├── .github
    ├── FUNDING.yml
    └── workflows
    │   ├── fix-php-code-style-issues.yml
    │   ├── run-tests.yml
    │   └── update-changelog.yml
├── .phpunit.cache
    └── test-results
├── CHANGELOG.md
├── LICENSE.md
├── README.md
├── UPGRADING.md
├── composer.json
└── src
    ├── Exceptions
        └── InvalidUrl.php
    ├── MixedContent.php
    ├── MixedContentExtractor.php
    ├── MixedContentObserver.php
    └── MixedContentScanner.php


/.github/FUNDING.yml:
--------------------------------------------------------------------------------
1 | github: spatie
2 | 


--------------------------------------------------------------------------------
/.github/workflows/fix-php-code-style-issues.yml:
--------------------------------------------------------------------------------
 1 | name: Fix PHP code style issues
 2 | 
 3 | on:
 4 |   push:
 5 |     paths:
 6 |       - '**.php'
 7 | 
 8 | permissions:
 9 |   contents: write
10 | 
11 | jobs:
12 |   php-code-styling:
13 |     runs-on: ubuntu-latest
14 | 
15 |     steps:
16 |       - name: Checkout code
17 |         uses: actions/checkout@v3
18 |         with:
19 |           ref: ${{ github.head_ref }}
20 | 
21 |       - name: Fix PHP code style issues
22 |         uses: aglipanci/laravel-pint-action@2.3.0
23 | 
24 |       - name: Commit changes
25 |         uses: stefanzweifel/git-auto-commit-action@v4
26 |         with:
27 |           commit_message: Fix styling
28 | 


--------------------------------------------------------------------------------
/.github/workflows/run-tests.yml:
--------------------------------------------------------------------------------
 1 | name: Tests
 2 | 
 3 | on: [push, pull_request]
 4 | 
 5 | jobs:
 6 |     test:
 7 |         runs-on: ${{ matrix.os }}
 8 |         strategy:
 9 |             fail-fast: false
10 |             matrix:
11 |                 os: [ubuntu-latest]
12 |                 php: [8.1, 8.2]
13 |                 dependency-version: [prefer-lowest, prefer-stable]
14 | 
15 |         name: P${{ matrix.php }} - ${{ matrix.dependency-version }} - ${{ matrix.os }}
16 | 
17 |         steps:
18 |             -   name: Checkout code
19 |                 uses: actions/checkout@v2
20 | 
21 |             -   name: Setup PHP
22 |                 uses: shivammathur/setup-php@v2
23 |                 with:
24 |                     php-version: ${{ matrix.php }}
25 |                     extensions: dom, curl, libxml, mbstring, zip, pcntl, pdo, sqlite, pdo_sqlite, bcmath, soap, intl, gd, exif, iconv, imagick
26 |                     coverage: none
27 | 
28 |             -   name: Install dependencies
29 |                 run: composer update --no-interaction --prefer-source
30 | 
31 |             -   name: Execute tests
32 |                 run: vendor/bin/phpunit
33 | 


--------------------------------------------------------------------------------
/.github/workflows/update-changelog.yml:
--------------------------------------------------------------------------------
 1 | name: "Update Changelog"
 2 | 
 3 | on:
 4 |   release:
 5 |     types: [released]
 6 | 
 7 | jobs:
 8 |   update:
 9 |     runs-on: ubuntu-latest
10 | 
11 |     steps:
12 |       - name: Checkout code
13 |         uses: actions/checkout@v2
14 |         with:
15 |           ref: main
16 | 
17 |       - name: Update Changelog
18 |         uses: stefanzweifel/changelog-updater-action@v1
19 |         with:
20 |           latest-version: ${{ github.event.release.name }}
21 |           release-notes: ${{ github.event.release.body }}
22 | 
23 |       - name: Commit updated CHANGELOG
24 |         uses: stefanzweifel/git-auto-commit-action@v4
25 |         with:
26 |           branch: main
27 |           commit_message: Update CHANGELOG
28 |           file_pattern: CHANGELOG.md
29 | 


