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

from __future__ import unicode_literals

import re

from .common import InfoExtractor
from .wistia import WistiaIE
from ..utils import (
    clean_html,
    ExtractorError,
    int_or_none,
    get_element_by_class,
    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.geturl()

        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):
    _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)

    @staticmethod
    def _extract_url(webpage, source_url):
        if not TeachableIE._is_teachable(webpage):
            return
        if re.match(r'https?://[^/]+/(?:courses|p)', source_url):
            return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url)

    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_urls(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	from __future__ import unicode_literals
	2
	3	import re
	4
	5	from .common import InfoExtractor
	6	from .wistia import WistiaIE
7fc60f4e S	7	from ..utils import (
	8	clean_html,
	9	ExtractorError,
4560adc8	10	int_or_none,
7fc60f4e	11	get_element_by_class,
4560adc8	12	strip_or_none,
7fc60f4e S	13	urlencode_postdata,
	14	urljoin,
	15	)
	16
	17
5ee7ae5c S	18	class TeachableBaseIE(InfoExtractor):
	19	_NETRC_MACHINE = 'teachable'
	20	_URL_PREFIX = 'teachable:'
	21
	22	_SITES = {
	23	# Only notable ones here
08a27407	24	'v1.upskillcourses.com': 'upskill',
38fa761a	25	'gns3.teachable.com': 'gns3',
5ee7ae5c S	26	'academyhacker.com': 'academyhacker',
	27	'stackskills.com': 'stackskills',
	28	'market.saleshacker.com': 'saleshacker',
	29	'learnability.org': 'learnability',
	30	'edurila.com': 'edurila',
eecf788b	31	'courses.workitdaily.com': 'workitdaily',
5ee7ae5c S	32	}
	33
	34	_VALID_URL_SUB_TUPLE = (_URL_PREFIX, '\|'.join(re.escape(site) for site in _SITES.keys()))
7fc60f4e S	35
7fc60f4e S	36	def _real_initialize(self):
5ee7ae5c	37	self._logged_in = False
7fc60f4e	38
5ee7ae5c S	39	def _login(self, site):
	40	if self._logged_in:
	41	return
	42
52efa4b3	43	username, password = self._get_login_info(netrc_machine=self._SITES.get(site, site))
7fc60f4e S	44	if username is None:
	45	return
	46
	47	login_page, urlh = self._download_webpage_handle(
5ee7ae5c S	48	'https://%s/sign_in' % site, None,
5ee7ae5c S	49	'Downloading %s login page' % site)
7fc60f4e	50
74bc2994 S	51	def is_logged(webpage):
	52	return any(re.search(p, webpage) for p in (
	53	r'class=["\']user-signout',
	54	r'<a[^>]+\bhref=["\']/sign_out',
	55	r'Log\s+[Oo]ut\s*<'))
	56
	57	if is_logged(login_page):
	58	self._logged_in = True
	59	return
	60
7947a1f7	61	login_url = urlh.geturl()
7fc60f4e S	62
	63	login_form = self._hidden_inputs(login_page)
	64
	65	login_form.update({
	66	'user[email]': username,
	67	'user[password]': password,
	68	})
	69
	70	post_url = self._search_regex(
	71	r'<form[^>]+action=(["\'])(?P<url>(?:(?!\1).)+)\1', login_page,
	72	'post url', default=login_url, group='url')
	73
	74	if not post_url.startswith('http'):
	75	post_url = urljoin(login_url, post_url)
	76
	77	response = self._download_webpage(
5ee7ae5c	78	post_url, None, 'Logging in to %s' % site,
7fc60f4e S	79	data=urlencode_postdata(login_form),
	80	headers={
	81	'Content-Type': 'application/x-www-form-urlencoded',
	82	'Referer': login_url,
	83	})
	84
5ee7ae5c S	85	if '>I accept the new Privacy Policy<' in response:
	86	raise ExtractorError(
	87	'Unable to login: %s asks you to accept new Privacy Policy. '
	88	'Go to https://%s/ and accept.' % (site, site), expected=True)
	89
7fc60f4e	90	# Successful login
74bc2994	91	if is_logged(response):
5ee7ae5c	92	self._logged_in = True
7fc60f4e S	93	return
	94
	95	message = get_element_by_class('alert', response)
