diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/adobepass.py | 210 | ||||
| -rw-r--r-- | youtube_dl/extractor/common.py | 10 |
2 files changed, 118 insertions, 102 deletions
diff --git a/youtube_dl/extractor/adobepass.py b/youtube_dl/extractor/adobepass.py index 50a208085..9add6c0f8 100644 --- a/youtube_dl/extractor/adobepass.py +++ b/youtube_dl/extractor/adobepass.py @@ -15,6 +15,20 @@ from ..utils import ( ) +MSO_INFO = { + 'DTV': { + 'name': 'DirecTV', + 'username_field': 'username', + 'password_field': 'password', + }, + 'Rogers': { + 'name': 'Rogers Cable', + 'username_field': 'UserName', + 'password_field': 'UserPassword', + }, +} + + class AdobePassIE(InfoExtractor): _SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s' _USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0' @@ -43,6 +57,18 @@ class AdobePassIE(InfoExtractor): token_expires = unified_timestamp(re.sub(r'[_ ]GMT', '', xml_text(token, date_ele))) return token_expires and token_expires <= int(time.time()) + def post_form(form_page_res, note, data={}): + form_page, urlh = form_page_res + post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url') + if not re.match(r'https?://', post_url): + post_url = compat_urlparse.urljoin(urlh.geturl(), post_url) + form_data = self._hidden_inputs(form_page) + form_data.update(data) + return self._download_webpage_handle( + post_url, video_id, note, data=urlencode_postdata(form_data), headers={ + 'Content-Type': 'application/x-www-form-urlencoded', + }) + def raise_mvpd_required(): raise ExtractorError( 'This video is only available for users of participating TV providers. ' @@ -57,105 +83,95 @@ class AdobePassIE(InfoExtractor): } guid = xml_text(resource, 'guid') - requestor_info = self._downloader.cache.load('mvpd', requestor_id) or {} - authn_token = requestor_info.get('authn_token') - if authn_token and is_expired(authn_token, 'simpleTokenExpires'): - authn_token = None - if not authn_token: - # TODO add support for other TV Providers - mso_id = self._downloader.params.get('ap_mso_id') - if not mso_id: - raise_mvpd_required() - username, password = self._get_netrc_login_info(mso_id) - if not username or not password: - return raise_mvpd_required() - - def post_form(form_page_res, note, data={}): - form_page, urlh = form_page_res - post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url') - if not re.match(r'https?://', post_url): - post_url = compat_urlparse.urljoin(urlh.geturl(), post_url) - form_data = self._hidden_inputs(form_page) - form_data.update(data) - return self._download_webpage_handle( - post_url, video_id, note, data=urlencode_postdata(form_data), headers={ - 'Content-Type': 'application/x-www-form-urlencoded', + retries = self._downloader.params.get('ap_retries', 3) + count = 0 + while count < retries: + requestor_info = self._downloader.cache.load('mvpd', requestor_id) or {} + authn_token = requestor_info.get('authn_token') + if authn_token and is_expired(authn_token, 'simpleTokenExpires'): + authn_token = None + if not authn_token: + # TODO add support for other TV Providers + mso_id = self._downloader.params.get('ap_mso_id') + if not mso_id: + raise_mvpd_required() + if mso_id not in MSO_INFO: + raise ExtractorError( + 'Unsupported TV Provider, use --list-ap-mso-ids to get a list of supported TV Providers' % mso_id, expected=True) + username, password = self._get_login_info('ap_username', 'ap_password', mso_id) + if not username or not password: + raise_mvpd_required() + mso_info = MSO_INFO[mso_id] + + provider_redirect_page_res = self._download_webpage_handle( + self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id, + 'Downloading Provider Redirect Page', query={ + 'noflash': 'true', + 'mso_id': mso_id, + 'requestor_id': requestor_id, + 'no_iframe': 'false', + 'domain_name': 'adobe.com', + 'redirect_url': url, }) - - provider_redirect_page_res = self._download_webpage_handle( - self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id, - 'Downloading Provider Redirect Page', query={ - 'noflash': 'true', - 'mso_id': mso_id, - 'requestor_id': requestor_id, - 'no_iframe': 'false', - 'domain_name': 'adobe.com', - 'redirect_url': url, + provider_login_page_res = post_form( + provider_redirect_page_res, 'Downloading Provider Login Page') + mvpd_confirm_page_res = post_form(provider_login_page_res, 'Logging in', { + mso_info['username_field']: username, + mso_info['password_field']: password, }) - provider_login_page_res = post_form( - provider_redirect_page_res, 'Downloading Provider Login Page') - login_data = {} - if mso_id == 'DTV': - login_data = { - 'username': username, - 'password': password, - } - elif mso_id == 'Rogers': - login_data = { - 'UserName': username, - 'UserPassword': password, - } - mvpd_confirm_page_res = post_form(provider_login_page_res, 'Logging in', login_data) - if mso_id == 'DTV': - post_form(mvpd_confirm_page_res, 'Confirming Login') - - session = self._download_webpage( - self._SERVICE_PROVIDER_TEMPLATE % 