--------------------------------------------------------------------------------
/.phpunit.cache/test-results:
--------------------------------------------------------------------------------
1 | {"version":1,"defects":[],"times":{"Spatie\\MixedContentScanner\\Test\\InvalidUrlTest::it_will_throw_an_exception_when_scanning_an_empty_url":0.003,"Spatie\\MixedContentScanner\\Test\\InvalidUrlTest::it_will_throw_an_exception_when_scanning_an_url_with_an_invalid_protocol":0,"Spatie\\MixedContentScanner\\Test\\MixedContentScannerTest::it_can_find_mixed_content":0.052,"Spatie\\MixedContentScanner\\Test\\MixedContentScannerTest::it_will_only_mark_stylesheet_rel_as_mixed_content":0.006,"Spatie\\MixedContentScanner\\Test\\MixedContentScannerTest::it_will_throw_an_exception_when_given_an_url_with_an_invalid_protocol":0,"Spatie\\MixedContentScanner\\Test\\MixedContentScannerTest::it_can_limit_the_amout_of_crawled_urls":0.009,"Spatie\\MixedContentScanner\\Test\\MixedContentScannerTest::it_can_scan_pages_not_ending_in_slash":0.005,"Spatie\\MixedContentScanner\\Test\\MixedContentTest::it_can_convert_itself_to_an_array":0}}


--------------------------------------------------------------------------------
/CHANGELOG.md:
--------------------------------------------------------------------------------
  1 | # Changelog
  2 | 
  3 | All notable changes to `mixed-content-scanner` will be documented in this file
  4 | 
  5 | ## 5.0.0 - 2023-06-04
  6 | 
  7 | - use crawler v8
  8 | 
  9 | ## 4.0.4 - 2023-03-06
 10 | 
 11 | ### What's Changed
 12 | 
 13 | - Fix tests on PHP 8.1 by @SamuelNitsche in https://github.com/spatie/mixed-content-scanner/pull/47
 14 | - Fix of issue #48 by @codeinnovers in https://github.com/spatie/mixed-content-scanner/pull/49
 15 | 
 16 | ### New Contributors
 17 | 
 18 | - @codeinnovers made their first contribution in https://github.com/spatie/mixed-content-scanner/pull/49
 19 | 
 20 | **Full Changelog**: https://github.com/spatie/mixed-content-scanner/compare/4.0.3...4.0.4
 21 | 
 22 | ## 4.0.3
 23 | 
 24 | - allow crawler v7
 25 | 
 26 | ## 4.0.2
 27 | 
 28 | - allow crawler v6
 29 | 
 30 | ## 4.0.1
 31 | 
 32 | - allow PHP 8
 33 | 
 34 | ## 3.3.0
 35 | 
 36 | - revert changes in 3.2.0
 37 | 
 38 | ## 3.2.0
 39 | 
 40 | - add scan css
 41 | 
 42 | ## 3.1.0 - 2018-03-22
 43 | 
 44 | - Respect robots.
 45 | 
 46 | ## 3.0.2 - 2018-03-02
 47 | 
 48 | - Update `spatie/crawler` to support correct `Collection` packages.
 49 | - Remove unneeded `cighten/collect` dependency.
 50 | 
 51 | ## 3.0.1 - 2018-03-01
 52 | 
 53 | - improve constraints
 54 | 
 55 | ## 3.0.0 - 2018-03-01
 56 | 
 57 | - upgrade `spatie/crawler` to 4.0
 58 | 
 59 | ## 2.1.1 - 2018-01-23
 60 | 
 61 | - add `configureCrawler`
 62 | 
 63 | ## 2.1.0 - 2018-01-23
 64 | 
 65 | **broken release, do not use**
 66 | 
 67 | - add `configureCrawler`
 68 | 
 69 | ## 2.0.1 - 2017-01-10
 70 | 
 71 | - ignore invalid links
 72 | 
 73 | ## 2.0.0 - 2017-12-22
 74 | 
 75 | - upgrade `spatie/crawler` to 3.0
 76 | 
 77 | ## 1.2.1 - 2017-10-09
 78 | 
 79 | - only consider links with rel stylesheet as canidates for mixed content
 80 | 
 81 | ## 1.2.0 - 2017-09-27
 82 | 
 83 | - add `setMaximumCrawlCount`
 84 | 
 85 | ## 1.1.1 - 2017-08-23
 86 | 
 87 | - do not mark shortlinks as mixed content
 88 | 
 89 | ## 1.1.0 - 2017-08-11
 90 | 
 91 | - add `toArray` to `MixedContent`
 92 | 
 93 | ## 1.0.1 - 2017-08-03
 94 | 
 95 | - lower reqs
 96 | 
 97 | ## 1.0.0 - 2017-08-03
 98 | 
 99 | - initial release
100 | 


