diff --git a/.env.dist.testing b/.env.dist.testing new file mode 100644 index 0000000..4d5f08e --- /dev/null +++ b/.env.dist.testing @@ -0,0 +1,8 @@ +CONVERTKIT_API_FORM_ID="2765139" +CONVERTKIT_API_LEGACY_FORM_URL="https://app.convertkit.com/landing_pages/470099" +CONVERTKIT_API_LANDING_PAGE_URL="https://cheerful-architect-3237.ck.page/cc5eb21744" +CONVERTKIT_API_LEGACY_LANDING_PAGE_URL="https://app.convertkit.com/landing_pages/470103" +CONVERTKIT_API_SEQUENCE_ID="1030824" +CONVERTKIT_API_TAG_ID="2744672" +CONVERTKIT_API_SUBSCRIBER_EMAIL="optin@n7studios.com" +CONVERTKIT_API_SUBSCRIBER_ID="1579118532" diff --git a/.env.example b/.env.example new file mode 100644 index 0000000..2cbb1ac --- /dev/null +++ b/.env.example @@ -0,0 +1,12 @@ +CONVERTKIT_API_KEY_NO_DATA= +CONVERTKIT_API_SECRET_NO_DATA= +CONVERTKIT_API_KEY= +CONVERTKIT_API_SECRET= +CONVERTKIT_API_FORM_ID="2765139" +CONVERTKIT_API_LEGACY_FORM_URL="https://app.convertkit.com/landing_pages/470099" +CONVERTKIT_API_LANDING_PAGE_URL="https://cheerful-architect-3237.ck.page/cc5eb21744" +CONVERTKIT_API_LEGACY_LANDING_PAGE_URL="https://app.convertkit.com/landing_pages/470103" +CONVERTKIT_API_SEQUENCE_ID="1030824" +CONVERTKIT_API_TAG_ID="2744672" +CONVERTKIT_API_SUBSCRIBER_EMAIL="optin@n7studios.com" +CONVERTKIT_API_SUBSCRIBER_ID="1579118532" diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md new file mode 100644 index 0000000..cf2b94d --- /dev/null +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -0,0 +1,20 @@ +## Summary + +A brief description of what this PR adds, changes or fixes. + +If it is adding functionality, a use case of why this is needed helps determine its suitability. + +## Testing + +Not sure how to perform testing, or perhaps didn't include a test in this PR? Walk through the following in order for a beginner-friendly guide: +- [Setup](SETUP.md) - setting up your local environment for development and testing +- [Development](DEVELOPMENT.md) - best practices for development +- [Testing](TESTING.md) - how to write and run tests + +## Checklist + +* [ ] I have [written a test](TESTING.md#writing-a-test) and included it in this PR +* [ ] I have [run all tests](TESTING.md#run-tests) and they pass +* [ ] The code passes when [running the PHP CodeSniffer](TESTING.md#run-php-codesniffer) +* [ ] The code passes when [running PHPStan](TESTING.md#run-phpstan) +* [ ] I have assigned a reviewer or two to review this PR (if you're not sure who to assign, we can do this step for you) \ No newline at end of file diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml new file mode 100644 index 0000000..19f579f --- /dev/null +++ b/.github/workflows/tests.yml @@ -0,0 +1,77 @@ +name: Run Tests + +# When to run tests. +on: + pull_request: + types: + - opened + - synchronize + push: + branches: + - main + +jobs: + tests: + # Name. + name: PHP ${{ matrix.php-versions }} + + # Virtual Environment to use. + # @see: https://github.com/actions/virtual-environments + runs-on: ubuntu-latest + + # Defines PHP Versions matrix to run tests on + strategy: + matrix: + php-versions: [ '7.4', '8.0', '8.1', '8.2' ] + + # Steps to install, configure and run tests + steps: + # Checkout (copy) this repository's Plugin to this VM. + - name: Checkout Code + uses: actions/checkout@v3 + + # Install PHP version + - name: Install PHP + uses: shivammathur/setup-php@v2 + with: + php-version: ${{ matrix.php-versions }} + coverage: none + + # Write any secrets, such as API keys, to the .env.dist.testing file now. + # Make sure your committed .env.dist.testing file ends with a newline. + # The formatting of the contents to include a blank newline is deliberate. + - name: Define GitHub Secrets in .env.dist.testing + uses: DamianReeves/write-file-action@v1.1 + with: + path: .env.dist.testing + contents: | + + CONVERTKIT_API_KEY=${{ secrets.CONVERTKIT_API_KEY }} + CONVERTKIT_API_SECRET=${{ secrets.CONVERTKIT_API_SECRET }} + CONVERTKIT_API_KEY_NO_DATA=${{ secrets.CONVERTKIT_API_KEY_NO_DATA }} + CONVERTKIT_API_SECRET_NO_DATA=${{ secrets.CONVERTKIT_API_SECRET_NO_DATA }} + write-mode: append + + # Rename .env.dist.testing to .env, so PHPUnit reads it for tests. + - name: Rename .env.dist.testing to .env + run: mv .env.dist.testing .env + + # Installs PHPUnit, PHP CodeSniffer and anything else needed to run tests. + - name: Run Composer + run: composer update + + # Generate autoloader + - name: Build PHP Autoloader + run: composer dump-autoload + + # Run Coding Standards. + - name: Run Coding Standards + run: php vendor/bin/phpcs --standard=phpcs.xml + + # Run Coding Standards on Tests. + - name: Run Coding Standards on Tests + run: php vendor/bin/phpcs --standard=phpcs.tests.xml + + # Run PHPUnit Tests. + - name: Run PHPUnit Tests + run: vendor/bin/phpunit --verbose --stop-on-failure \ No newline at end of file diff --git a/.gitignore b/.gitignore index d755384..36c9917 100644 --- a/.gitignore +++ b/.gitignore @@ -1,6 +1,7 @@ .DS_Store .env .env.testing +.phpunit.result.cache composer.lock phpstan.neon src/logs diff --git a/TESTING.md b/TESTING.md new file mode 100644 index 0000000..2a56209 --- /dev/null +++ b/TESTING.md @@ -0,0 +1,89 @@ +# Testing Guide + +This document describes how to: +- create and run tests for your development work, +- ensure code meets coding standards, for best practices and security, + +If you're new to creating and running tests, this guide will walk you through how to do this. + +For those more experienced with creating and running tests, our tests are written in PHP using [PHPUnit](https://phpunit.de/). + +## Prerequisites + +If you haven't yet set up your local development environment, refer to the [Setup Guide](SETUP.md). + +If you haven't yet created a branch and made any code changes, refer to the [Development Guide](DEVELOPMENT.md) + +## Write (or modify) a test + +If your work creates new functionality, write a test. + +If your work fixes existing functionality, check if a test exists. Either update that test, or create a new test if one doesn't exist. + +Tests are written in PHP using [PHPUnit](https://phpunit.de/), and the existing `tests/ConvertKitAPITest.php` is a good place to start as a guide. + +## Run PHPUnit + +Once you have written your code and tests, run the tests to make sure there are no errors. + +To run the tests, enter the following commands in a separate Terminal window: + +```bash +vendor/bin/phpunit --verbose --stop-on-failure +``` + +If a test fails, you can inspect the output. + +Any errors should be corrected by making applicable code or test changes. + +## Run PHP CodeSniffer + +[PHP_CodeSniffer](https://github.com/squizlabs/PHP_CodeSniffer) checks that all code meets the [PSR-12 Coding Standards](https://www.php-fig.org/psr/psr-12/). + +To run CodeSniffer on tests, enter the following command: + +```bash +vendor/bin/phpcs +``` + +Any