add filterLinks option

JustinBeckwith · Nov 19, 2019 · bc60619 · bc60619
1 parent d653f2c
commit bc60619
Show file tree

Hide file tree

Showing 4 changed files with 28 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -128,6 +128,7 @@ Asynchronous method that runs a site wide scan. Options come in the form of an o
 - `port` (number) - When the `path` is provided as a local path on disk, the `port` on which to start the temporary web server. Defaults to a random high range order port.
 - `recurse` (boolean) - By default, all scans are shallow. Only the top level links on the requested page will be scanned. By setting `recurse` to `true`, the crawler will follow all links on the page, and continue scanning links **on the same domain** for as long as it can go. Results are cached, so no worries about loops.
 - `linksToSkip` (array) - An array of regular expression strings that should be skipped during the scan.
+- `filterLinks` (function) - A function that's called for each link with the link URL as its only argument. Return `true` to skip the link or `false` to check it.
 
 #### linkinator.LinkChecker()
 Constructor method that can be used to create a new `LinkChecker` instance. This is particularly useful if you want to receive events as the crawler crawls. Exposes the following events:

diff --git a/src/index.ts b/src/index.ts
@@ -17,6 +17,7 @@ export interface CheckOptions {
  path: string;
  recurse?: boolean;
  linksToSkip?: string[];
+ filterLink?: (arg0: string) => boolean;
 }
 
 export enum LinkState {
@@ -144,7 +145,7 @@ export class LinkChecker extends EventEmitter {
  })
  .filter(match => !!match);
 
- if (skips.length > 0) {
+ if (skips.length > 0 || (opts.checkOptions.filterLink && opts.checkOptions.filterLink(opts.url.href))) {
  const result: LinkResult = {
  url: opts.url.href,
  state: LinkState.SKIPPED,

diff --git a/test/fixtures/filter/index.html b/test/fixtures/filter/index.html
@@ -0,0 +1,7 @@
+<html>
+<body>
+<a href="https://good.com">I'm good</a>
+<a href="http://www.filterme.com">I should be filtered</a>
+<a href="https://example.com/filtermetoo">I should also be filtered</a>
+</body>
+</html>
diff --git a/test/test.ts b/test/test.ts
@@ -45,6 +45,24 @@ describe('linkinator', () => {
  );
  });
 
+ it('should skip links if passed a filterLink function', async () => {
+ const scope = nock('https://good.com')
+ .head('/')
+ .reply(200);
+ const results = await check({
+ path: 'test/fixtures/filter',
+ filterLink: (href) => {
+ return href.includes('filterme')
+ }
+ });
+ assert.ok(results.passed);
+ assert.strictEqual(
+ results.links.filter(x => x.state === LinkState.SKIPPED).length,
+ 2
+ );
+ scope.done();
+ });
+
  it('should report broken links', async () => {
  const scope = nock('http://fake.local')
  .head('/')