--------------------------------------------------------------------------------
/LICENSE.md:
--------------------------------------------------------------------------------
 1 | The MIT License (MIT)
 2 | 
 3 | Copyright (c) Spatie bvba <info@spatie.be>
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in
13 | all copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
21 | THE SOFTWARE.
22 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
  1 | # Scan your site for mixed content
  2 | 
  3 | [![Latest Version on Packagist](https://img.shields.io/packagist/v/spatie/mixed-content-scanner.svg?style=flat-square)](https://packagist.org/packages/spatie/mixed-content-scanner)
  4 | ![Tests](https://github.com/spatie/mixed-content-scanner/workflows/Tests/badge.svg)
  5 | [![Total Downloads](https://img.shields.io/packagist/dt/spatie/mixed-content-scanner.svg?style=flat-square)](https://packagist.org/packages/spatie/mixed-content-scanner)
  6 | 
  7 | This package contains a class that can scan your site for [mixed content](https://developer.mozilla.org/en-US/docs/Web/Security/Mixed_content).
  8 | 
  9 | Here's an example of how you can use it:
 10 | 
 11 | ```php
 12 | use Spatie\MixedContentScanner\MixedContentScanner;
 13 | 
 14 | $logger = new MixedContentLogger();
 15 | 
 16 | $scanner = new MixedContentScanner($logger);
 17 | 
 18 | $scanner->scan('https://example.com');
 19 | ```
 20 | 
 21 | `MixedContentLogger` is a class containing methods that get called when mixed content is (not) found. 
 22 | 
 23 | If you don't need a custom implementation but simply want to look for mixed content using a command line tool, take a look at [our mixed-content-scanner-cli package](https://github.com/spatie/mixed-content-scanner-cli).
 24 | 
 25 | ## Support us
 26 | 
 27 | Learn how to create a package like this one, by watching our premium video course:
 28 | 
 29 | [![Laravel Package training](https://spatie.be/github/package-training.jpg)](https://laravelpackage.training)
 30 | 
 31 | We invest a lot of resources into creating [best in class open source packages](https://spatie.be/open-source). You can support us by [buying one of our paid products](https://spatie.be/open-source/support-us).
 32 | 
 33 | We highly appreciate you sending us a postcard from your hometown, mentioning which of our package(s) you are using. You'll find our address on [our contact page](https://spatie.be/about-us). We publish all received postcards on [our virtual postcard wall](https://spatie.be/open-source/postcards).
 34 | 
 35 | ## Installation
 36 | 
 37 | You can install the package via composer:
 38 | 
 39 | ```bash
 40 | composer require spatie/mixed-content-scanner
 41 | ```
 42 | 
 43 | ## How it works under the hood
 44 | 
 45 | When scanning a site, the scanner will crawl everypage. On the retrieve html, these elements and attributes will be checked:
 46 | 
 47 | - `audio`: `src`
 48 | - `embed`: `src`
 49 | - `form`: `action`
 50 | - `link`: `href`
 51 | - `iframe`: `src`
 52 | - `img`: `src`, `srcset`
 53 | - `object`: `data`
 54 | - `param`: `value`
 55 | - `script`: `src`
 56 | - `source`: `src`, `srcset`
 57 | - `video`: `src`
 58 | 
 59 | If any of those attributes start with `http://` the element will be regarded as mixed content.
 60 | 
 61 | The package does not scan linked `.css` or `.js` files, nor does it take inline `<script>` or `<style>` and [shortlinks](http://microformats.org/wiki/rel-shortlink) into consideration.
 62 | 
 63 | ## Usage
 64 | 
 65 | ```php
 66 | use Spatie\MixedContentScanner\MixedContentScanner
 67 | 
 68 | $logger = new MixedContentLogger();
 69 | 
 70 | $scanner = new MixedContentScanner($logger);
 71 | 
 72 | $scanner->scan('https://example.com');
 73 | ```
 74 | 
 75 | That `MixedContentScanner` accepts an instance of a class that extends `\Spatie\MixedContentScannerMixedContentObserver`. You should create such a class yourself. Let's take a look at an example implementation.
 76 | 
 77 | ```php
 78 | use Psr\Http\Message\UriInterface;
 79 | use Spatie\MixedContentScanner\MixedContent;
 80 | use Spatie\MixedContentScanner\MixedContentObserver;
 81 | 
 82 | class MyMixedContentLogger extends MixedContentObserver
 83 | {
 84 |     /**
 85 |      * Will be called when mixed content was found.
 86 |      * 
 87 |      * @param \Spatie\MixedContentScanner\MixedContent $mixedContent
 88 |      */
 89 |     public function mixedContentFound(MixedContent $mixedContent): void
 90 |     {
 91 |     }
 92 | 
 93 |     /**
 94 |      * Will be called when no mixed content was found on the given url.
 95 |      * 
 96 |      * @param \Psr\Http\Message\UriInterface $crawledUrl
 97 |      */
 98 |     public function noMixedContentFound(UriInterface $crawledUrl): void
 99 |     {
100 |     }
101 | 
102 |     /**
103 |      * Will be called when the scanner has finished crawling.
104 |      */
105 |     public function finishedCrawling(): void
106 |     {
107 |     }
108 | }
109 | ```
110 | 
111 | Of course, you should supply a function body to these methods yourself. If you don't need a function just leave it off.
112 | 
113 | The `$mixedContent` variable the `mixedContentFound` class accept is an instance of `\Spatie\MixedContentScanner\MixedContent` which has these three properties:
114 | 
115 | - `$elementName`: the name of the element that is regarded as mixed content
116 | - `$mixedContentUrl`: the url of the element that is regarded as mixed content. For an image this can be the value of `src` or `srcset` for a `form` this can be the value of `action`, ...
117 | - `$foundOnUrl`: the url where the mixed content was found
118 | 
119 | ### Customizing the requests
120 | 
121 | The scanner is powered by [our homegrown Crawler](https://github.com/spatie/crawler) which on it's turn leverages [Guzzle](http://docs.guzzlephp.org/en/stable/) to perform webrequests.
122 | You can pass an array of options to the second argument of `MixedContentScanner`. These options will be passed to the Guzzle Client. 
123 | 
124 | Here's an example where ssl verification is being turned off.
125 | 
126 | ```php
127 | $scanner = new MixedContentScanner($logger);
128 | $scanner->scan('https://laravel.com', ['verify' => 'false']);
129 | ```
130 | 
131 | ### Filtering the crawled urls
132 | 
133 | By default, the mixed content scanner will crawl all urls of the hostname given. If you want to filter the urls to be crawled, you can pass the scanner a class that extends `Spatie\Crawler\CrawlProfile`.
134 | 
135 | Here's the content of that class:
136 | 
137 | ```php
138 | namespace Spatie\Crawler;
139 | 
140 | use Psr\Http\Message\UriInterface;
141 | 
142 | abstract class CrawlProfile
143 | {
144 |     /**
145 |      * Determine if the given url should be crawled.
146 |      *
147 |      * @param \Psr\Http\Message\UriInterface $url
148 |      *
149 |      * @return bool
150 |      */
151 |     abstract public function shouldCrawl(UriInterface $url): bool;
152 | }
153 | ```
154 | 
155 | And here's how you can let the scanner use your profile:
156 | 
157 | ```php
158 | use Spatie\MixedContentScanner\MixedContentScanner;
159 | 
160 | $logger = new MixedContentLogger();
161 | 
162 | $scanner = new MixedContentScanner($logger);
163 | 
164 | $scanner->setCrawlProfile(new MyCrawlProfile);
165 | ```
166 | 
167 | ## Customizing the crawler
168 | 
169 | The scanner is powered by [our homegrown Crawler](https://github.com/spatie/crawler). You can call any methods on the crawler before the crawling process starts by calling `configureCrawler` on a `MixedContentScanner`.
170 | 
171 | ```php
172 | use Spatie\Crawler\Crawler;
173 | use Spatie\MixedContentScanner\MixedContentScanner;
174 | 
175 | $scanner = (new MixedContentScanner($logger))
176 |     ->configureCrawler(function(Crawler $crawler) {
177 |         $crawler->setConcurrency(1) // now all urls will be crawled one by one 
178 |     });
179 | ```
180 | 
181 | ## Changelog
182 | 
183 | Please see [CHANGELOG](CHANGELOG.md) for more information what has changed recently.
184 | 
185 | ## Testing
186 | 
187 | ``` bash
188 | composer test
189 | ```
190 | 
191 | ## Contributing
192 | 
193 | Please see [CONTRIBUTING](https://github.com/spatie/.github/blob/main/CONTRIBUTING.md) for details.
194 | 
195 | ## Security
196 | 
197 | If you've found a bug regarding security please mail [security@spatie.be](mailto:security@spatie.be) instead of using the issue tracker.
198 | 
199 | ## Postcardware
200 | 
201 | You're free to use this package, but if it makes it to your production environment we highly appreciate you sending us a postcard from your hometown, mentioning which of our package(s) you are using.
202 | 
203 | Our address is: Spatie, Kruikstraat 22, 2018 Antwerp, Belgium.
204 | 
205 | We publish all received postcards [on our company website](https://spatie.be/en/opensource/postcards).
206 | 
207 | ## Credits
208 | 
209 | - [Freek Van der Herten](https://github.com/freekmurze)
210 | - [All Contributors](../../contributors)
211 | 
212 | The scanner is inspired by [mixed-content-scan](https://github.com/bramus/mixed-content-scan) by [Bram Van Damme](https://github.com/bramus). Parts of his readme and code were used.
213 | 
214 | ## License
215 | 
216 | The MIT License (MIT). Please see [License File](LICENSE.md) for more information.
217 | 


