
	207
	208	return self.playlist_result(entries, video_id, title)
7fc60f4e S	209
7fc60f4e S	210
5ee7ae5c S	211	class TeachableCourseIE(TeachableBaseIE):
	212	_VALID_URL = r'''(?x)
	213	(?:
	214	%shttps?://(?P<site_t>[^/]+)\|
	215	https?://(?:www\.)?(?P<site>%s)
	216	)
	217	/(?:courses\|p)/(?:enrolled/)?(?P<id>[^/?#&]+)
	218	''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
7fc60f4e	219	_TESTS = [{
08a27407	220	'url': 'http://v1.upskillcourses.com/courses/essential-web-developer-course/',
7fc60f4e	221	'info_dict': {
5ee7ae5c	222	'id': 'essential-web-developer-course',
7fc60f4e S	223	'title': 'The Essential Web Developer Course (Free)',
	224	},
	225	'playlist_count': 192,
	226	}, {
08a27407	227	'url': 'http://v1.upskillcourses.com/courses/119763/',
7fc60f4e S	228	'only_matching': True,
7fc60f4e S	229	}, {
08a27407	230	'url': 'http://v1.upskillcourses.com/courses/enrolled/119763',
7fc60f4e	231	'only_matching': True,
5ee7ae5c	232	}, {
38fa761a	233	'url': 'https://gns3.teachable.com/courses/enrolled/423415',
5ee7ae5c S	234	'only_matching': True,
	235	}, {
	236	'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini',
	237	'only_matching': True,
	238	}, {
	239	'url': 'teachable:https://filmsimplified.com/p/davinci-resolve-15-crash-course',
	240	'only_matching': True,
7fc60f4e S	241	}]
	242
	243	@classmethod
	244	def suitable(cls, url):
5ee7ae5c S	245	return False if TeachableIE.suitable(url) else super(
5ee7ae5c S	246	TeachableCourseIE, cls).suitable(url)
7fc60f4e S	247
7fc60f4e S	248	def _real_extract(self, url):
5ad28e7f	249	mobj = self._match_valid_url(url)
5ee7ae5c S	250	site = mobj.group('site') or mobj.group('site_t')
	251	course_id = mobj.group('id')
	252
	253	self._login(site)
	254
	255	prefixed = url.startswith(self._URL_PREFIX)
	256	if prefixed:
	257	prefix = self._URL_PREFIX
	258	url = url[len(prefix):]
7fc60f4e S	259
	260	webpage = self._download_webpage(url, course_id)
	261
5ee7ae5c	262	url_base = 'https://%s/' % site
7fc60f4e S	263
	264	entries = []
	265
	266	for mobj in re.finditer(
	267	r'(?s)(?P<li><li[^>]+class=(["\'])(?:(?!\2).)*?section-item[^>]+>.+?</li>)',
	268	webpage):
	269	li = mobj.group('li')
29f7c58a	270	if 'fa-youtube-play' not in li and not re.search(r'\d{1,2}:\d{2}', li):
7fc60f4e S	271	continue
	272	lecture_url = self._search_regex(
	273	r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', li,
	274	'lecture url', default=None, group='url')
	275	if not lecture_url:
	276	continue
	277	lecture_id = self._search_regex(
	278	r'/lectures/(\d+)', lecture_url, 'lecture id', default=None)
	279	title = self._html_search_regex(
	280	r'<span[^>]+class=["\']lecture-name[^>]+>([^<]+)', li,
	281	'title', default=None)
5ee7ae5c S	282	entry_url = urljoin(url_base, lecture_url)
	283	if prefixed:
	284	entry_url = self._URL_PREFIX + entry_url
7fc60f4e S	285	entries.append(
7fc60f4e S	286	self.url_result(
5ee7ae5c S	287	entry_url,
5ee7ae5c S	288	ie=TeachableIE.ie_key(), video_id=lecture_id,
7fc60f4e S	289	video_title=clean_html(title)))
	290
	291	course_title = self._html_search_regex(
	292	(r'(?s)<img[^>]+class=["\']course-image[^>]+>\s*<h\d>(.+?)</h',
	293	r'(?s)<h\d[^>]+class=["\']course-title[^>]+>(.+?)</h'),
	294	webpage, 'course title', fatal=False)
	295
	296	return self.playlist_result(entries, course_id, course_title)