From: Sergey M Date: Fri, 10 Jun 2016 19:34:58 +0000 (+0700) Subject: Merge pull request #9747 from TRox1972/lynda X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=1058f56e96316e778ed74ad008949c634a582e84;hp=-c;p=youtube-dl Merge pull request #9747 from TRox1972/lynda [Lynda] Extract course description --- 1058f56e96316e778ed74ad008949c634a582e84 diff --combined youtube_dl/extractor/lynda.py index 7610985b4,c1bca5678..5b458d9bc --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@@ -1,94 -1,93 +1,94 @@@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor -from ..compat import compat_str +from ..compat import ( + compat_HTTPError, + compat_str, + compat_urlparse, +) from ..utils import ( ExtractorError, - clean_html, int_or_none, - sanitized_Request, urlencode_postdata, ) class LyndaBaseIE(InfoExtractor): - _LOGIN_URL = 'https://www.lynda.com/login/login.aspx' + _SIGNIN_URL = 'https://www.lynda.com/signin' + _PASSWORD_URL = 'https://www.lynda.com/signin/password' + _USER_URL = 'https://www.lynda.com/signin/user' _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.' _NETRC_MACHINE = 'lynda' def _real_initialize(self): self._login() + @staticmethod + def _check_error(json_string, key_or_keys): + keys = [key_or_keys] if isinstance(key_or_keys, compat_str) else key_or_keys + for key in keys: + error = json_string.get(key) + if error: + raise ExtractorError('Unable to login: %s' % error, expected=True) + + def _login_step(self, form_html, fallback_action_url, extra_form_data, note, referrer_url): + action_url = self._search_regex( + r']+action=(["\'])(?P.+?)\1', form_html, + 'post url', default=fallback_action_url, group='url') + + if not action_url.startswith('http'): + action_url = compat_urlparse.urljoin(self._SIGNIN_URL, action_url) + + form_data = self._hidden_inputs(form_html) + form_data.update(extra_form_data) + + try: + response = self._download_json( + action_url, None, note, + data=urlencode_postdata(form_data), + headers={ + 'Referer': referrer_url, + 'X-Requested-With': 'XMLHttpRequest', + }) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500: + response = self._parse_json(e.cause.read().decode('utf-8'), None) + self._check_error(response, ('email', 'password')) + raise + + self._check_error(response, 'ErrorMessage') + + return response, action_url + def _login(self): username, password = self._get_login_info() if username is None: return - login_form = { - 'username': username, - 'password': password, - 'remember': 'false', - 'stayPut': 'false' - } - request = sanitized_Request( - self._LOGIN_URL, urlencode_postdata(login_form)) - login_page = self._download_webpage( - request, None, 'Logging in as %s' % username) - - # Not (yet) logged in - m = re.search(r'loginResultJson\s*=\s*\'(?P[^\']+)\';', login_page) - if m is not None: - response = m.group('json') - response_json = json.loads(response) - state = response_json['state'] - - if state == 'notlogged': - raise ExtractorError( - 'Unable to login, incorrect username and/or password', - expected=True) - - # This is when we get popup: - # > You're already logged in to lynda.com on two devices. - # > If you log in here, we'll log you out of another device. - # So, we need to confirm this. - if state == 'conflicted': - confirm_form = { - 'username': '', - 'password': '', - 'resolve': 'true', - 'remember': 'false', - 'stayPut': 'false', - } - request = sanitized_Request( - self._LOGIN_URL, urlencode_postdata(confirm_form)) - login_page = self._download_webpage( - request, None, - 'Confirming log in and log out from another device') - - if all(not re.search(p, login_page) for p in ('isLoggedIn\s*:\s*true', r'logout\.aspx', r'>Log out<')): - if 'login error' in login_page: - mobj = re.search( - r'(?s)]+class="topmost">(?P[^<]+)</h1>\s*<div>(?P<description>.+?)</div>', - login_page) - if mobj: - raise ExtractorError( - 'lynda returned error: %s - %s' - % (mobj.group('title'), clean_html(mobj.group('description'))), - expected=True) - raise ExtractorError('Unable to log in') - - def _logout(self): - username, _ = self._get_login_info() - if username is None: + # Step 1: download signin page + signin_page = self._download_webpage( + self._SIGNIN_URL, None, 'Downloading signin page') + + # Already logged in + if any(re.search(p, signin_page) for p in ( + 'isLoggedIn\s*:\s*true', r'logout\.aspx', r'>Log out<')): return - self._download_webpage( - 'http://www.lynda.com/ajax/logout.aspx', None, - 'Logging out', 'Unable to log out', fatal=False) + # Step 2: submit email + signin_form = self._search_regex( + r'(?s)(<form[^>]+data-form-name=["\']signin["\'][^>]*>.+?</form>)', + signin_page, 'signin form') + signin_page, signin_url = self._login_step( + signin_form, self._PASSWORD_URL, {'email': username}, + 'Submitting email', self._SIGNIN_URL) + + # Step 3: submit password + password_form = signin_page['body'] + self._login_step( + password_form, self._USER_URL, {'email': username, 'password': password}, + 'Submitting password', signin_url) class LyndaIE(LyndaBaseIE): @@@ -213,6 -212,8 +213,6 @@@ class LyndaCourseIE(LyndaBaseIE) 'http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id, course_id, 'Downloading course JSON') - self._logout() - if course.get('Status') == 'NotFound': raise ExtractorError( 'Course %s does not exist' % course_id, expected=True) @@@ -245,5 -246,6 +245,6 @@@ % unaccessible_videos + self._ACCOUNT_CREDENTIALS_HINT) course_title = course.get('Title') + course_description = course.get('Description') - return self.playlist_result(entries, course_id, course_title) + return self.playlist_result(entries, course_id, course_title, course_description)