	96	if message is not None:
	97	raise ExtractorError(
	98	'Unable to login: %s' % clean_html(message), expected=True)
	99
	100	raise ExtractorError('Unable to log in')
	101
	102
5ee7ae5c S	103	class TeachableIE(TeachableBaseIE):
	104	_VALID_URL = r'''(?x)
	105	(?:
	106	%shttps?://(?P<site_t>[^/]+)\|
	107	https?://(?:www\.)?(?P<site>%s)
	108	)
	109	/courses/[^/]+/lectures/(?P<id>\d+)
	110	''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
7fc60f4e S	111
7fc60f4e S	112	_TESTS = [{
6e47200b	113	'url': 'https://gns3.teachable.com/courses/gns3-certified-associate/lectures/6842364',
7fc60f4e	114	'info_dict': {
6e47200b S	115	'id': 'untlgzk1v7',
	116	'ext': 'bin',
	117	'title': 'Overview',
	118	'description': 'md5:071463ff08b86c208811130ea1c2464c',
	119	'duration': 736.4,
	120	'timestamp': 1542315762,
	121	'upload_date': '20181115',
	122	'chapter': 'Welcome',
	123	'chapter_number': 1,
7fc60f4e S	124	},
	125	'params': {
	126	'skip_download': True,
	127	},
	128	}, {
08a27407	129	'url': 'http://v1.upskillcourses.com/courses/119763/lectures/1747100',
7fc60f4e	130	'only_matching': True,
5ee7ae5c	131	}, {
38fa761a	132	'url': 'https://gns3.teachable.com/courses/423415/lectures/6885939',
5ee7ae5c S	133	'only_matching': True,
5ee7ae5c S	134	}, {
08a27407	135	'url': 'teachable:https://v1.upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
5ee7ae5c	136	'only_matching': True,
7fc60f4e S	137	}]
7fc60f4e S	138
5ee7ae5c S	139	@staticmethod
	140	def _is_teachable(webpage):
	141	return 'teachableTracker.linker:autoLink' in webpage and re.search(
29f7c58a	142	r'<link[^>]+href=["\']https?://(?:process\.fs\|assets)\.teachablecdn\.com',
5ee7ae5c S	143	webpage)
	144
	145	@staticmethod
	146	def _extract_url(webpage, source_url):
	147	if not TeachableIE._is_teachable(webpage):
5ee7ae5c S	148	return
	149	if re.match(r'https?://[^/]+/(?:courses\|p)', source_url):
	150	return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url)
	151
7fc60f4e	152	def _real_extract(self, url):
5ad28e7f	153	mobj = self._match_valid_url(url)
5ee7ae5c S	154	site = mobj.group('site') or mobj.group('site_t')
	155	video_id = mobj.group('id')
	156
	157	self._login(site)
	158
	159	prefixed = url.startswith(self._URL_PREFIX)
	160	if prefixed:
	161	url = url[len(self._URL_PREFIX):]
7fc60f4e S	162
	163	webpage = self._download_webpage(url, video_id)
	164
00d798b7 S	165	wistia_urls = WistiaIE._extract_urls(webpage)
00d798b7 S	166	if not wistia_urls:
7fc60f4e S	167	if any(re.search(p, webpage) for p in (
	168	r'class=["\']lecture-contents-locked',
	169	r'>\s*Lecture contents locked',
f8a12427 S	170	r'id=["\']lecture-locked',
	171	# https://academy.tailoredtutors.co.uk/courses/108779/lectures/1955313
	172	r'class=["\'](?:inner-)?lesson-locked',
	173	r'>LESSON LOCKED<')):
7fc60f4e	174	self.raise_login_required('Lecture contents locked')
941e359e	175	raise ExtractorError('Unable to find video URL')
7fc60f4e S	176
	177	title = self._og_search_title(webpage, default=None)
	178
4560adc8 S	179	chapter = None
	180	chapter_number = None
	181	section_item = self._search_regex(
	182	r'(?s)(?P<li><li[^>]+\bdata-lecture-id=["\']%s[^>]+>.+?</li>)' % video_id,
	183	webpage, 'section item', default=None, group='li')
	184	if section_item:
	185	chapter_number = int_or_none(self._search_regex(
	186	r'data-ss-position=["\'](\d+)', section_item, 'section id',
	187	default=None))
	188	if chapter_number is not None:
	189	sections = []
	190	for s in re.findall(
	191	r'(?s)<div[^>]+\bclass=["\']section-title[^>]+>(.+?)</div>', webpage):
	192	section = strip_or_none(clean_html(s))
	193	if not section:
	194	sections = []
	195	break
	196	sections.append(section)
