Cleanup of the UrlData.is_* functions

linkcheck/checker/fileurl.py

@@ -209,25 +209,6 @@ class FileUrl (urlbase.UrlBase):
             data = super(FileUrl, self).read_content()
         return data
 
-    def is_html (self):
-        """Check if file is a HTML file."""
-        return self.ContentMimetypes.get(self.get_content_type()) == "html"
-
-    def is_css (self):
-        """
-        Check if file is a CSS file.
-        """
-        return self.ContentMimetypes.get(self.get_content_type()) == "css"
-
-    def is_file (self):
-        """
-        This is a file.
-
-        @return: True
-        @rtype: bool
-        """
-        return True
-
     def get_os_filename (self):
         """
         Construct os specific file path out of the file:// URL.

linkcheck/checker/ftpurl.py

@@ -161,14 +161,6 @@ class FtpUrl (internpaturl.InternPatternUrl, proxysupport.ProxySupport):
         self.url_connection.dir(add_entry)
         return files
 
-    def is_html (self):
-        """See if URL target is a HTML file by looking at the extension."""
-        return self.ContentMimetypes.get(self.get_content_type()) == "html"
-
-    def is_css (self):
-        """See if URL target is a CSS file by looking at the extension."""
-        return self.ContentMimetypes.get(self.get_content_type()) == "css"
-
     def is_parseable (self):
         """See if URL target is parseable for recursion."""
         if self.is_directory():

linkcheck/checker/httpurl.py

@@ -217,35 +217,6 @@ class HttpUrl (internpaturl.InternPatternUrl, proxysupport.ProxySupport):
             buf.write(data)
         return buf.getvalue()
 
-    def is_html (self):
-        """
-        See if this URL points to a HTML file by looking at the
-        Content-Type header, file extension and file content.
-
-        @return: True if URL points to HTML file
-        @rtype: bool
-        """
-        if not self.valid:
-            return False
-        mime = self.get_content_type()
-        return self.ContentMimetypes.get(mime) == "html"
-
-    def is_css (self):
-        """Return True iff content of this url is CSS stylesheet."""
-        if not self.valid:
-            return False
-        mime = self.get_content_type()
-        return self.ContentMimetypes.get(mime) == "css"
-
-    def is_http (self):
-        """
-        This is a HTTP file.
-
-        @return: True
-        @rtype: bool
-        """
-        return True
-
     def is_parseable (self):
         """
         Check if content is parseable for recursion.

linkcheck/checker/urlbase.py

@@ -234,22 +234,27 @@ class UrlBase (object):
         return False
 
     def is_html (self):
-        """
-        Return True iff content of this url is HTML formatted.
-        """
-        return False
+        """Return True iff content of this url is HTML formatted."""
+        return self._is_ctype("html")
 
     def is_css (self):
         """Return True iff content of this url is CSS stylesheet."""
-        return False
+        return self._is_ctype("css")
+
+    def _is_ctype(self, ctype):
+        """Return True iff content is valid and of the given type."""
+        if not self.valid:
+            return False
+        mime = self.get_content_type()
+        return self.ContentMimetypes.get(mime) == ctype
 
     def is_http (self):
-        """Return True for http:// URLs."""
-        return False
+        """Return True for http:// or https:// URLs."""
+        return self.scheme in ("http", "https")
 
     def is_file (self):
         """Return True for file:// URLs."""
-        return False
+        return self.scheme == "file"
 
     def is_directory(self):
         """Return True if current URL represents a directory."""