errors should be corrected by either: +- making applicable code changes +- (Experimental) running `vendor/bin/phpcbf` to automatically fix coding standards + +Need to change the coding standard rules applied? Either: +- ignore a rule in the affected code, by adding `phpcs:ignore {rule}`, where {rule} is the given rule that failed in the above output. +- edit the [phpcs.tests.xml](phpcs.xml) file. + +**Rules can be ignored with caution**, but it's essential that rules relating to coding style and inline code commenting / docblocks remain. + +## Run PHP CodeSniffer for Tests + +[PHP_CodeSniffer](https://github.com/squizlabs/PHP_CodeSniffer) checks that all test code meets the [PSR-12 Coding Standards](https://www.php-fig.org/psr/psr-12/). + +To run CodeSniffer on tests, enter the following command: + +```bash +vendor/bin/phpcs --standard=phpcs.tests.xml +``` + +`--standard=phpcs.tests.xml` tells PHP CodeSniffer to use the use the [phpcs.tests.xml](phpcs.tests.xml) configuration file + +Any errors should be corrected by either: +- making applicable code changes +- (Experimental) running `vendor/bin/phpcbf --standard=phpcs.tests.xml` to automatically fix coding standards + +Need to change the coding standard rules applied? Either: +- ignore a rule in the affected code, by adding `phpcs:ignore {rule}`, where {rule} is the given rule that failed in the above output. +- edit the [phpcs.tests.xml](phpcs.tests.xml) file. + +**Rules can be ignored with caution**, but it's essential that rules relating to coding style and inline code commenting / docblocks remain. + +## Next Steps + +Once your tests are written and successfully run locally, submit your branch via a new [Pull Request](https://github.com/ConvertKit/ConvertKitSDK-PHP/compare). + +It's best to create a Pull Request in draft mode, as this will trigger all tests to run as a GitHub Action, allowing you to double check all tests pass. + +If the PR tests fail, you can make code changes as necessary, pushing to the same branch. This will trigger the tests to run again. + +If the PR tests pass, you can publish the PR, assigning some reviewers. \ No newline at end of file diff --git a/composer.json b/composer.json index a667c54..6dee533 100644 --- a/composer.json +++ b/composer.json @@ -20,6 +20,7 @@ "monolog/monolog": "^2.0" }, "require-dev": { + "vlucas/phpdotenv": "^5.5", "phpunit/phpunit": "^5.7 || ^9.0", "squizlabs/php_codesniffer": "^3.3", "phpstan/phpstan": "^1.2" @@ -27,10 +28,7 @@ "autoload": { "psr-4": { "ConvertKit_API\\": "src/" - }, - "classmap": [ - "src/lib/" - ] + } }, "minimum-stability": "dev", "prefer-stable": true diff --git a/phpcs.tests.xml b/phpcs.tests.xml new file mode 100644 index 0000000..15b27b9 --- /dev/null +++ b/phpcs.tests.xml @@ -0,0 +1,17 @@ + + + Coding Standards for Tests + + + tests + + + + + + + + + + + \ No newline at end of file diff --git a/phpcs.xml b/phpcs.xml new file mode 100644 index 0000000..4153cb7 --- /dev/null +++ b/phpcs.xml @@ -0,0 +1,58 @@ + + + Coding Standards + + + src + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/phpunit.xml b/phpunit.xml index ee505f0..0d14407 100644 --- a/phpunit.xml +++ b/phpunit.xml @@ -1,13 +1,5 @@ - + tests diff --git a/src/ConvertKit_API.php b/src/ConvertKit_API.php index c49a29e..48ce836 100644 --- a/src/ConvertKit_API.php +++ b/src/ConvertKit_API.php @@ -1,4 +1,11 @@ api_key = $api_key; + public function __construct(string $api_key, string $api_secret, bool $debug = false) + { + $this->api_key = $api_key; $this->api_secret = $api_secret; - $this->debug = $debug; - $this->client = new Client(); + $this->debug = $debug; + $this->client = new Client(); - if( $debug ) { + if ($debug) { $this->debug_logger = new Logger('ck-debug'); - $this->debug_logger->pushHandler(new StreamHandler(__DIR__.'/logs/debug.log', Logger::DEBUG)); + $stream_handler = new StreamHandler(__DIR__ . '/logs/debug.log', Logger::DEBUG); + $this->debug_logger->pushHandler( + $stream_handler // phpcs:ignore Squiz.Objects.ObjectInstantiation.NotAssigned + ); } } - private function create_log($message) { - if($this->debug) { + /** + * Add an entry to monologger. + * + * @param string $message Message. + * + * @return void + */ + private function create_log(string $message) + { + if ($this->debug) { $this->debug_logger->info($message); } } + /** * Gets the current account * @@ -106,17 +128,18 @@ private function create_log($message) { */ public function get_account() { - $request = $this->api_version . '/account'; + $request = 'account'; - $options = array( + $options = [ 'api_secret' => $this->api_secret, - ); + ]; - $this->create_log(sprintf("GET account: %s, %s", $request, json_encode($options))); + $this->create_log(sprintf('GET account: %s, %s', $request, json_encode($options))); - return $this->make_request( $request, 'GET', $options ); + return $this->get($request, $options); } + /** * Gets all sequences * @@ -124,83 +147,105 @@ public function get_account() */ public function get_sequences() { - $request = $this->api_version . '/sequences'; + $request = 'sequences'; - $options = array( + $options = [ 'api_key' => $this->api_key, - ); + ]; - $this->create_log(sprintf("GET sequences: %s, %s", $request, json_encode($options))); + $this->create_log(sprintf('GET sequences: %s, %s', $request, json_encode($options))); - return $this->make_request( $request, 'GET', $options ); + return $this->get($request, $options); } + /** * Gets subscribers to a sequence * - * @param $sequence_id - * @param string $sort_order + * @param integer $sequence_id Sequence ID. + * @param string $sort_order Sort Order (asc|desc). * * @return false|mixed */ - public function get_sequence_subscriptions($sequence_id, $sort_order = 'asc') + public function get_sequence_subscriptions(int $sequence_id, string $sort_order = 'asc') { - $request = $this->api_version . sprintf('/sequences/%s/subscriptions', $sequence_id); + $request = sprintf('sequences/%s/subscriptions', $sequence_id); - $options = array( + $options = [ 'api_secret' => $this->api_secret, - 'sort_order' => $sort_order + 'sort_order' => $sort_order, + ]; + + $this->create_log( + sprintf( + 'GET sequence subscriptions: %s, %s, %s', + $request, + json_encode($options), + $sequence_id + ) ); - $this->create_log(sprintf("GET sequence subscriptions: %s, %s, %s", $request, json_encode($options), $sequence_id)); - - return $this->make_request( $request, 'GET', $options ); + return $this->get($request, $options); } + /** * Adds a subscriber to a sequence by email address * - * @param $sequence_id - * @param $email + * @param integer $sequence_id Sequence ID. + * @param string $email Email Address. * * @return false|mixed */ - public function add_subscriber_to_sequence($sequence_id, $email) + public function add_subscriber_to_sequence(int $sequence_id, string $email) { - $request = $this->api_version . sprintf('/courses/%s/subscribe', $sequence_id); + $request = sprintf('courses/%s/subscribe', $sequence_id); - $options = array( + $options = [ 'api_key' => $this->api_key, - 'email' => $email + 'email' => $email, + ]; + + $this->create_log( + sprintf( + 'POST add subscriber to sequence: %s, %s, %s, %s', + $request, + json_encode($options), + $sequence_id, + $email + ) ); - $this->create_log(sprintf("POST add subscriber to sequence: %s, %s, %s, %s", $request, json_encode($options), $sequence_id, $email)); - - return $this->make_request( $request, 'POST', $options ); + return $this->post($request, $options); } + /** * Adds a tag to a subscriber * - * @param int $tag Tag ID - * @param array $options Array of user data + * @param integer $tag Tag ID. + * @param array $options Array of user data. + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. + * * @return false|object */ - public function add_tag( $tag, $options ) { - - if( !is_int($tag) || !is_array($options) ) { - throw new \InvalidArgumentException; + public function add_tag(int $tag, array $options) + { + if (!is_int($tag) || !is_array($options)) { + throw new \InvalidArgumentException(); } - $request = $this->api_version . sprintf( '/tags/%s/subscribe', $tag ); + $request = sprintf('tags/%s/subscribe', $tag); $options['api_key'] = $this->api_key; - $this->create_log(sprintf("POST add tag: %s, %s, %s", $request, json_encode($options), $tag)); + $this->create_log(sprintf('POST add tag: %s, %s, %s', $request, json_encode($options), $tag)); - return $this->make_request( $request, 'POST', $options ); + return $this->post($request, $options); } + /** * Gets a resource index * Possible resources: forms, landing_pages, subscription_forms, tags @@ -208,426 +253,575 @@ public function add_tag( $tag, $options ) { * GET /{$resource}/ * * @param string $resource Resource type. + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. + * * @return object API response */ - public function get_resources( $resource ) { - - if( !is_string($resource) ) { - throw new \InvalidArgumentException; + public function get_resources(string $resource) + { + if (!is_string($resource)) { + throw new \InvalidArgumentException(); } - if ( ! array_key_exists( $resource, $this->resources ) ) { - - $options = array( - 'api_key' => $this->api_key, - 'timeout' => 10, + if (! array_key_exists($resource, $this->resources)) { + $options = [ + 'api_key' => $this->api_key, + 'timeout' => 10, 'Accept-Encoding' => 'gzip', - ); + ]; + + // Assign the resource to the request variable. + $request = $resource; - $request = sprintf('/%s/%s', $this->api_version, $resource === 'landing_pages' ? 'forms' : $resource); + // Landing pages are included in the /forms endpoint. + if ($resource === 'landing_pages') { + $request = 'forms'; + } - $this->create_log(sprintf("GET request %s, %s", $request, json_encode($options))); + $this->create_log(sprintf('GET request %s, %s', $request, json_encode($options))); - $resources = $this->make_request( $request, 'GET', $options ); + $resources = $this->get($request, $options); - if(!$resources) { - $this->create_log("No resources"); - $this->resources[ $resource ] = array( - array( - 'id' => '-2', + if (!$resources) { + $this->create_log('No resources'); + $this->resources[$resource] = [ + [ + 'id' => '-2', 'name' => 'Error contacting API', - ), - ); + ], + ]; } else { - $_resource = array(); + $_resource = []; + + if ('forms' === $resource) { + $response = []; + if (isset($resources->forms)) { + $response = $resources->forms; + } - if ( 'forms' === $resource ) { - $response = isset( $resources->forms ) ? $resources->forms : array(); - $this->create_log(sprintf("forms response %s", json_encode($response))); - foreach ( $response as $form ) { - if ( isset( $form->archived ) && $form->archived ) { + $this->create_log(sprintf('forms response %s', json_encode($response))); + foreach ($response as $form) { + if (isset($form->archived) && $form->archived) { continue; } + $_resource[] = $form; } - } elseif ( 'landing_pages' === $resource ) { - $response = isset($resources->forms ) ? $resources->forms : array(); - $this->create_log(sprintf("landing_pages response %s", json_encode($response))); - foreach ( $response as $landing_page ) { - if ( 'hosted' === $landing_page->type ) { - if ( isset( $landing_page->archived ) && $landing_page->archived ) { + } else if ('landing_pages' === $resource) { + $response = []; + if (isset($resources->forms)) { + $response = $resources->forms; + } + + $this->create_log(sprintf('landing_pages response %s', json_encode($response))); + foreach ($response as $landing_page) { + if ('hosted' === $landing_page->type) { + if (isset($landing_page->archived) && $landing_page->archived) { continue; } + $_resource[] = $landing_page; } } - } elseif ( 'subscription_forms' === $resource ) { - $this->create_log("subscription_forms"); - foreach ( $resources as $mapping ) { - if ( isset( $mapping->archived ) && $mapping->archived ) { + } else if ('subscription_forms' === $resource) { + $this->create_log('subscription_forms'); + foreach ($resources as $mapping) { + if (isset($mapping->archived) && $mapping->archived) { continue; } - $_resource[ $mapping->id ] = $mapping->form_id; + + $_resource[$mapping->id] = $mapping->form_id; } - } elseif ( 'tags' === $resource ) { - $response = isset( $resources->tags ) ? $resources->tags : array(); - $this->create_log(sprintf("tags response %s", json_encode($response))); - foreach ( $response as $tag ) { - $_resource[] = $tag; + } else if ('tags' === $resource) { + $response = []; + if (isset($resources->tags)) { + $response = $resources->tags; } - } - $this->resources[ $resource ] = $_resource; - } + $this->create_log(sprintf('tags response %s', json_encode($response))); + foreach ($response as $tag) { + $_resource[] = $tag; + } + }//end if - } + $this->resources[$resource] = $_resource; + }//end if + }//end if - return $this->resources[ $resource ]; + return $this->resources[$resource]; } + /** * Adds a subscriber to a form. * - * @param string $form_id Form ID. - * @param array $options Array of user data (email, name). + * @param integer $form_id Form ID. + * @param array $options Array of user data (email, name). + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. * * @return false|object */ - public function form_subscribe( $form_id, $options ) { - - if( !is_int($form_id) || !is_array($options) ) { - throw new \InvalidArgumentException; + public function form_subscribe(int $form_id, array $options) + { + if (!is_int($form_id) || !is_array($options)) { + throw new \InvalidArgumentException(); } - $request = $this->api_version . sprintf( '/forms/%s/subscribe', $form_id ); + $request = sprintf('forms/%s/subscribe', $form_id); $options['api_key'] = $this->api_key; - $this->create_log(sprintf("POST form subscribe: %s, %s, %s", $request, json_encode($options), $form_id)); - - return $this->make_request( $request, 'POST', $options ); + $this->create_log(sprintf('POST form subscribe: %s, %s, %s', $request, json_encode($options), $form_id)); + return $this->post($request, $options); } + /** * Remove subscription from a form * * @param array $options Array of user data (email). * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. + * * @return false|object */ - public function form_unsubscribe( $options ) { - - if( !is_array($options) ) { - throw new \InvalidArgumentException; + public function form_unsubscribe(array $options) + { + if (!is_array($options)) { + throw new \InvalidArgumentException(); } - $request = $this->api_version . '/unsubscribe'; + $request = 'unsubscribe'; $options['api_secret'] = $this->api_secret; - $this->create_log(sprintf("PUT form unsubscribe: %s, %s", $request, json_encode($options))); + $this->create_log(sprintf('PUT form unsubscribe: %s, %s', $request, json_encode($options))); - return $this->make_request( $request, 'PUT', $options ); + return $this->put($request, $options); } + /** * Get the ConvertKit subscriber ID associated with email address if it exists. * Return false if subscriber not found. * - * @param $email_address string - * @return false|int $subscriber_id + * @param string $email_address Email Address. + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. + * + * @return false|integer */ - public function get_subscriber_id( $email_address ) { - - if( !is_string($email_address) || !filter_var($email_address, FILTER_VALIDATE_EMAIL)) { - throw new \InvalidArgumentException; + public function get_subscriber_id(string $email_address) + { + if (!is_string($email_address) || !filter_var($email_address, FILTER_VALIDATE_EMAIL)) { + throw new \InvalidArgumentException(); } - $request = $this->api_version . '/subscribers'; - - $options = array( - 'api_secret' => $this->api_secret, - 'status' => 'all', + $request = 'subscribers'; + + $options = [ + 'api_secret' => $this->api_secret, + 'status' => 'all', + 'email_address' => $email_address, + ]; + + $this->create_log( + sprintf( + 'GET subscriber id from all subscribers: %s, %s, %s', + $request, + json_encode($options), + $email_address + ) ); - $this->create_log(sprintf("GET subscriber id from all subscribers: %s, %s, %s", $request, json_encode($options), $email_address)); + $subscribers = $this->get($request, $options); - $subscribers = $this->make_request( $request, 'GET', $options ); - - if( !$subscribers ) { - $this->create_log("No subscribers"); + if (!$subscribers) { + $this->create_log('No subscribers'); return false; } - $subscriber_id = $this::check_if_subscriber_in_array($email_address, $subscribers->subscribers); - - if($subscriber_id) { - return $subscriber_id; - } - - $total_pages = $subscribers->total_pages; - - $this->create_log(sprintf("Total number of pages is %s", $total_pages)); - - for ( $i = 2; $i <= $total_pages; $i++ ) { - $options['page'] = $i; - $this->create_log(sprintf("Go to page %s", $i)); - $subscribers = $this->make_request( $request, 'GET', $options ); - - if( !$subscribers ) { - return false; - } - - $subscriber_id = $this::check_if_subscriber_in_array($email_address, $subscribers->subscribers); - - if($subscriber_id) { - return $subscriber_id; - } + if ($subscribers->total_subscribers === 0) { + $this->create_log('No subscribers'); + return false; } - $this->create_log("Subscriber not found anywhere"); - - return false; - + // Return the subscriber's ID. + return $subscribers->subscribers[0]->id; } + /** * Get subscriber by id * - * @param $subscriber_id int + * @param integer $subscriber_id Subscriber ID. + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. * - * @return false|int + * @return false|integer */ - public function get_subscriber( $subscriber_id ) { - - if( !is_int($subscriber_id) || $subscriber_id < 1 ) { - throw new \InvalidArgumentException; + public function get_subscriber(int $subscriber_id) + { + if (!is_int($subscriber_id) || $subscriber_id < 1) { + throw new \InvalidArgumentException(); } - $request = $this->api_version . sprintf( '/subscribers/%s', $subscriber_id ); + $request = sprintf('subscribers/%s', $subscriber_id); - $options = array( + $options = [ 'api_secret' => $this->api_secret, - ); + ]; - $this->create_log(sprintf("GET subscriber tags: %s, %s, %s", $request, json_encode($options), $subscriber_id)); - - return $this->make_request( $request, 'GET', $options ); + $this->create_log(sprintf('GET subscriber tags: %s, %s, %s', $request, json_encode($options), $subscriber_id)); + return $this->get($request, $options); } + /** * Get a list of the tags for a subscriber. * - * @param $subscriber_id - * @return false|array $subscriber_tags Array of tags for customer with key of tag_id + * @param integer $subscriber_id Subscriber ID. + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. + * + * @return false|array */ - public function get_subscriber_tags( $subscriber_id ) { - - if( !is_int($subscriber_id) || $subscriber_id < 1 ) { - throw new \InvalidArgumentException; + public function get_subscriber_tags(int $subscriber_id) + { + if (!is_int($subscriber_id) || $subscriber_id < 1) { + throw new \InvalidArgumentException(); } - $request = $this->api_version . sprintf( '/subscribers/%s/tags', $subscriber_id ); + $request = sprintf('subscribers/%s/tags', $subscriber_id); - $options = array( + $options = [ 'api_key' => $this->api_key, - ); - - $this->create_log(sprintf("GET subscriber tags: %s, %s, %s", $request, json_encode($options), $subscriber_id)); + ]; - return $this->make_request( $request, 'GET', $options ); + $this->create_log(sprintf('GET subscriber tags: %s, %s, %s', $request, json_encode($options), $subscriber_id)); + return $this->get($request, $options); } + /** - * @param $options + * List purchases. + * + * @param array $options Request options. + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. * * @return false|object */ - public function list_purchases($options) { - - if( !is_array($options) ) { - throw new \InvalidArgumentException; + public function list_purchases(array $options) + { + if (!is_array($options)) { + throw new \InvalidArgumentException(); } - $request = $this->api_version . '/purchases'; + $request = 'purchases'; $options['api_secret'] = $this->api_secret; - $this->create_log(sprintf("GET list purchases: %s, %s", $request, json_encode($options))); + $this->create_log(sprintf('GET list purchases: %s, %s', $request, json_encode($options))); - return $this->make_request( $request, 'GET', $options ); + return $this->get($request, $options); } + /** * Creates a purchase. * - * @param array $options + * @param array $options Purchase data. + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. * * @return false|object */ - public function