Support itms-services: URLs. #532

doc/changelog.txt

@@ -1,5 +1,9 @@
 9.4 "" (released xx.xx.xxxx)
 
+Features:
+- checking: Support itms-services: URLs.
+  Closes: GH bug #532
+
 
 9.3 "Better Living Through Chemistry" (released 16.7.2014)
 

linkcheck/checker/__init__.py

@@ -143,6 +143,8 @@ def get_urlclass_from (scheme, assume_local_file=False):
         klass = nntpurl.NntpUrl
     elif scheme == "dns":
         klass = dnsurl.DnsUrl
+    elif scheme == "itms-services":
+        klass = itmsservicesurl.ItmsServicesUrl
     elif scheme and unknownurl.is_unknown_scheme(scheme):
         klass = unknownurl.UnknownUrl
     elif assume_local_file:
@@ -174,4 +176,4 @@ def get_index_html (urls):
 
 # all the URL classes
 from . import (fileurl, unknownurl, ftpurl, httpurl, dnsurl,
-    mailtourl, telneturl, nntpurl, ignoreurl)
+    mailtourl, telneturl, nntpurl, ignoreurl, itmsservicesurl)

linkcheck/checker/itmsservicesurl.py

@@ -0,0 +1,45 @@
+# -*- coding: iso-8859-1 -*-
+# Copyright (C) 2014 Bastian Kleineidam
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License along
+# with this program; if not, write to the Free Software Foundation, Inc.,
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+"""
+Handle itms-services URLs.
+"""
+
+from . import urlbase
+from .. import log, LOG_CHECK
+
+
+class ItmsServicesUrl(urlbase.UrlBase):
+    """Apple iOS application download URLs."""
+
+    def check_syntax(self):
+        """Only logs that this URL is unknown."""
+        super(ItmsServicesUrl, self).check_syntax()
+        if u"url=" not in self.urlparts[3]:
+            self.set_result(_("Missing required url parameter"), valid=False)
+
+    def local_check(self):
+        """Disable content checks."""
+        log.debug(LOG_CHECK, "Checking %s", unicode(self))
+        pass
+
+    def check_content(self):
+        """Allow recursion to check the url CGI param."""
+        return True
+
+    def is_parseable(self):
+        """This URL is parseable."""
+        return True

linkcheck/parser/__init__.py

@@ -17,7 +17,7 @@
 """
 Main functions for link parsing
 """
-from .. import log, LOG_CHECK, strformat
+from .. import log, LOG_CHECK, strformat, url as urlutil
 from ..htmlutil import linkparse
 from ..HtmlParser import htmlsax
 from ..bookmarks import firefox
@@ -30,6 +30,8 @@ def parse_url(url_data):
         key = "html"
     elif url_data.is_file() and firefox.has_sqlite and firefox.extension.search(url_data.url):
         key = "firefox"
+    elif url_data.scheme == "itms-services":
+        key = "itms_services"
     else:
         # determine parse routine according to content types
         mime = url_data.content_type
@@ -140,4 +142,13 @@ def parse_firefox (url_data):
         url_data.add_url(url, name=name)
 
 
+def parse_itms_services(url_data):
+    """Get "url" CGI parameter value as child URL."""
+    query = url_data.urlparts[3]
+    for k, v, sep in urlutil.parse_qsl(query, keep_blank_values=True):
+        if k == "url":
+            url_data.add_url(v)
+            break
+
+
 from .sitemap import parse_sitemap, parse_sitemapindex