From: Sergey M․ Date: Sun, 9 Dec 2018 15:28:24 +0000 (+0700) Subject: [teachable] Add support for teachable based platform sites (closes #5451, closes... X-Git-Url: http://git.bitcoin.ninja/?a=commitdiff_plain;h=5ee7ae5c7577c9c137a7b38edd5ad01ae3a40376;p=youtube-dl [teachable] Add support for teachable based platform sites (closes #5451, closes #18150, closes #18272) --- diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index e28db6968..6a5d12ab1 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1091,6 +1091,10 @@ from .tass import TassIE from .tastytrade import TastyTradeIE from .tbs import TBSIE from .tdslifeway import TDSLifewayIE +from .teachable import ( + TeachableIE, + TeachableCourseIE, +) from .teachertube import ( TeacherTubeIE, TeacherTubeUserIE, @@ -1240,10 +1244,6 @@ from .uplynk import ( UplynkIE, UplynkPreplayIE, ) -from .upskill import ( - UpskillIE, - UpskillCourseIE, -) from .urort import UrortIE from .urplay import URPlayIE from .usanetwork import USANetworkIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 59cf03faf..65b482333 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -109,6 +109,7 @@ from .vice import ViceIE from .xfileshare import XFileShareIE from .cloudflarestream import CloudflareStreamIE from .peertube import PeerTubeIE +from .teachable import TeachableIE from .indavideo import IndavideoEmbedIE from .apa import APAIE from .foxnews import FoxNewsIE @@ -3112,6 +3113,10 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key()) + teachable_url = TeachableIE._extract_url(webpage, url) + if teachable_url: + return self.url_result(teachable_url) + indavideo_urls = IndavideoEmbedIE._extract_urls(webpage) if indavideo_urls: return self.playlist_from_matches( diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py new file mode 100644 index 000000000..a0c46b2e6 --- /dev/null +++ b/youtube_dl/extractor/teachable.py @@ -0,0 +1,259 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from .wistia import WistiaIE +from ..compat import compat_str +from ..utils import ( + clean_html, + ExtractorError, + get_element_by_class, + urlencode_postdata, + urljoin, +) + + +class TeachableBaseIE(InfoExtractor): + _NETRC_MACHINE = 'teachable' + _URL_PREFIX = 'teachable:' + + _SITES = { + # Only notable ones here + 'upskillcourses.com': 'upskill', + 'academy.gns3.com': 'gns3', + 'academyhacker.com': 'academyhacker', + 'stackskills.com': 'stackskills', + 'market.saleshacker.com': 'saleshacker', + 'learnability.org': 'learnability', + 'edurila.com': 'edurila', + } + + _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) + + login_url = compat_str(urlh.geturl()) + + login_form = self._hidden_inputs(login_page) + + login_form.update({ + 'user[email]': username, + 'user[password]': password, + }) + + post_url = self._search_regex( + r']+action=(["\'])(?P(?:(?!\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 any(re.search(p, response) for p in ( + r'class=["\']user-signout', + r']+\bhref=["\']/sign_out', + r'>\s*Log out\s*<')): + 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[^/]+)| + https?://(?:www\.)?(?P%s) + ) + /courses/[^/]+/lectures/(?P\d+) + ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE + + _TESTS = [{ + 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', + 'info_dict': { + 'id': 'uzw6zw58or', + 'ext': 'mp4', + 'title': 'Welcome to the Course!', + 'description': 'md5:65edb0affa582974de4625b9cdea1107', + 'duration': 138.763, + 'timestamp': 1479846621, + 'upload_date': '20161122', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'http://upskillcourses.com/courses/119763/lectures/1747100', + 'only_matching': True, + }, { + 'url': 'https://academy.gns3.com/courses/423415/lectures/6885939', + 'only_matching': True, + }, { + 'url': 'teachable:https://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']+href=["\']https?://process\.fs\.teachablecdn\.com', + webpage) + + @staticmethod + def _extract_url(webpage, source_url): + if not TeachableIE._is_teachable(webpage): + print('NOT TEACHABLE') + return + if re.match(r'https?://[^/]+/(?:courses|p)', source_url): + return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url) + + def _real_extract(self, url): + mobj = re.match(self._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_url = WistiaIE._extract_url(webpage) + if not wistia_url: + if any(re.search(p, webpage) for p in ( + r'class=["\']lecture-contents-locked', + r'>\s*Lecture contents locked', + r'id=["\']lecture-locked')): + self.raise_login_required('Lecture contents locked') + + title = self._og_search_title(webpage, default=None) + + return { + '_type': 'url_transparent', + 'url': wistia_url, + 'ie_key': WistiaIE.ie_key(), + 'title': title, + } + + +class TeachableCourseIE(TeachableBaseIE): + _VALID_URL = r'''(?x) + (?: + %shttps?://(?P[^/]+)| + https?://(?:www\.)?(?P%s) + ) + /(?:courses|p)/(?:enrolled/)?(?P[^/?#&]+) + ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE + _TESTS = [{ + 'url': 'http://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://upskillcourses.com/courses/119763/', + 'only_matching': True, + }, { + 'url': 'http://upskillcourses.com/courses/enrolled/119763', + 'only_matching': True, + }, { + 'url': 'https://academy.gns3.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 = re.match(self._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
  • ]+class=(["\'])(?:(?!\2).)*?section-item[^>]+>.+?