'session', video_id, - 'Retrieving Session', data=urlencode_postdata({ - '_method': 'GET', - 'requestor_id': requestor_id, - }), headers=mvpd_headers) - if '<pendingLogout' in session: - self._downloader.cache.store('mvpd', requestor_id, {}) - return self._extract_mvpd_auth(url, video_id, requestor_id, resource) - authn_token = unescapeHTML(xml_text(session, 'authnToken')) - requestor_info['authn_token'] = authn_token - self._downloader.cache.store('mvpd', requestor_id, requestor_info) - - authz_token = requestor_info.get(guid) - if authz_token and is_expired(authz_token, 'simpleTokenTTL'): - authz_token = None - if not authz_token: - authorize = self._download_webpage( - self._SERVICE_PROVIDER_TEMPLATE % 'authorize', video_id, - 'Retrieving Authorization Token', data=urlencode_postdata({ - 'resource_id': resource, + if mso_id == 'DTV': + post_form(mvpd_confirm_page_res, 'Confirming Login') + + session = self._download_webpage( + self._SERVICE_PROVIDER_TEMPLATE % 'session', video_id, + 'Retrieving Session', data=urlencode_postdata({ + '_method': 'GET', + 'requestor_id': requestor_id, + }), headers=mvpd_headers) + if '<pendingLogout' in session: + self._downloader.cache.store('mvpd', requestor_id, {}) + count += 1 + continue + authn_token = unescapeHTML(xml_text(session, 'authnToken')) + requestor_info['authn_token'] = authn_token + self._downloader.cache.store('mvpd', requestor_id, requestor_info) + + authz_token = requestor_info.get(guid) + if authz_token and is_expired(authz_token, 'simpleTokenTTL'): + authz_token = None + if not authz_token: + authorize = self._download_webpage( + self._SERVICE_PROVIDER_TEMPLATE % 'authorize', video_id, + 'Retrieving Authorization Token', data=urlencode_postdata({ + 'resource_id': resource, + 'requestor_id': requestor_id, + 'authentication_token': authn_token, + 'mso_id': xml_text(authn_token, 'simpleTokenMsoID'), + 'userMeta': '1', + }), headers=mvpd_headers) + if '<pendingLogout' in authorize: + self._downloader.cache.store('mvpd', requestor_id, {}) + count += 1 + continue + authz_token = unescapeHTML(xml_text(authorize, 'authzToken')) + requestor_info[guid] = authz_token + self._downloader.cache.store('mvpd', requestor_id, requestor_info) + + mvpd_headers.update({ + 'ap_19': xml_text(authn_token, 'simpleSamlNameID'), + 'ap_23': xml_text(authn_token, 'simpleSamlSessionIndex'), + }) + + short_authorize = self._download_webpage( + self._SERVICE_PROVIDER_TEMPLATE % 'shortAuthorize', + video_id, 'Retrieving Media Token', data=urlencode_postdata({ + 'authz_token': authz_token, 'requestor_id': requestor_id, - 'authentication_token': authn_token, - 'mso_id': xml_text(authn_token, 'simpleTokenMsoID'), - 'userMeta': '1', + 'session_guid': xml_text(authn_token, 'simpleTokenAuthenticationGuid'), + 'hashed_guid': 'false', }), headers=mvpd_headers) - if '<pendingLogout' in authorize: + if '<pendingLogout' in short_authorize: self._downloader.cache.store('mvpd', requestor_id, {}) - return self._extract_mvpd_auth(url, video_id, requestor_id, resource) - authz_token = unescapeHTML(xml_text(authorize, 'authzToken')) - requestor_info[guid] = authz_token - self._downloader.cache.store('mvpd', requestor_id, requestor_info) - - mvpd_headers.update({ - 'ap_19': xml_text(authn_token, 'simpleSamlNameID'), - 'ap_23': xml_text(authn_token, 'simpleSamlSessionIndex'), - }) - - short_authorize = self._download_webpage( - self._SERVICE_PROVIDER_TEMPLATE % 'shortAuthorize', - video_id, 'Retrieving Media Token', data=urlencode_postdata({ - 'authz_token': authz_token, - 'requestor_id': requestor_id, - 'session_guid': xml_text(authn_token, 'simpleTokenAuthenticationGuid'), - 'hashed_guid': 'false', - }), headers=mvpd_headers) - if '<pendingLogout' in short_authorize: - self._downloader.cache.store('mvpd', requestor_id, {}) - return self._extract_mvpd_auth(url, video_id, requestor_id, resource) - return short_authorize + count += 1 + continue + return short_authorize diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 6edd5a769..ff19270ae 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -680,7 +680,7 @@ class InfoExtractor(object): return (username, password) - def _get_login_info(self): + def _get_login_info(self, username_option='username', password_option='password', netrc_machine=None): """ Get the login info as (username, password) It will look in the netrc file using the _NETRC_MACHINE value @@ -694,11 +694,11 @@ class InfoExtractor(object): downloader_params = self._downloader.params # Attempt to use provided username and password or .netrc data - if downloader_params.get('username') is not None: - username = downloader_params['username'] - password = downloader_params['password'] + if downloader_params.get(username_option) is not None: + username = downloader_params[username_option] + password = downloader_params[password_option] else: - username, password = self._get_netrc_login_info() + username, password = self._get_netrc_login_info(netrc_machine) return (username, password) |