--------------------------------------------------------------------------------
/UPGRADING.md:
--------------------------------------------------------------------------------
 1 | # Upgrading
 2 | 
 3 | Because there are many breaking changes an upgrade is not that easy. 
 4 | There are many edge cases this guide does not cover. 
 5 | We accept PRs to improve this guide.
 6 | 
 7 | ## From 4.0 to 5.0
 8 | 
 9 | - `spatie/crawler` is updated to `^8.0`. In the `MixedContentObserver` provided by this package, a new parameter `linkText` was added to several methods. If you extend that observer, you should add that parameter to your methods as well.
10 | 
11 | ## From 2.0 to 3.0
12 | 
13 | - `spatie/crawler` is updated to `^4.0`. This version made changes to the way custom `Profiles` and `Observers` are made. Please see the [UPGRADING](https://github.com/spatie/crawler/blob/master/UPGRADING.md) guide of `spatie/crawler` to know how to update any custom crawl profiles or observers - if you have any.
14 | 
15 | 
16 | ## From 1.0 to 2.0
17 | 
18 | - We're now using `spatie/crawler` v3. Please check its [UPGRADING.md](https://github.com/spatie/crawler/blob/master/UPGRADING.md#from-v2-to-v3)
19 | for the information to update loggers.
20 | 


