From b30fb3b09cf1ee270c348ee44de3d9336ba98bb8 Mon Sep 17 00:00:00 2001
From: calvin <calvin@e7d03fd6-7b0d-0410-9947-9c21f3af8025>
Date: Mon, 16 Jun 2008 19:52:09 +0000
Subject: [PATCH] Remove duplicate code in http checker.

git-svn-id: https://linkchecker.svn.sourceforge.net/svnroot/linkchecker/trunk/linkchecker@3820 e7d03fd6-7b0d-0410-9947-9c21f3af8025
---
 linkcheck/checker/const.py   |  5 +++++
 linkcheck/checker/httpurl.py | 17 +++++------------
 2 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/linkcheck/checker/const.py b/linkcheck/checker/const.py
index 28019d93..6f95fd4b 100644
--- a/linkcheck/checker/const.py
+++ b/linkcheck/checker/const.py
@@ -144,6 +144,11 @@ PARSE_MIMETYPES = (
     "application/x-shockwave-flash",
 )
 
+HTML_MIMETYPES = (
+    "text/html",
+    "application/xhtml+xml",
+)
+
 # if file extension lookup was unsuccessful, look at the content
 PARSE_CONTENTS = {
     "html": re.compile(r'^(?i)<(!DOCTYPE html|html|head|title)'),
diff --git a/linkcheck/checker/httpurl.py b/linkcheck/checker/httpurl.py
index af2631f2..50ad7af0 100644
--- a/linkcheck/checker/httpurl.py
+++ b/linkcheck/checker/httpurl.py
@@ -36,7 +36,7 @@ from .const import WARN_HTTP_ROBOTS_DENIED, WARN_HTTP_NO_ANCHOR_SUPPORT, \
     WARN_HTTP_WRONG_REDIRECT, WARN_HTTP_MOVED_PERMANENT, \
     WARN_HTTP_EMPTY_CONTENT, WARN_HTTP_COOKIE_STORE_ERROR, \
     WARN_HTTP_DECOMPRESS_ERROR, WARN_HTTP_UNSUPPORTED_ENCODING, \
-    PARSE_MIMETYPES
+    PARSE_MIMETYPES, HTML_MIMETYPES
 
 # helper alias
 unicode_safe = strformat.unicode_safe
@@ -606,7 +606,7 @@ Use URL %(newurl)s instead for checking.""") % {
         """
         if not (self.valid and self.headers):
             return False
-        if headers.get_content_type(self.headers) not in ("text/html", "application/xhtml+xml"):
+        if headers.get_content_type(self.headers) not in HTML_MIMETYPES:
             return False
         return self.encoding_supported()
 
@@ -638,23 +638,16 @@ Use URL %(newurl)s instead for checking.""") % {
             return False
         if headers.get_content_type(self.headers) not in PARSE_MIMETYPES:
             return False
-        encoding = headers.get_content_encoding(self.headers)
-        if encoding and encoding not in _supported_encodings and \
-           encoding != 'identity':
-            self.add_warning(_('Unsupported content encoding %(encoding)r.') %
-                             {"encoding": encoding},
-                             tag=WARN_HTTP_UNSUPPORTED_ENCODING)
-            return False
-        return True
+        return self.encoding_supported()
 
     def parse_url (self):
         """
         Parse file contents for new links to check.
         """
         ctype = headers.get_content_type(self.headers)
-        if ctype in ("text/html", "application/xhtml+xml"):
+        if self.is_html():
             self.parse_html()
-        elif ctype == "text/css":
+        elif self.is_css():
             self.parse_css()
         elif ctype == "application/x-shockwave-flash":
             self.parse_swf()