create_purchase($options) { - - if( !is_array($options) ) { - throw new \InvalidArgumentException; + public function create_purchase(array $options) + { + if (!is_array($options)) { + throw new \InvalidArgumentException(); } - $request = $this->api_version . '/purchases'; + $request = 'purchases'; $options['api_secret'] = $this->api_secret; - $this->create_log(sprintf("POST create purchase: %s, %s", $request, json_encode($options))); + $this->create_log(sprintf('POST create purchase: %s, %s', $request, json_encode($options))); - return $this->make_request( $request, 'POST', $options ); + return $this->post($request, $options); } + /** - * Get markup from ConvertKit for the provided $url + * Get markup from ConvertKit for the provided $url. + * + * Supports legacy forms and legacy landing pages. + * Forms and Landing Pages should be embedded using the supplied JS embed script in + * the API response when using get_resources(). + * + * @param string $url URL of HTML page. + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. * - * @param string $url URL of API action. * @return false|string */ - public function get_resource( $url ) { - - if( !is_string($url) ) { - throw new \InvalidArgumentException; - } - - if (strpos( $url, 'api_key' ) === false) { - $url .= '?api_key=' . $this->api_key; + public function get_resource(string $url) + { + if (!is_string($url) || !filter_var($url, FILTER_VALIDATE_URL)) { + throw new \InvalidArgumentException(); } $resource = ''; - $this->create_log(sprintf("Getting resource %s", $url)); + $this->create_log(sprintf('Getting resource %s', $url)); - if ( ! empty( $url ) && isset( $this->markup[ $url ] ) ) { - $this->create_log("Resource already set"); - $resource = $this->markup[ $url ]; - } elseif ( ! empty( $url ) ) { + // If the resource was already fetched, return the cached version now. + if (isset($this->markup[$url])) { + $this->create_log('Resource already set'); + return $this->markup[$url]; + } - if ( ! function_exists( 'str_get_html' ) ) { - require_once( dirname( __FILE__ ) . '/lib/simple-html-dom.php' ); - } + // Fetch the resource. + $request = new Request( + 'GET', + $url, + ['Accept-Encoding' => 'gzip'] + ); + $response = $this->client->send($request); + + // Fetch HTML. + $body = $response->getBody()->getContents(); + + // Forcibly tell DOMDocument that this HTML uses the UTF-8 charset. + // isn't enough, as DOMDocument still interprets the HTML as ISO-8859, + // which breaks character encoding. + // Use of mb_convert_encoding() with HTML-ENTITIES is deprecated in PHP 8.2, so we have to use this method. + // If we don't, special characters render incorrectly. + $body = str_replace( + '', + '' . "\n" . '', + $body + ); - if ( ! function_exists( 'url_to_absolute' ) ) { - require_once( dirname( __FILE__ ) . '/lib/url-to-absolute.php' ); - } + // Get just the scheme and host from the URL. + $url_scheme = parse_url($url); + $url_scheme_host_only = $url_scheme['scheme'] . '://' . $url_scheme['host']; + + // Load the HTML into a DOMDocument. + libxml_use_internal_errors(true); + $html = new \DOMDocument(); + $html->loadHTML($body); + + // Convert any relative URLs to absolute URLs in the HTML DOM. + $this->convert_relative_to_absolute_urls($html->getElementsByTagName('a'), 'href', $url_scheme_host_only); + $this->convert_relative_to_absolute_urls($html->getElementsByTagName('link'), 'href', $url_scheme_host_only); + $this->convert_relative_to_absolute_urls($html->getElementsByTagName('img'), 'src', $url_scheme_host_only); + $this->convert_relative_to_absolute_urls($html->getElementsByTagName('script'), 'src', $url_scheme_host_only); + $this->convert_relative_to_absolute_urls($html->getElementsByTagName('form'), 'action', $url_scheme_host_only); + + // Remove some HTML tags that DOMDocument adds, returning the output. + // We do this instead of using LIBXML_HTML_NOIMPLIED in loadHTML(), because Legacy Forms + // are not always contained in a single root / outer element, which is required for + // LIBXML_HTML_NOIMPLIED to correctly work. + $resource = $this->strip_html_head_body_tags($html->saveHTML()); + + // Cache and return. + $this->markup[$url] = $resource; + return $resource; + } - $this->create_log("Getting html from url"); - $html = file_get_html($url); - foreach ( $html->find( 'a, link' ) as $element ) { - if ( isset( $element->href ) ) { - $this->create_log(sprintf("To absolute url: %s", $element->href)); - echo url_to_absolute( $url, $element->href ); - $element->href = url_to_absolute( $url, $element->href ); - } + /** + * Converts any relative URls to absolute, fully qualified HTTP(s) URLs for the given + * DOM Elements. + * + * @param \DOMNodeList $elements Elements. + * @param string $attribute HTML Attribute. + * @param string $url Absolute URL to prepend to relative URLs. + * + * @since 1.0.0 + * + * @return void + */ + private function convert_relative_to_absolute_urls(\DOMNodeList $elements, string $attribute, string $url) + { + // Anchor hrefs. + foreach ($elements as $element) { + // Skip if the attribute's value is empty. + if (empty($element->getAttribute($attribute))) { + continue; } - foreach ( $html->find( 'img, script' ) as $element ) { - if ( isset( $element->src ) ) { - $this->create_log(sprintf("To absolute src: %s", $element->src)); - $element->src = url_to_absolute( $url, $element->src ); - } + // Skip if the attribute's value is a fully qualified URL. + if (filter_var($element->getAttribute($attribute), FILTER_VALIDATE_URL)) { + continue; } - foreach ( $html->find( 'form' ) as $element ) { - if ( isset( $element->action ) ) { - $this->create_log(sprintf("To absolute form: %s", $element->action)); - $element->action = url_to_absolute( $url, $element->action ); - } else { - $element->action = $url; - } + // Skip if this is a Google Font CSS URL. + if (strpos($element->getAttribute($attribute), '//fonts.googleapis.com') !