    • )', + webpage): + li = mobj.group('li') + if 'fa-youtube-play' not in li: + continue + lecture_url = self._search_regex( + r']+href=(["\'])(?P(?:(?!\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']+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)]+class=["\']course-image[^>]+>\s*(.+?)]+class=["\']course-title[^>]+>(.+?)]+action=(["\'])(?P(?:(?!\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', - data=urlencode_postdata(login_form), - headers={ - 'Content-Type': 'application/x-www-form-urlencoded', - 'Referer': login_url, - }) - - # Successful login - if any(re.search(p, response) for p in ( - r'class=["\']user-signout', - r']+\bhref=["\']/sign_out', - r'>\s*Log out\s*<')): - 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 UpskillIE(UpskillBaseIE): - _VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/[^/]+/lectures/(?P\d+)' - - _TESTS = [{ - 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', - 'info_dict': { - 'id': 'uzw6zw58or', - 'ext': 'mp4', - 'title': 'Welcome to the Course!', - 'description': 'md5:8d66c13403783370af62ca97a7357bdd', - 'duration': 138.763, - 'timestamp': 1479846621, - 'upload_date': '20161122', - }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'http://upskillcourses.com/courses/119763/lectures/1747100', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - wistia_url = WistiaIE._extract_url(webpage) - if not wistia_url: - if any(re.search(p, webpage) for p in ( - r'class=["\']lecture-contents-locked', - r'>\s*Lecture contents locked', - r'id=["\']lecture-locked')): - self.raise_login_required('Lecture contents locked') - - title = self._og_search_title(webpage, default=None) - - return { - '_type': 'url_transparent', - 'url': wistia_url, - 'ie_key': WistiaIE.ie_key(), - 'title': title, - } - - -class UpskillCourseIE(UpskillBaseIE): - _VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/(?:enrolled/)?(?P[^/?#&]+)' - _TESTS = [{ - 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/', - 'info_dict': { - 'id': '119763', - 'title': 'The Essential Web Developer Course (Free)', - }, - 'playlist_count': 192, - }, { - 'url': 'http://upskillcourses.com/courses/119763/', - 'only_matching': True, - }, { - 'url': 'http://upskillcourses.com/courses/enrolled/119763', - 'only_matching': True, - }] - - @classmethod - def suitable(cls, url): - return False if UpskillIE.suitable(url) else super( - UpskillCourseIE, cls).suitable(url) - - def _real_extract(self, url): - course_id = self._match_id(url) - - webpage = self._download_webpage(url, course_id) - - course_id = self._search_regex( - r'data-course-id=["\'](\d+)', webpage, 'course id', - default=course_id) - - entries = [] - - for mobj in re.finditer( - r'(?s)(?P
  • ]+class=(["\'])(?:(?!\2).)*?section-item[^>]+>.+?
    • )', - webpage): - li = mobj.group('li') - if 'fa-youtube-play' not in li: - continue - lecture_url = self._search_regex( - r']+href=(["\'])(?P(?:(?!\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']+class=["\']lecture-name[^>]+>([^<]+)', li, - 'title', default=None) - entries.append( - self.url_result( - urljoin('http://upskillcourses.com/', lecture_url), - ie=UpskillIE.ie_key(), video_id=lecture_id, - video_title=clean_html(title))) - - course_title = self._html_search_regex( - (r'(?s)]+class=["\']course-image[^>]+>\s*(.+?)]+class=["\']course-title[^>]+>(.+?)