--------------------------------------------------------------------------------
/composer.json:
--------------------------------------------------------------------------------
 1 | {
 2 |     "name": "spatie/mixed-content-scanner",
 3 |     "description": "Scan your site for mixed content",
 4 |     "keywords": [
 5 |         "spatie",
 6 |         "mixed-content-scanner"
 7 |     ],
 8 |     "homepage": "https://github.com/spatie/mixed-content-scanner",
 9 |     "license": "MIT",
10 |     "authors": [
11 |         {
12 |             "name": "Freek Van der Herten",
13 |             "email": "freek@spatie.be",
14 |             "homepage": "https://spatie.be",
15 |             "role": "Developer"
16 |         }
17 |     ],
18 |     "require": {
19 |         "php": "^8.1",
20 |         "spatie/crawler": "^8.0"
21 |     },
22 |     "require-dev": {
23 |         "phpunit/phpunit": "^10.0",
24 |         "symfony/var-dumper": "^6.0"
25 |     },
26 |     "autoload": {
27 |         "psr-4": {
28 |             "Spatie\\MixedContentScanner\\": "src"
29 |         }
30 |     },
31 |     "autoload-dev": {
32 |         "psr-4": {
33 |             "Spatie\\MixedContentScanner\\Test\\": "tests"
34 |         }
35 |     },
36 |     "scripts": {
37 |         "test": "vendor/bin/phpunit"
38 |     },
39 |     "config": {
40 |         "sort-packages": true
41 |     }
42 | }
43 | 