== false) { + continue; } - $resource = $html->save(); - $this->markup[ $url ] = $resource; - + // If here, the attribute's value is a relative URL, missing the http(s) and domain. + // Prepend the URL to the attribute's value. + $element->setAttribute($attribute, $url . $element->getAttribute($attribute)); } + } - return $resource; + + /** + * Strips , and opening and closing tags from the given markup, + * as well as the Content-Type meta tag we might have added in get_html(). + * + * @param string $markup HTML Markup. + * + * @since 1.0.0 + * + * @return string HTML Markup + */ + private function strip_html_head_body_tags(string $markup) + { + $markup = str_replace('', '', $markup); + $markup = str_replace('', '', $markup); + $markup = str_replace('', '', $markup); + $markup = str_replace('', '', $markup); + $markup = str_replace('', '', $markup); + $markup = str_replace('', '', $markup); + $markup = str_replace('', '', $markup); + + return $markup; + } + + /** + * Performs a GET request to the API. + * + * @param string $endpoint API Endpoint. + * @param array $args Request arguments. + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. + * + * @return false|mixed + */ + public function get(string $endpoint, array $args = []) + { + return $this->make_request($endpoint, 'GET', $args); } /** - * @param $endpoint string, endpoint for request - * @param $method string, POST, GET, PUT, PATCH, DELETE - * @param array $args array, additional arguments for request + * Performs a POST request to the API. + * + * @param string $endpoint API Endpoint. + * @param array $args Request arguments. + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. * * @return false|mixed */ - public function make_request($endpoint, $method, $args = array()) { + public function post(string $endpoint, array $args = []) + { + return $this->make_request($endpoint, 'POST', $args); + } - if( !is_string($endpoint) || !is_string($method) || !is_array($args) ) { - throw new \InvalidArgumentException; + /** + * Performs a PUT request to the API. + * + * @param string $endpoint API Endpoint. + * @param array $args Request arguments. + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. + * + * @return false|mixed + */ + public function put(string $endpoint, array $args = []) + { + return $this->make_request($endpoint, 'PUT', $args); + } + + /** + * Performs a DELETE request to the API. + * + * @param string $endpoint API Endpoint. + * @param array $args Request arguments. + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. + * + * @return false|mixed + */ + public function delete(string $endpoint, array $args = []) + { + return $this->make_request($endpoint, 'DELETE', $args); + } + + /** + * Performs an API request using Guzzle. + * + * @param string $endpoint API Endpoint. + * @param string $method Request method (POST, GET, PUT, PATCH, DELETE). + * @param array $args Request arguments. + * + * @throws \InvalidArgumentException If the provided arguments are not of the expected type. + * + * @return false|mixed + */ + public function make_request(string $endpoint, string $method, array $args = []) + { + if (!is_string($endpoint) || !is_string($method) || !is_array($args)) { + throw new \InvalidArgumentException(); } - $url = $this->api_url_base . $endpoint; + $url = $this->api_url_base . $this->api_version . '/' . $endpoint; - $this->create_log(sprintf("Making request on %s.", $url)); + $this->create_log(sprintf('Making request on %s.', $url)); $request_body = json_encode($args); - $this->create_log(sprintf("%s, Request body: %s", $method, $request_body)); + $this->create_log(sprintf('%s, Request body: %s', $method, $request_body)); - if( $method === "GET" ){ - if($args) { + if ($method === 'GET') { + if ($args) { $url .= '?' . http_build_query($args); } + $request = new Request($method, $url); } else { - $request = new Request($method, $url, array( - 'Content-Type' => 'application/json', - 'Content-Length' => strlen($request_body) - ), $request_body); + $request = new Request( + $method, + $url, + [ + 'Content-Type' => 'application/json', + 'Content-Length' => strlen($request_body), + ], + $request_body + ); } - $response = $this->client->send($request, [ - 'exceptions' => false - ]); + $response = $this->client->send( + $request, + ['exceptions' => false] + ); $status_code = $response->getStatusCode(); - // If not between 200 and 300 - if (!preg_match("/^[2-3][0-9]{2}/", $status_code)) { - $this->create_log(sprintf("Response code is %s.", $status_code)); + // If not between 200 and 300. + if (!preg_match('/^[2-3][0-9]{2}/', $status_code)) { + $this->create_log(sprintf('Response code is %s.', $status_code)); return false; } $response_body = json_decode($response->getBody()->getContents()); - if($response_body) { - $this->create_log("Finish request successfully."); + if ($response_body) { + $this->create_log('Finish request successfully.'); return $response_body; } - $this->create_log("Failed to finish request."); + $this->create_log('Failed to finish request.'); return false; - } - - /** - * Looks for subscriber with email in array - * - * @param $email_address - * @param $subscribers - * - * @return false|int false if not found, else subscriber object - */ - private function check_if_subscriber_in_array($email_address, $subscribers) { - - foreach ($subscribers as $subscriber) { - if ($subscriber->email_address === $email_address) { - $this->create_log("Subscriber found!"); - return $subscriber->id; - } - } - - $this->create_log("Subscriber not found on current page."); - return false; - - } - } diff --git a/src/lib/simple-html-dom.php b/src/lib/simple-html-dom.php deleted file mode 100644 index acef9cd..0000000 --- a/src/lib/simple-html-dom.php +++ /dev/null @@ -1,1719 +0,0 @@ -size is the "real" number of bytes the dom was created from. - * but for most purposes, it's a really good estimation. - * Paperg - Added the forceTagsClosed to the dom constructor. Forcing tags closed is great for malformed html, but it CAN lead to parsing errors. - * Allow the user to tell us how much they trust the html. - * Paperg add the text and plaintext to the selectors for the find syntax. plaintext implies text in the innertext of a node. text implies that the tag is a text node. - * This allows for us to find tags based on the text they contain. - * Create find_ancestor_tag to see if a tag is - at any level - inside of another specific tag. - * Paperg: added parse_charset so that we know about the character set of the source document. - * NOTE: If the user's system has a routine called get_last_retrieve_url_contents_content_type availalbe, we will assume it's returning the content-type header from the - * last transfer or curl_exec, and we will parse that and use it in preference to any other method of charset detection. - * - * Found infinite loop in the case of broken html in restore_noise. Rewrote to protect from that. - * PaperG (John Schlick) Added get_display_size for "IMG" tags. - * - * Licensed under The MIT License - * Redistributions of files must retain the above copyright notice. - * - * @author S.C. Chen - * @author John Schlick - * @author Rus Carroll - * @version 1.5 ($Rev: 196 $) - * @package PlaceLocalInclude - * @subpackage simple_html_dom - */ - -/** - * All of the Defines for the classes below. - * @author S.C. Chen - */ -define('HDOM_TYPE_ELEMENT', 1); -define('HDOM_TYPE_COMMENT', 2); -define('HDOM_TYPE_TEXT', 3); -define('HDOM_TYPE_ENDTAG', 4); -define('HDOM_TYPE_ROOT', 5); -define('HDOM_TYPE_UNKNOWN', 6); -define('HDOM_QUOTE_DOUBLE', 0); -define('HDOM_QUOTE_SINGLE', 1); -define('HDOM_QUOTE_NO', 3); -define('HDOM_INFO_BEGIN', 0); -define('HDOM_INFO_END', 1); -define('HDOM_INFO_QUOTE', 2); -define('HDOM_INFO_SPACE', 3); -define('HDOM_INFO_TEXT', 4); -define('HDOM_INFO_INNER', 