Fix missing content types for cached URLs.

doc/changelog.txt

@@ -7,6 +7,7 @@ Fixes:
   internal links when given as start URL.
 - logging: Allow Unicode strings to be written to stdout without
   encoding errors on Unix systems.
+- logging: Fix missing content type for cached URLs.
 - gui: Reset statistics before each run.
 
 Changes:

linkcheck/checker/fileurl.py

@@ -255,9 +255,12 @@ class FileUrl (urlbase.UrlBase):
             self.aggregate.urlqueue.put(url_data)
 
     def get_content_type (self):
-        if self.url:
-            return fileutil.guess_mimetype(self.url, read=self.get_content)
-        return u""
+        if self.content_type is None:
+            if self.url:
+                self.content_type = fileutil.guess_mimetype(self.url, read=self.get_content)
+            else:
+                self.content_type = u""
+        return self.content_type
 
     def get_intern_pattern (self):
         """

linkcheck/checker/ftpurl.py

@@ -206,7 +206,9 @@ class FtpUrl (internpaturl.InternPatternUrl, proxysupport.ProxySupport):
         getattr(self, "parse_"+key)()
 
     def get_content_type (self, read=None):
-        return fileutil.guess_mimetype(self.url, read=read)
+        if self.content_type is None:
+            self.content_type = fileutil.guess_mimetype(self.url, read=read)
+        return self.content_type
 
     def read_content (self):
         """Return URL target content, or in case of directories a dummy HTML

linkcheck/checker/httpurl.py

@@ -284,9 +284,12 @@ class HttpUrl (internpaturl.InternPatternUrl, proxysupport.ProxySupport):
 
     def get_content_type (self):
         """Return content MIME type or empty string."""
-        if self.headers:
-            return headers.get_content_type(self.headers)
-        return u""
+        if self.content_type is None:
+            if self.headers:
+               self.content_type = headers.get_content_type(self.headers)
+            else:
+                self.content_type = u""
+        return self.content_type
 
     def follow_redirections (self, response, set_result=True):
         """

linkcheck/checker/urlbase.py

@@ -179,6 +179,8 @@ class UrlBase (object):
         self.title = None
         # flag if content should be checked or not
         self.do_check_content = True
+        # MIME content type
+        self.content_type = None
 
     def set_result (self, msg, valid=True, overwrite=False):
         """
@@ -295,6 +297,7 @@ class UrlBase (object):
         self.dltime = cache_data["dltime"]
         self.dlsize = cache_data["dlsize"]
         self.anchors = cache_data["anchors"]
+        self.content_type = cache_data["content_type"]
         self.cached = True
         if anchor_changed and self.valid and self.anchor:
             # recheck anchor
@@ -312,6 +315,7 @@ class UrlBase (object):
                 "dlsize": self.dlsize,
                 "anchors": self.anchors,
                 "anchor": self.anchor,
+                "content_type": self.get_content_type(),
                }
 
     def get_alias_cache_data (self):
@@ -654,7 +658,9 @@ class UrlBase (object):
     def get_content_type (self):
         """Return content MIME type or empty string.
         Should be overridden in subclasses."""
-        return u""
+        if self.content_type is None:
+            self.content_type = u""
+        return self.content_type
 
     def can_get_content (self):
         """Indicate wether url get_content() can be called."""