--------------------------------------------------------------------------------
/src/Exceptions/InvalidUrl.php:
--------------------------------------------------------------------------------
 1 | <?php
 2 | 
 3 | namespace Spatie\MixedContentScanner\Exceptions;
 4 | 
 5 | use Exception;
 6 | 
 7 | class InvalidUrl extends Exception
 8 | {
 9 |     public static function invalidScheme(string $url)
10 |     {
11 |         return new static("`{$url}` did not start with a valid scheme. It should start with either `http://` or `https`");
12 |     }
13 | 
14 |     public static function urlIsEmpty()
15 |     {
16 |         return new static('You must pass a valid url. Empty value given.');
17 |     }
18 | }
19 | 


--------------------------------------------------------------------------------
/src/MixedContent.php:
--------------------------------------------------------------------------------
 1 | <?php
 2 | 
 3 | namespace Spatie\MixedContentScanner;
 4 | 
 5 | use Psr\Http\Message\UriInterface;
 6 | 
 7 | class MixedContent
 8 | {
 9 |     public string $elementName = '';
10 | 
11 |     public ?UriInterface $mixedContentUrl = null;
12 | 
13 |     public ?UriInterface $foundOnUrl = null;
14 | 
15 |     public function __construct(string $elementName, UriInterface $mixedContentUrl, UriInterface $foundOnUrl)
16 |     {
17 |         $this->elementName = $elementName;
18 | 
19 |         if ($mixedContentUrl->getPath() === '') {
20 |             $mixedContentUrl = $mixedContentUrl->withPath('/');
21 |         }
22 | 
23 |         $this->mixedContentUrl = $mixedContentUrl;
24 | 
25 |         if ($foundOnUrl->getPath() === '') {
26 |             $foundOnUrl = $foundOnUrl->withPath('/');
27 |         }
28 | 
29 |         $this->foundOnUrl = $foundOnUrl;
30 |     }
31 | 
32 |     public function toArray(): array
33 |     {
34 |         return [
35 |             'elementName' => $this->elementName,
36 |             'mixedContentUrl' => (string) $this->mixedContentUrl,
37 |             'foundOnUrl' => (string) $this->foundOnUrl,
38 |         ];
39 |     }
40 | }
41 | 


