From 5982f089383299080c01a345ba251f5ea6af6bd9 Mon Sep 17 00:00:00 2001
From: Filip Engberg <filip@itiden.se>
Date: Fri, 12 Dec 2014 09:22:02 +0100
Subject: [PATCH 1/2] Added plugin for finding links in content using Regular
 expression

---
 config/linkcheckerrc                |  3 ++
 linkcheck/plugins/regexlinkcheck.py | 71 +++++++++++++++++++++++++++++
 2 files changed, 74 insertions(+)
 create mode 100644 linkcheck/plugins/regexlinkcheck.py

diff --git a/config/linkcheckerrc b/config/linkcheckerrc
index 2dc4e3606..e9bc2911c 100644
--- a/config/linkcheckerrc
+++ b/config/linkcheckerrc
@@ -269,3 +269,6 @@
 # Parse and check links in Word files
 #[WordParser]
 
+# Search for and check links in page contents using regular expression 
+[RegexLinkCheck]
+linkregex=:"([^"]*\.html)"
diff --git a/linkcheck/plugins/regexlinkcheck.py b/linkcheck/plugins/regexlinkcheck.py
new file mode 100644
index 000000000..3bce023f0
--- /dev/null
+++ b/linkcheck/plugins/regexlinkcheck.py
@@ -0,0 +1,71 @@
+# -*- coding: iso-8859-1 -*-
+# Copyright (C) 2000-2014 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.
+"""
+Check page content with regular expression for links.
+"""
+import re
+from . import _ContentPlugin
+from .. import log, LOG_PLUGIN
+
+
+class RegexLinkCheck(_ContentPlugin):
+    """Define a regular expression which matches any content.
+    It will treat matched content as a url and check it. 
+    This applies only to valid pages, so we can get their content.
+
+    Use this to check for pages that contain urls that cannot 
+    be found using the built-in tag finding, 
+    for example if there are urls defined in a json object.
+
+    Note that multiple values can be combined in the regular expression"."""
+
+    def __init__(self, config):
+        """Set link regex from config."""
+        super(RegexLinkCheck, self).__init__(config)
+        self.linkregex = None
+        pattern = config["linkregex"]
+        if pattern:
+            try:
+                self.linkregex = re.compile(pattern)
+            except re.error as msg:
+                log.warn(LOG_PLUGIN, "Invalid regex pattern %r: %s" % (pattern, msg))
+
+    def applies_to(self, url_data):
+        """Check for linkregex, extern flag and parseability."""
+        return self.linkregex and not url_data.extern[0] and url_data.is_parseable()
+
+    def check(self, url_data):
+        """Check content."""
+        log.debug(LOG_PLUGIN, "checking content for link regex")
+        content = url_data.get_content()
+        # add urls for found matches, up to the maximum allowed number
+        match = self.linkregex.search(content)
+        if match:
+            url_data.add_url(match.group(1))
+
+    @classmethod
+    def read_config(cls, configparser):
+        """Read configuration file options."""
+        config = dict()
+        section = cls.__name__
+        option = "linkregex"
+        if configparser.has_option(section, option):
+            value = configparser.get(section, option)
+        else:
+            value = None
+        config[option] = value
+        return config

From 847b3a3a807940809fa1ca3566da5891121a2332 Mon Sep 17 00:00:00 2001
From: Filip Engberg <filip@itiden.se>
Date: Mon, 15 Dec 2014 10:24:56 +0100
Subject: [PATCH 2/2] Comment out plugin by default

---
 config/linkcheckerrc | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/config/linkcheckerrc b/config/linkcheckerrc
index e9bc2911c..3bf72b2e6 100644
--- a/config/linkcheckerrc
+++ b/config/linkcheckerrc
@@ -270,5 +270,5 @@
 #[WordParser]
 
 # Search for and check links in page contents using regular expression 
-[RegexLinkCheck]
-linkregex=:"([^"]*\.html)"
+#[RegexLinkCheck]
+#linkregex=:"([^"]*\.html)"