X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsafari.py;h=8a5d48fc2cf0c1021b38f6dbaa1fbb12767aab2a;hb=68217024e83c8e7965f2800e9ff7a9575f049b5c;hp=ae619636ce643d78bcd53e4cd31ec7e549a1652b;hpb=bcb668de189b92bd1dcad661d50ae981f25deca4;p=youtube-dl diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index ae619636c..8a5d48fc2 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -1,15 +1,13 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import re from .common import InfoExtractor -from .brightcove import BrightcoveLegacyIE from ..utils import ( ExtractorError, sanitized_Request, - smuggle_url, std_headers, urlencode_postdata, update_url_query, @@ -18,34 +16,35 @@ from ..utils import ( class SafariBaseIE(InfoExtractor): _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/' - _SUCCESSFUL_LOGIN_REGEX = r']*>Sign Out' _NETRC_MACHINE = 'safari' - _API_BASE = 'https://www.safaribooksonline.com/api/v1/book' + _API_BASE = 'https://www.safaribooksonline.com/api/v1' _API_FORMAT = 'json' LOGGED_IN = False def _real_initialize(self): - return - # We only need to log in once for courses or individual videos - if not self.LOGGED_IN: - self._login() - SafariBaseIE.LOGGED_IN = True + self._login() def _login(self): - (username, password) = self._get_login_info() + username, password = self._get_login_info() if username is None: - self.raise_login_required('safaribooksonline.com account is required') + return headers = std_headers.copy() if 'Referer' not in headers: headers['Referer'] = self._LOGIN_URL - login_page_request = sanitized_Request(self._LOGIN_URL, headers=headers) login_page = self._download_webpage( - login_page_request, None, - 'Downloading login form') + self._LOGIN_URL, None, 'Downloading login form', headers=headers) + + def is_logged(webpage): + return any(re.search(p, webpage) for p in ( + r'href=["\']/accounts/logout/', r'>Sign Out<')) + + if is_logged(login_page): + self.LOGGED_IN = True + return csrf = self._html_search_regex( r"name='csrfmiddlewaretoken'\s+value='([^']+)'", @@ -62,29 +61,20 @@ class SafariBaseIE(InfoExtractor): request = sanitized_Request( self._LOGIN_URL, urlencode_postdata(login_form), headers=headers) login_page = self._download_webpage( - request, None, 'Logging in as %s' % username) + request, None, 'Logging in') - if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None: + if not is_logged(login_page): raise ExtractorError( 'Login failed; make sure your credentials are correct and try again.', expected=True) - self.to_screen('Login successful') + self.LOGGED_IN = True class SafariIE(SafariBaseIE): IE_NAME = 'safari' IE_DESC = 'safaribooksonline.com online video' - _VALID_URL = r'''(?x)https?:// - (?:www\.)?safaribooksonline\.com/ - (?: - library/view/[^/]+| - api/v1/book - )/ - (?P[^/]+)/ - (?:chapter(?:-content)?/)? - (?Ppart\d+)\.html - ''' + _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P[^/]+)/(?P[^/?#&]+)\.html' _TESTS = [{ 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html', @@ -97,37 +87,83 @@ class SafariIE(SafariBaseIE): 'upload_date': '20150724', 'uploader_id': 'stork', }, - }, { - 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html', - 'only_matching': True, }, { # non-digits in course id 'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html', 'only_matching': True, + }, { + 'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html', + 'only_matching': True, }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - course_id = mobj.group('course_id') - part = mobj.group('part') - - webpage = self._download_webpage(url, '%s/%s' % (course_id, part)) - reference_id = self._search_regex(r'data-reference-id="([^"]+)"', webpage, 'kaltura reference id') - partner_id = self._search_regex(r'data-partner-id="([^"]+)"', webpage, 'kaltura widget id') - ui_id = self._search_regex(r'data-ui-id="([^"]+)"', webpage, 'kaltura uiconf id') - - return self.url_result(update_url_query('https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', { + video_id = '%s/%s' % (mobj.group('course_id'), mobj.group('part')) + + webpage = self._download_webpage(url, video_id) + reference_id = self._search_regex( + r'data-reference-id=(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'kaltura reference id', group='id') + partner_id = self._search_regex( + r'data-partner-id=(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'kaltura widget id', group='id') + ui_id = self._search_regex( + r'data-ui-id=(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'kaltura uiconf id', group='id') + + query = { 'wid': '_%s' % partner_id, 'uiconf_id': ui_id, 'flashvars[referenceId]': reference_id, - }), 'Kaltura') + } + + if self.LOGGED_IN: + kaltura_session = self._download_json( + '%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id), + video_id, 'Downloading kaltura session JSON', + 'Unable to download kaltura session JSON', fatal=False) + if kaltura_session: + session = kaltura_session.get('session') + if session: + query['flashvars[ks]'] = session + + return self.url_result(update_url_query( + 'https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', query), + 'Kaltura') + + +class SafariApiIE(SafariBaseIE): + IE_NAME = 'safari:api' + _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P[^/]+)/chapter(?:-content)?/(?P[^/?#&]+)\.html' + + _TESTS = [{ + 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html', + 'only_matching': True, + }, { + 'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + part = self._download_json( + url, '%s/%s' % (mobj.group('course_id'), mobj.group('part')), + 'Downloading part JSON') + return self.url_result(part['web_url'], SafariIE.ie_key()) class SafariCourseIE(SafariBaseIE): IE_NAME = 'safari:course' IE_DESC = 'safaribooksonline.com online courses' - _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P[^/]+)/?(?:[#?]|$)' + _VALID_URL = r'''(?x) + https?:// + (?: + (?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)| + techbus\.safaribooksonline\.com + ) + /(?P[^/]+)/?(?:[#?]|$) + ''' _TESTS = [{ 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/', @@ -140,13 +176,16 @@ class SafariCourseIE(SafariBaseIE): }, { 'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json', 'only_matching': True, + }, { + 'url': 'http://techbus.safaribooksonline.com/9780134426365', + 'only_matching': True, }] def _real_extract(self, url): course_id = self._match_id(url) course_json = self._download_json( - '%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT), + '%s/book/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT), course_id, 'Downloading course JSON') if 'chapters' not in course_json: @@ -154,7 +193,7 @@ class SafariCourseIE(SafariBaseIE): 'No chapters found for course %s' % course_id, expected=True) entries = [ - self.url_result(chapter, 'Safari') + self.url_result(chapter, SafariApiIE.ie_key()) for chapter in course_json['chapters']] course_title = course_json['title']