--------------------------------------------------------------------------------
/src/MixedContentExtractor.php:
--------------------------------------------------------------------------------
 1 | <?php
 2 | 
 3 | namespace Spatie\MixedContentScanner;
 4 | 
 5 | use Exception;
 6 | use GuzzleHttp\Psr7\Uri;
 7 | use Illuminate\Support\Collection;
 8 | use Symfony\Component\DomCrawler\Crawler as DomCrawler;
 9 | 
10 | class MixedContentExtractor
11 | {
12 |     public static function extract(string $html, string $currentUri): array
13 |     {
14 |         return static::getSearchNodes()
15 |             ->mapSpread(function ($tagName, $attribute) use ($html, $currentUri) {
16 |                 return (new DomCrawler($html, $currentUri))
17 |                     ->filterXPath("//{$tagName}[@{$attribute}]")
18 |                     ->reduce(function (DomCrawler $node) {
19 |                         return ! self::isShortLink($node);
20 |                     })
21 |                     ->each(function (DomCrawler $node) use ($tagName, $attribute) {
22 |                         try {
23 |                             $url = new Uri($node->attr($attribute));
24 | 
25 |                             if ($tagName === 'link' && $attribute === 'href') {
26 |                                 if ($node->attr('rel') !== 'stylesheet') {
27 |                                     return null;
28 |                                 }
29 |                             }
30 | 
31 |                             return $url->getScheme() === 'http' ? [$tagName, $url] : null;
32 |                         } catch (Exception $e) {
33 |                             // ignore invalid links
34 |                         }
35 |                     });
36 |             })
37 |             ->flatten(1)
38 |             ->filter()
39 |             ->mapSpread(function ($tagName, $mixedContentUrl) use ($currentUri) {
40 |                 return new MixedContent($tagName, $mixedContentUrl, new Uri($currentUri));
41 |             })
42 |             ->toArray();
43 |     }
44 | 
45 |     protected static function getSearchNodes(): Collection
46 |     {
47 |         return collect([
48 |             ['audio', 'src'],
49 |             ['embed', 'src'],
50 |             ['form', 'action'],
51 |             ['link', 'href'],
52 |             ['iframe', 'src'],
53 |             ['img', 'src'],
54 |             ['img', 'srcset'],
55 |             ['object', 'data'],
56 |             ['param', 'value'],
57 |             ['script', 'src'],
58 |             ['source', 'src'],
59 |             ['source', 'srcset'],
60 |             ['video', 'src'],
61 |         ]);
62 |     }
63 | 
64 |     protected static function isShortLink(DomCrawler $node): bool
65 |     {
66 |         $relAttribute = $node->getNode(0)->attributes->getNamedItem('rel');
67 | 
68 |         if (is_null($relAttribute)) {
69 |             return false;
70 |         }
71 | 
72 |         return strtolower($relAttribute->nodeValue) === 'shortlink';
73 |     }
74 | }
75 | 


--------------------------------------------------------------------------------
/src/MixedContentObserver.php:
--------------------------------------------------------------------------------
 1 | <?php
 2 | 
 3 | namespace Spatie\MixedContentScanner;
 4 | 
 5 | use GuzzleHttp\Exception\RequestException;
 6 | use Psr\Http\Message\ResponseInterface;
 7 | use Psr\Http\Message\UriInterface;
 8 | use Spatie\Crawler\CrawlObservers\CrawlObserver;
 9 | 
10 | class MixedContentObserver extends CrawlObserver
11 | {
12 |     public function crawled(
13 |         UriInterface $url,
14 |         ResponseInterface $response, ?
15 |         UriInterface $foundOnUrl = null,
16 |         ?string $linkText = null,
17 |     ): void
18 |     {
19 |         $mixedContent = MixedContentExtractor::extract((string) $response->getBody(), $url);
20 | 
21 |         if (! count($mixedContent)) {
22 |             $this->noMixedContentFound($url);
23 | 
24 |             return;
25 |         }
26 | 
27 |         foreach ($mixedContent as $mixedContentItem) {
28 |             $this->mixedContentFound($mixedContentItem);
29 |         }
30 |     }
31 | 
32 |     public function crawlFailed(
33 |         UriInterface $url,
34 |         RequestException $requestException,
35 |         ?UriInterface $foundOnUrl = null,
36 |         ?string $linkText = null,
37 |     ): void {
38 |     }
39 | 
40 |     /**
41 |      * Will be called when mixed content was found.
42 |      *
43 |      * @param \Spatie\MixedContentScanner\MixedContent $mixedContent
44 |      */
45 |     public function mixedContentFound(MixedContent $mixedContent)
46 |     {
47 |     }
48 | 
49 |     /**
50 |      * Will be called when no mixed content was found on the given url.
51 |      *
52 |      * @param \Psr\Http\Message\UriInterface
53 |      */
54 |     public function noMixedContentFound(UriInterface $crawledUrl): void
55 |     {
56 |     }
57 | }
58 | 


