linkinator - npm Package Compare versions

Comparing version 1.1.6 to 1.1.7

build/src/links.js

@@ -30,4 +30,3 @@ "use strict";
     });
-    const sanitized = links.filter(link => !!link)
-        .map(link => normalizeLink(link, baseUrl).href);
+    const sanitized = links.filter(link => !!link).map(link => normalizeLink(link, baseUrl));
     return sanitized;
@@ -37,6 +36,11 @@ }
 function normalizeLink(link, baseUrl) {
-    const slink = new url_1.URL(link, baseUrl);
-    slink.hash = '';
-    return slink;
+    try {
+        const slink = new url_1.URL(link, baseUrl);
+        slink.hash = '';
+        return slink.href;
+    }
+    catch (e) {
+        return link;
+    }
 }
 //# sourceMappingURL=links.js.map

package.json

 {
   "name": "linkinator",
-  "description": "Find broken links, missing images, etc in your HTML.",
-  "version": "1.1.6",
+  "description": "Find broken links, missing images, etc in your HTML. Scurry around your site and find all those broken links.",
+  "version": "1.1.7",
   "license": "MIT",
@@ -44,3 +44,3 @@ "repository": "JustinBeckwith/linkinator",
     "gts": "^0.9.0",
-    "mocha": "^5.2.0",
+    "mocha": "^6.0.0",
     "nock": "^10.0.6",
@@ -65,3 +65,7 @@ "nyc": "^13.3.0",
     "seo",
-    "url"
+    "url",
+    "broken link checker",
+    "broken",
+    "link",
+    "checker"
   ],
@@ -68,0 +72,0 @@ "nyc": {

README.md

@@ -0,4 +1,4 @@
+# 🐿 linkinator
+> A super simple site crawler and broken link checker.
 
-
-# 🐿 linkinator
 [![npm version](https://img.shields.io/npm/v/linkinator.svg)](https://www.npmjs.org/package/linkinator)
@@ -11,12 +11,46 @@ [![Build Status](https://api.cirrus-ci.com/github/JustinBeckwith/linkinator.svg)](https://cirrus-ci.com/github/JustinBeckwith/linkinator)
 
-> A super simple site crawler and broken link checker.
 
+Behold my latest inator! The `linkinator` provides an API and CLI for crawling websites and validating links.  It's got a ton of sweet features:
+- 🔥Easily perform scans on remote sites or local files
+- 🔥Scan any element that includes links, not just `<a href>`
+- 🔥Supports redirects, absolute links, relative links, all the things
+- 🔥Configure specific regex patterns to skip
+
 ## Installation
-```bash
+
+```sh
 $ npm install linkinator
 ```
 
-## Usage
+## Command Usage
+
 You can use this as a library, or as a CLI.  Let's see the CLI!
+
 ```sh
+$ linkinator LOCATION [ --arguments ]
+
+  Positional arguments
+
+    LOCATION
+      Required. Either the URL or the path on disk to check for broken links.
+
+  Flags
+    --recurse, -r
+        Recurively follow links on the same root domain.
+
+    --skip, -s
+        List of urls in regexy form to not include in the check.
+
+    --include, -i
+        List of urls in regexy form to include.  The opposite of --skip.
+
+    --help
+        Show this command.
+```
+
+### Command Examples
+
+You can run a shallow scan of a website for busted links:
+
+```sh
 $ npx linkinator http://jbeckwith.com
@@ -26,2 +60,3 @@ ```
 That was fun.  What about local files?  The linkinator will stand up a static web server for yinz:
+
 ```sh
@@ -32,2 +67,3 @@ $ npx linkinator ./docs
 But that only gets the top level of links.  Lets go deeper and do a full recursive scan!
+
 ```sh
@@ -38,2 +74,3 @@ $ npx linkinator ./docs --recurse
 Aw, snap.  I didn't want that to check *those* links.  Let's skip em:
+
 ```sh
@@ -43,3 +80,117 @@ $ npx linkinator ./docs --skip www.googleapis.com
 
+The `--skip` parameter will accept any regex! You can do more complex matching, or even tell it to only scan links with a given domain:
+
+```sh
+$ linkinator http://jbeckwith.com --skip '^(?!http://jbeckwith.com)'
+```
+
+## API Usage
+
+#### linkinator.check(options)
+Asynchronous method that runs a site wide scan. Options come in the form of an object that includes:
+- `path` (string) - A fully qualified path to the url to be scanned, or the path to the directory on disk that contains files to be scanned. *required*.
+- `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.
+
+#### 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:
+- `pagestart` (string) - Provides the url that the crawler has just started to scan.
+- `link` (object) - Provides an object with
+  - `url` (string) - The url that was scanned
+  - `state` (string) - The result of the scan.  Potential values include `BROKEN`, `OK`, or `SKIPPED`.
+  - `status` (number) - The HTTP status code of the request.
+
+### Simple example
+
+```js
+const link = require('linkinator');
+
+async function simple() {
+  const results = await link.check({
+    path: 'http://example.com'
+  });
+
+  // To see if all the links passed, you can check `passed`
+  console.log(`Passed: ${results.passed}`);
+
+  // Show the list of scanned links and their results
+  console.log(results);
+
+  // Example output:
+  // {
+  //   passed: true,
+  //   links: [
+  //     {
+  //       url: 'http://example.com',
+  //       status: 200,
+  //       state: 'OK'
+  //     },
+  //     {
+  //       url: 'http://www.iana.org/domains/example',
+  //       status: 200,
+  //       state: 'OK'
+  //     }
+  //   ]
+  // }
+}
+simple();
+```
+
+### Complete example
+
+In most cases you're going to want to respond to events, as running the check command can kinda take a long time.
+
+```js
+const link = require('linkinator');
+
+async function complex() {
+  // create a new `LinkChecker` that we'll use to run the scan.
+  const checker = new link.LinkChecker();
+
+  // Respond to the beginning of a new page being scanned
+  checker.on('pagestart', url => {
+    console.log(`Scanning ${url}`);
+  });
+
+  // After a page is scanned, check out the results!
+  checker.on('link', result => {
+
+    // check the specific url that was scanned
+    console.log(`  ${result.url}`);
+
+    // How did the scan go?  Potential states are `BROKEN`, `OK`, and `SKIPPED`
+    console.log(`  ${result.state}`);
+
+    // What was the status code of the response?
+    console.log(`  ${result.status}`);
+  });
+
+  // Go ahead and start the scan! As events occur, we will see them above.
+  const result = await checker.check({
+    path: 'http://example.com',
+    // port: 8673,
+    // recurse?: true,
+    // linksToSkip: [
+    //   'https://jbeckwith.com/some/link',
+    //   'http://example.com'
+    // ]
+  });
+
+  // Check to see if the scan passed!
+  console.log(result.passed ? 'PASSED :D' : 'FAILED :(');
+
+  // How many links did we scan?
+  console.log(`Scanned total of ${result.links.length} links!`);
+
+  // The final result will contain the list of checked links, and the pass/fail
+  const brokeLinksCount = result.links.filter(x => x.state === 'BROKEN');
+  console.log(`Detected ${brokeLinksCount.length} broken links.`);
+}
+
+complex();
+```
+
 ## License
+
 [MIT](LICENSE)

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

31869

increased by19.15%

Lines of code

368

increased by1.1%

Number of lines in readme file

192

increased by368.29%

No dependency changes