5); -define('HDOM_INFO_OUTER', 6); -define('HDOM_INFO_ENDSPACE',7); -define('DEFAULT_TARGET_CHARSET', 'UTF-8'); -define('DEFAULT_BR_TEXT', "\r\n"); -define('DEFAULT_SPAN_TEXT', " "); -define('MAX_FILE_SIZE', 600000); -// helper functions -// ----------------------------------------------------------------------------- -// get html dom from file -// $maxlen is defined in the code as PHP_STREAM_COPY_ALL which is defined as -1. -function file_get_html($url, $use_include_path = false, $context=null, $offset = -1, $maxLen=-1, $lowercase = true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) -{ - // We DO force the tags to be terminated. - $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText); - // For sourceforge users: uncomment the next line and comment the retreive_url_contents line 2 lines down if it is not already done. - $contents = file_get_contents($url, $use_include_path, $context); - // Paperg - use our own mechanism for getting the contents as we want to control the timeout. - //$contents = retrieve_url_contents($url); - if (empty($contents) || strlen($contents) > MAX_FILE_SIZE) - { - return false; - } - // The second parameter can force the selectors to all be lowercase. - $dom->load($contents, $lowercase, $stripRN); - return $dom; -} - -// get html dom from string -function str_get_html($str, $lowercase=true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) -{ - $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText); - if (empty($str) || strlen($str) > MAX_FILE_SIZE) - { - $dom->clear(); - return false; - } - $dom->load($str, $lowercase, $stripRN); - return $dom; -} - -// dump html dom tree -function dump_html_tree($node, $show_attr=true, $deep=0) -{ - $node->dump($node); -} - - -/** - * simple html dom node - * PaperG - added ability for "find" routine to lowercase the value of the selector. - * PaperG - added $tag_start to track the start position of the tag in the total byte index - * - * @package PlaceLocalInclude - */ -class simple_html_dom_node -{ - public $nodetype = HDOM_TYPE_TEXT; - public $tag = 'text'; - public $attr = array(); - public $children = array(); - public $nodes = array(); - public $parent = null; - // The "info" array - see HDOM_INFO_... for what each element contains. - public $_ = array(); - public $tag_start = 0; - private $dom = null; - - function __construct($dom) - { - $this->dom = $dom; - $dom->nodes[] = $this; - } - - function __destruct() - { - $this->clear(); - } - - function __toString() - { - return $this->outertext(); - } - - // clean up memory due to php5 circular references memory leak... - function clear() - { - $this->dom = null; - $this->nodes = null; - $this->parent = null; - $this->children = null; - } - - // dump node's tree - function dump($show_attr=true, $deep=0) - { - $lead = str_repeat(' ', $deep); - - echo $lead.$this->tag; - if ($show_attr && count($this->attr)>0) - { - echo '('; - foreach ($this->attr as $k=>$v) - echo "[$k]=>\"".$this->$k.'", '; - echo ')'; - } - echo "\n"; - - if ($this->nodes) - { - foreach ($this->nodes as $c) - { - $c->dump($show_attr, $deep+1); - } - } - } - - - // Debugging function to dump a single dom node with a bunch of information about it. - function dump_node($echo=true) - { - - $string = $this->tag; - if (count($this->attr)>0) - { - $string .= '('; - foreach ($this->attr as $k=>$v) - { - $string .= "[$k]=>\"".$this->$k.'", '; - } - $string .= ')'; - } - if (count($this->_)>0) - { - $string .= ' $_ ('; - foreach ($this->_ as $k=>$v) - { - if (is_array($v)) - { - $string .= "[$k]=>("; - foreach ($v as $k2=>$v2) - { - $string .= "[$k2]=>\"".$v2.'", '; - } - $string .= ")"; - } else { - $string .= "[$k]=>\"".$v.'", '; - } - } - $string .= ")"; - } - - if (isset($this->text)) - { - $string .= " text: (" . $this->text . ")"; - } - - $string .= " HDOM_INNER_INFO: '"; - if (isset($node->_[HDOM_INFO_INNER])) - { - $string .= $node->_[HDOM_INFO_INNER] . "'"; - } - else - { - $string .= ' NULL '; - } - - $string .= " children: " . count($this->children); - $string .= " nodes: " . count($this->nodes); - $string .= " tag_start: " . $this->tag_start; - $string .= "\n"; - - if ($echo) - { - echo $string; - return; - } - else - { - return $string; - } - } - - // returns the parent of node - // If a node is passed in, it will reset the parent of the current node to that one. - function parent($parent=null) - { - // I am SURE that this doesn't work properly. - // It fails to unset the current node from it's current parents nodes or children list first. - if ($parent !== null) - { - $this->parent = $parent; - $this->parent->nodes[] = $this; - $this->parent->children[] = $this; - } - - return $this->parent; - } - - // verify that node has children - function has_child() - { - return !empty($this->children); - } - - // returns children of node - function children($idx=-1) - { - if ($idx===-1) - { - return $this->children; - } - if (isset($this->children[$idx])) return $this->children[$idx]; - return null; - } - - // returns the first child of node - function first_child() - { - if (count($this->children)>0) - { - return $this->children[0]; - } - return null; - } - - // returns the last child of node - function last_child() - { - if (($count=count($this->children))>0) - { - return $this->children[$count-1]; - } - return null; - } - - // returns the next sibling of node - function next_sibling() - { - if ($this->parent===null) - { - return null; - } - - $idx = 0; - $count = count($this->parent->children); - while ($idx<$count && $this!==$this->parent->children[$idx]) - { - ++$idx; - } - if (++$idx>=$count) - { - return null; - } - return $this->parent->children[$idx]; - } - - // returns the previous sibling of node - function prev_sibling() - { - if ($this->parent===null) return null; - $idx = 0; - $count = count($this->parent->children); - while ($idx<$count && $this!==$this->parent->children[$idx]) - ++$idx; - if (--$idx<0) return null; - return $this->parent->children[$idx]; - } - - // function to locate a specific ancestor tag in the path to the root. - function find_ancestor_tag($tag) - { - global $debugObject; - if (is_object($debugObject)) { $debugObject->debugLogEntry(1); } - - // Start by including ourselves in the comparison. - $returnDom = $this; - - while (!is_null($returnDom)) - { - if (is_object($debugObject)) { $debugObject->debugLog(2, "Current tag is: " . $returnDom->tag); } - - if ($returnDom->tag == $tag) - { - break; - } - $returnDom = $returnDom->parent; - } - return $returnDom; - } - - // get dom node's inner html - function innertext() - { - if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER]; - if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); - - $ret = ''; - foreach ($this->nodes as $n) - $ret .