	197	if chapter_number <= len(sections):
	198	chapter = sections[chapter_number - 1]
	199
00d798b7	200	entries = [{
7fc60f4e S	201	'_type': 'url_transparent',
	202	'url': wistia_url,
	203	'ie_key': WistiaIE.ie_key(),
	204	'title': title,
4560adc8 S	205	'chapter': chapter,
4560adc8 S	206	'chapter_number': chapter_number,
00d798b7 S	207	} for wistia_url in wistia_urls]
	208
	209	return self.playlist_result(entries, video_id, title)
7fc60f4e S	210
7fc60f4e S	211
5ee7ae5c S	212	class TeachableCourseIE(TeachableBaseIE):
	213	_VALID_URL = r'''(?x)
	214	(?:
	215	%shttps?://(?P<site_t>[^/]+)\|
	216	https?://(?:www\.)?(?P<site>%s)
	217	)
	218	/(?:courses\|p)/(?:enrolled/)?(?P<id>[^/?#&]+)
	219	''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
7fc60f4e	220	_TESTS = [{
08a27407	221	'url': 'http://v1.upskillcourses.com/courses/essential-web-developer-course/',
7fc60f4e	222	'info_dict': {
5ee7ae5c	223	'id': 'essential-web-developer-course',
7fc60f4e S	224	'title': 'The Essential Web Developer Course (Free)',
	225	},
	226	'playlist_count': 192,
	227	}, {
08a27407	228	'url': 'http://v1.upskillcourses.com/courses/119763/',
7fc60f4e S	229	'only_matching': True,
7fc60f4e S	230	}, {
08a27407	231	'url': 'http://v1.upskillcourses.com/courses/enrolled/119763',
7fc60f4e	232	'only_matching': True,
5ee7ae5c	233	}, {
38fa761a	234	'url': 'https://gns3.teachable.com/courses/enrolled/423415',
5ee7ae5c S	235	'only_matching': True,
	236	}, {
	237	'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini',
	238	'only_matching': True,
	239	}, {
	240	'url': 'teachable:https://filmsimplified.com/p/davinci-resolve-15-crash-course',
	241	'only_matching': True,
7fc60f4e S	242	}]
	243
	244	@classmethod
	245	def suitable(cls, url):
5ee7ae5c S	246	return False if TeachableIE.suitable(url) else super(
5ee7ae5c S	247	TeachableCourseIE, cls).suitable(url)
7fc60f4e S	248
7fc60f4e S	249	def _real_extract(self, url):
5ad28e7f	250	mobj = self._match_valid_url(url)
5ee7ae5c S	251	site = mobj.group('site') or mobj.group('site_t')
	252	course_id = mobj.group('id')
	253
	254	self._login(site)
	255
	256	prefixed = url.startswith(self._URL_PREFIX)
	257	if prefixed:
	258	prefix = self._URL_PREFIX
	259	url = url[len(prefix):]
7fc60f4e S	260
	261	webpage = self._download_webpage(url, course_id)
	262
5ee7ae5c	263	url_base = 'https://%s/' % site
7fc60f4e S	264
	265	entries = []
	266
	267	for mobj in re.finditer(
	268	r'(?s)(?P<li><li[^>]+class=(["\'])(?:(?!\2).)*?section-item[^>]+>.+?</li>)',
	269	webpage):
	270	li = mobj.group('li')
29f7c58a	271	if 'fa-youtube-play' not in li and not re.search(r'\d{1,2}:\d{2}', li):
7fc60f4e S	272	continue
	273	lecture_url = self._search_regex(
	274	r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', li,
	275	'lecture url', default=None, group='url')
	276	if not lecture_url:
	277	continue
	278	lecture_id = self._search_regex(
	279	r'/lectures/(\d+)', lecture_url, 'lecture id', default=None)
	280	title = self._html_search_regex(
	281	r'<span[^>]+class=["\']lecture-name[^>]+>([^<]+)', li,
	282	'title', default=None)
5ee7ae5c S	283	entry_url = urljoin(url_base, lecture_url)
	284	if prefixed:
	285	entry_url = self._URL_PREFIX + entry_url
7fc60f4e S	286	entries.append(
7fc60f4e S	287	self.url_result(
5ee7ae5c S	288	entry_url,
5ee7ae5c S	289	ie=TeachableIE.ie_key(), video_id=lecture_id,
7fc60f4e S	290	video_title=clean_html(title)))
	291
	292	course_title = self._html_search_regex(
	293	(r'(?s)<img[^>]+class=["\']course-image[^>]+>\s*<h\d>(.+?)</h',
	294	r'(?s)<h\d[^>]+class=["\']course-title[^>]+>(.+?)</h'),
	295	webpage, 'course title', fatal=False)
	296
	297	return self.playlist_result(entries, course_id, course_title)