--------------------------------------------------------------------------------
/src/MixedContentScanner.php:
--------------------------------------------------------------------------------
 1 | <?php
 2 | 
 3 | namespace Spatie\MixedContentScanner;
 4 | 
 5 | use Closure;
 6 | use GuzzleHttp\Psr7\Uri;
 7 | use Spatie\Crawler\Crawler;
 8 | use Spatie\Crawler\CrawlProfiles\CrawlInternalUrls;
 9 | use Spatie\Crawler\CrawlProfiles\CrawlProfile;
10 | use Spatie\MixedContentScanner\Exceptions\InvalidUrl;
11 | 
12 | class MixedContentScanner
13 | {
14 |     public MixedContentObserver $mixedContentObserver;
15 | 
16 |     public ?CrawlProfile $crawlProfile = null;
17 | 
18 |     protected ?int $maximumCrawlCount = null;
19 | 
20 |     protected Closure $configureCrawler;
21 | 
22 |     public function __construct(MixedContentObserver $mixedContentObserver)
23 |     {
24 |         $this->mixedContentObserver = $mixedContentObserver;
25 | 
26 |         $this->configureCrawler = function (Crawler $crawler) {
27 |         };
28 |     }
29 | 
30 |     public function scan(string $url, array $clientOptions = []): void
31 |     {
32 |         $this->guardAgainstInvalidUrl($url);
33 | 
34 |         $url = new Uri($url);
35 | 
36 |         $crawler = Crawler::create($clientOptions);
37 | 
38 |         ($this->configureCrawler)($crawler);
39 | 
40 |         if ($this->maximumCrawlCount) {
41 |             $crawler->setTotalCrawlLimit($this->maximumCrawlCount);
42 |         }
43 | 
44 |         $crawler->setCrawlProfile($this->crawlProfile ?? new CrawlInternalUrls($url))
45 |             ->setCrawlObserver($this->mixedContentObserver)
46 |             ->startCrawling($url);
47 |     }
48 | 
49 |     public function configureCrawler(callable $callable): self
50 |     {
51 |         $this->configureCrawler = $callable;
52 | 
53 |         return $this;
54 |     }
55 | 
56 |     public function setCrawlProfile(CrawlProfile $crawlProfile): self
57 |     {
58 |         $this->crawlProfile = $crawlProfile;
59 | 
60 |         return $this;
61 |     }
62 | 
63 |     protected function guardAgainstInvalidUrl(string $url): void
64 |     {
65 |         if ($url === '') {
66 |             throw InvalidUrl::urlIsEmpty();
67 |         }
68 | 
69 |         if (! $this->startsWith($url, ['http://', 'https://'])) {
70 |             throw InvalidUrl::invalidScheme($url);
71 |         }
72 |     }
73 | 
74 |     protected function startsWith(string $haystack, array $needles): bool
75 |     {
76 |         foreach ((array) $needles as $needle) {
77 |             if ($needle != '' && substr($haystack, 0, strlen($needle)) === (string) $needle) {
78 |                 return true;
79 |             }
80 |         }
81 | 
82 |         return false;
83 |     }
84 | }
85 | 


--------------------------------------------------------------------------------