[adobepass] create separate class for adobe pass authentication

2016-08-14 17:55:56 +01:00
parent 884cdb6cd9
commit 1fd6e30988
5 changed files with 134 additions and 99 deletions
--- a/youtube_dl/extractor/adobepass.py
+++ b/youtube_dl/extractor/adobepass.py
@@ -0,0 +1,124 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+import time
+import xml.etree.ElementTree as etree
+
+from .common import InfoExtractor
+from ..utils import (
+    unescapeHTML,
+    urlencode_postdata,
+    unified_timestamp,
+)
+
+
+class AdobePass(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'
+
+    @staticmethod
+    def _get_mvpd_resource(provider_id, title, guid, rating):
+        channel = etree.Element('channel')
+        channel_title = etree.SubElement(channel, 'title')
+        channel_title.text = provider_id
+        item = etree.SubElement(channel, 'item')
+        resource_title = etree.SubElement(item, 'title')
+        resource_title.text = title
+        resource_guid = etree.SubElement(item, 'guid')
+        resource_guid.text = guid
+        resource_rating = etree.SubElement(item, 'media:rating')
+        resource_rating.attrib = {'scheme': 'urn:v-chip'}
+        resource_rating.text = rating
+        return '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/">' + etree.tostring(channel).decode() + '</rss>'
+
+    def _extract_mvpd_auth(self, url, video_id, requestor_id, resource):
+        def xml_text(xml_str, tag):
+            return self._search_regex(
+                '<%s>(.+?)</%s>' % (tag, tag), xml_str, tag)
+
+        mvpd_headers = {
+            'ap_42': 'anonymous',
+            'ap_11': 'Linux i686',
+            'ap_z': self._USER_AGENT,
+            'User-Agent': self._USER_AGENT,
+        }
+
+        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:
+            token_expires = unified_timestamp(re.sub(r'[_ ]GMT', '', xml_text(authn_token, 'simpleTokenExpires')))
+            if token_expires and token_expires <= int(time.time()):
+                authn_token = None
+                requestor_info = {}
+        if not authn_token:
+            # TODO add support for other TV Providers
+            mso_id = 'DTV'
+            username, password = self._get_netrc_login_info(mso_id)
+            if not username or not password:
+                return ''
+
+            def post_form(form_page, note, data={}):
+                post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
+                return self._download_webpage(
+                    post_url, video_id, note, data=urlencode_postdata(data or self._hidden_inputs(form_page)), headers={
+                        'Content-Type': 'application/x-www-form-urlencoded',
+                    })
+
+            provider_redirect_page = self._download_webpage(
+                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 = post_form(
+                provider_redirect_page, 'Downloading Provider Login Page')
+            mvpd_confirm_page = post_form(provider_login_page, 'Logging in', {
+                'username': username,
+                'password': password,
+            })
+            post_form(mvpd_confirm_page, '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)
+            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 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)
+            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'),
+        })
+
+        return 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)
--- a/youtube_dl/extractor/aenetworks.py
+++ b/youtube_dl/extractor/aenetworks.py
@@ -109,7 +109,10 @@ class AENetworksIE(AENetworksBaseIE):
        info = self._parse_theplatform_metadata(theplatform_metadata)
        if theplatform_metadata.get('AETN$isBehindWall'):
            requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
-            resource = '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>%s</title><item><title>%s</title><guid>%s</guid><media:rating scheme="urn:v-chip">%s</media:rating></item></channel></rss>' % (requestor_id, theplatform_metadata['title'], theplatform_metadata['AETN$PPL_pplProgramId'], theplatform_metadata['ratings'][0]['rating'])
+            resource = self._get_mvpd_resource(
+                requestor_id, theplatform_metadata['title'],
+                theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
+                theplatform_metadata['ratings'][0]['rating'])
            query['auth'] = self._extract_mvpd_auth(
                url, video_id, requestor_id, resource)
        info.update(self._search_json_ld(webpage, video_id, fatal=False))
--- a/youtube_dl/extractor/nationalgeographic.py
+++ b/youtube_dl/extractor/nationalgeographic.py
@@ -119,7 +119,7 @@ class NationalGeographicIE(ThePlatformIE):
            auth_resource_id = self._search_regex(
                r"video_auth_resourceId\s*=\s*'([^']+)'",
                webpage, 'auth resource id')
-            query['auth'] = self._extract_mvpd_auth(url, display_id, 'natgeo', auth_resource_id) or ''
+            query['auth'] = self._extract_mvpd_auth(url, display_id, 'natgeo', auth_resource_id)

