Fixed #7: some pages incorrectly marked not valid HTML

fallax · Nov 20, 2024 · d997f86 · d997f86
1 parent 956e022
commit d997f86
Show file tree

Hide file tree

Showing 3 changed files with 12 additions and 6 deletions.
diff --git a/README.md b/README.md
@@ -55,6 +55,12 @@ To check all the links within a live web page, skipping over internal links:
 curl https://test.com | sed -n 's/.*href="\(h[^"]*\).*/\1/p' | coroner -s test.com
 ```
 
+Check all links within markdown files in a folder or its subfolders recursively:
+
+```
+find . -name "*.md" -not \( -name .svn -prune -o -name .git -prune \) -type f -print0 | xargs -0 sed -n 's/.*(\(http[^)]*\).*/\1/p' | coroner
+```
+
 ## Options
 
 Options are:

diff --git a/package.json b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "coroner",
-  "version": "1.0.5",
+  "version": "1.0.6",
   "type": "commonjs",
   "exports": "./index.js",
   "description": "more useful dead link detection",

diff --git a/tests.js b/tests.js
@@ -160,11 +160,11 @@ const tests = [
         statusCodes: [200, 304],
         name: 'validHTML', // Check the response body looks like a valid HTML document
         test: (input, options, response, responseText) =>
-            !responseText.slice(0, 30).trim().toLowerCase().startsWith("<!doctype html") && 
-            !responseText.slice(0, 30).trim().toLowerCase().startsWith("<html") &&
-            !responseText.slice(0, 30).trim().toLowerCase().startsWith("<!--") &&
-            !responseText.slice(0, 60).trim().toLowerCase().startsWith("<?xml version=\"1.0\" encoding=\"utf-8\"?><!doctype html"),
-        reason: (input, options, response, responseText) => "Does not look like a valid HTML file: first characters are " + responseText.slice(0, 60).trim().toLowerCase()
+            !responseText.slice(0, 100).trim().toLowerCase().startsWith("<!doctype html") && 
+            !responseText.slice(0, 100).trim().toLowerCase().startsWith("<html") &&
+            !responseText.slice(0, 100).trim().toLowerCase().startsWith("<!--") &&
+            !responseText.slice(0, 100).trim().toLowerCase().startsWith("<?xml version=\"1.0\" encoding=\"utf-8\"?><!doctype html"),
+        reason: (input, options, response, responseText) => "Does not look like a valid HTML file: first characters are '" + responseText.slice(0, 60).trim().toLowerCase() + "'"
     },
     {
         phase: 'post',