        return {
            '_type': 'url_transparent',
--- a/youtube_dl/extractor/syfy.py
+++ b/youtube_dl/extractor/syfy.py
@@ -40,7 +40,9 @@ class SyfyIE(ThePlatformIE):
            'manifest': 'm3u',
        }
        if syfy_mpx.get('entitlement') == 'auth':
-            resource = '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>syfy</title><item><title><![CDATA[%s]]></title><guid>%s</guid><media:rating scheme="urn:v-chip">%s</media:rating></item></channel></rss>' % (title, video_id, syfy_mpx.get('mpxRating', 'TV-14'))
+            resource = self._get_mvpd_resource(
+                'syfy', title, video_id,
+                syfy_mpx.get('mpxRating', 'TV-14'))
            query['auth'] = self._extract_mvpd_auth(
                url, video_id, 'syfy', resource)

--- a/youtube_dl/extractor/theplatform.py
+++ b/youtube_dl/extractor/theplatform.py
@@ -6,10 +6,10 @@ import time
 import hmac
 import binascii
 import hashlib
-import netrc


 from .once import OnceIE
+from .adobepass import AdobePass
 from ..compat import (
    compat_parse_qs,
    compat_urllib_parse_urlparse,
@@ -25,9 +25,6 @@ from ..utils import (
    xpath_with_ns,
    mimetype2ext,
    find_xpath_attr,
-    unescapeHTML,
-    urlencode_postdata,
-    unified_timestamp,
 )

 default_ns = 'http://www.w3.org/2005/SMIL21/Language'
@@ -96,7 +93,7 @@ class ThePlatformBaseIE(OnceIE):
        return self._parse_theplatform_metadata(info)


-class ThePlatformIE(ThePlatformBaseIE):
+class ThePlatformIE(ThePlatformBaseIE, AdobePass):
    _VALID_URL = r'''(?x)
        (?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
           (?:(?:(?:[^/]+/)+select/)?(?P<media>media/(?:guid/\d+/)?)|(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/))?
@@ -202,97 +199,6 @@ class ThePlatformIE(ThePlatformBaseIE):
        sig = flags + expiration_date + checksum + str_to_hex(sig_secret)
        return '%s&sig=%s' % (url, sig)

-    def _extract_mvpd_auth(self, url, video_id, requestor_id, resource):
-        def xml_text(xml_str, tag):
-            return self._search_regex(
-                '<%s>(.+?)</%s>' % (tag, tag), xml_str, tag)
-
-        mvpd_headers = {
-            'ap_42': 'anonymous',
-            'ap_11': 'Linux i686',
-            'ap_z': 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0',
-            'User-Agent': 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0',
-        }
-
-        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:
-            token_expires = unified_timestamp(re.sub(r'[_ ]GMT', '', xml_text(authn_token, 'simpleTokenExpires')))
-            if token_expires and token_expires <= int(time.time()):
-                authn_token = None
-                requestor_info = {}
-        if not authn_token:
-            # TODO add support for other TV Providers
-            mso_id = 'DTV'
-            username, password = self._get_netrc_login_info(mso_id)
-            if not username or not password:
-                return ''
-
-            def post_form(form_page, note, data={}):
-                post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
-                return self._download_webpage(
-                    post_url, video_id, note, data=urlencode_postdata(data or self._hidden_inputs(form_page)), headers={
-                        'Content-Type': 'application/x-www-form-urlencoded',
-                    })
-
-            provider_redirect_page = self._download_webpage(
-                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 = post_form(
-                provider_redirect_page, 'Downloading Provider Login Page')
-            mvpd_confirm_page = post_form(provider_login_page, 'Logging in', {
-                'username': username,
-                'password': password,
-            })
-            post_form(mvpd_confirm_page, '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)
-            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 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)
-            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'),
-        })
-
-        return 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)
-
    def _real_extract(self, url):
        url, smuggled_data = unsmuggle_url(url, {})