= $n->outertext(); - return $ret; - } - - // get dom node's outer text (with tag) - function outertext() - { - global $debugObject; - if (is_object($debugObject)) - { - $text = ''; - if ($this->tag == 'text') - { - if (!empty($this->text)) - { - $text = " with text: " . $this->text; - } - } - $debugObject->debugLog(1, 'Innertext of tag: ' . $this->tag . $text); - } - - if ($this->tag==='root') return $this->innertext(); - - // trigger callback - if ($this->dom && $this->dom->callback!==null) - { - call_user_func_array($this->dom->callback, array($this)); - } - - if (isset($this->_[HDOM_INFO_OUTER])) return $this->_[HDOM_INFO_OUTER]; - if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); - - // render begin tag - if ($this->dom && $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]) - { - $ret = $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]->makeup(); - } else { - $ret = ""; - } - - // render inner text - if (isset($this->_[HDOM_INFO_INNER])) - { - // If it's a br tag... don't return the HDOM_INNER_INFO that we may or may not have added. - if ($this->tag != "br") - { - $ret .= $this->_[HDOM_INFO_INNER]; - } - } else { - if ($this->nodes) - { - foreach ($this->nodes as $n) - { - $ret .= $this->convert_text($n->outertext()); - } - } - } - - // render end tag - if (isset($this->_[HDOM_INFO_END]) && $this->_[HDOM_INFO_END]!=0) - $ret .= 'tag.'>'; - return $ret; - } - - // get dom node's plain text - function text() - { - if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER]; - switch ($this->nodetype) - { - case HDOM_TYPE_TEXT: return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); - case HDOM_TYPE_COMMENT: return ''; - case HDOM_TYPE_UNKNOWN: return ''; - } - if (strcasecmp($this->tag, 'script')===0) return ''; - if (strcasecmp($this->tag, 'style')===0) return ''; - - $ret = ''; - // In rare cases, (always node type 1 or HDOM_TYPE_ELEMENT - observed for some span tags, and some p tags) $this->nodes is set to NULL. - // NOTE: This indicates that there is a problem where it's set to NULL without a clear happening. - // WHY is this happening? - if (!is_null($this->nodes)) - { - foreach ($this->nodes as $n) - { - $ret .= $this->convert_text($n->text()); - } - - // If this node is a span... add a space at the end of it so multiple spans don't run into each other. This is plaintext after all. - if ($this->tag == "span") - { - $ret .= $this->dom->default_span_text; - } - - - } - return $ret; - } - - function xmltext() - { - $ret = $this->innertext(); - $ret = str_ireplace('', '', $ret); - return $ret; - } - - // build node's text with tag - function makeup() - { - // text, comment, unknown - if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); - - $ret = '<'.$this->tag; - $i = -1; - - foreach ($this->attr as $key=>$val) - { - ++$i; - - // skip removed attribute - if ($val===null || $val===false) - continue; - - $ret .= $this->_[HDOM_INFO_SPACE][$i][0]; - //no value attr: nowrap, checked selected... - if ($val===true) - $ret .= $key; - else { - switch ($this->_[HDOM_INFO_QUOTE][$i]) - { - case HDOM_QUOTE_DOUBLE: $quote = '"'; break; - case HDOM_QUOTE_SINGLE: $quote = '\''; break; - default: $quote = ''; - } - $ret .= $key.$this->_[HDOM_INFO_SPACE][$i][1].'='.$this->_[HDOM_INFO_SPACE][$i][2].$quote.$val.$quote; - } - } - $ret = $this->dom->restore_noise($ret); - return $ret . $this->_[HDOM_INFO_ENDSPACE] . '>'; - } - - // find elements by css selector - //PaperG - added ability for find to lowercase the value of the selector. - function find($selector, $idx=null, $lowercase=false) - { - $selectors = $this->parse_selector($selector); - if (($count=count($selectors))===0) return array(); - $found_keys = array(); - - // find each selector - for ($c=0; $c<$count; ++$c) - { - // The change on the below line was documented on the sourceforge code tracker id 2788009 - // used to be: if (($levle=count($selectors[0]))===0) return array(); - if (($levle=count($selectors[$c]))===0) return array(); - if (!isset($this->_[HDOM_INFO_BEGIN])) return array(); - - $head = array($this->_[HDOM_INFO_BEGIN]=>1); - - // handle descendant selectors, no recursive! - for ($l=0; $l<$levle; ++$l) - { - $ret = array(); - foreach ($head as $k=>$v) - { - $n = ($k===-1) ? $this->dom->root : $this->dom->nodes[$k]; - //PaperG - Pass this optional parameter on to the seek function. - $n->seek($selectors[$c][$l], $ret, $lowercase); - } - $head = $ret; - } - - foreach ($head as $k=>$v) - { - if (!isset($found_keys[$k])) - $found_keys[$k] = 1; - } - } - - // sort keys - ksort($found_keys); - - $found = array(); - foreach ($found_keys as $k=>$v) - $found[] = $this->dom->nodes[$k]; - - // return nth-element or array - if (is_null($idx)) return $found; - else if ($idx<0) $idx = count($found) + $idx; - return (isset($found[$idx])) ? $found[$idx] : null; - } - - // seek for given conditions - // PaperG - added parameter to allow for case insensitive testing of the value of a selector. - protected function seek($selector, &$ret, $lowercase=false) - { - global $debugObject; - if (is_object($debugObject)) { $debugObject->debugLogEntry(1); } - - list($tag, $key, $val, $exp, $no_key) = $selector; - - // xpath index - if ($tag && $key && is_numeric($key)) - { - $count = 0; - foreach ($this->children as $c) - { - if ($tag==='*' || $tag===$c->tag) { - if (++$count==$key) { - $ret[$c->_[HDOM_INFO_BEGIN]] = 1; - return; - } - } - } - return; - } - - $end = (!empty($this->_[HDOM_INFO_END])) ? $this->_[HDOM_INFO_END] : 0; - if ($end==0) { - $parent = $this->parent; - while (!isset($parent->_[HDOM_INFO_END]) && $parent!==null) { - $end -= 1; - $parent = $parent->parent; - } - $end += $parent->_[HDOM_INFO_END]; - } - - for ($i=$this->_[HDOM_INFO_BEGIN]+1; $i<$end; ++$i) { - $node = $this->dom->nodes[$i]; - - $pass = true; - - if ($tag==='*' && !$key) { - if (in_array($node, $this->children, true)) - $ret[$i] = 1; - continue; - } - - // compare tag - if ($tag && $tag!=$node->tag && $tag!=='*') {$pass=false;} - // compare key - if ($pass && $key) { - if ($no_key) { - if (isset($node->attr[$key])) $pass=false; - } else { - if (($key != "plaintext") && !isset($node->attr[$key])) $pass=false; - } - } - // compare value - if ($pass && $key && $val && $val!=='*') { - // If they have told us that this is a "plaintext" search then we want the plaintext of the node - right? - if ($key == "plaintext") { - // $node->plaintext actually returns $node->text(); - $nodeKeyValue = $node->text(); - } else { - // this is a normal search, we want the value of that attribute of the tag. - $nodeKeyValue = $node->attr[$key]; - } - if (is_object($debugObject)) {$debugObject->debugLog(2, "testing node: " . $node->tag . " for attribute: " . $key . $exp . $val . " where nodes value is: " . $nodeKeyValue);} - - //PaperG - If lowercase is set, do a case insensitive test of the value of the selector. - if ($lowercase) { - $check = $this->match($exp, strtolower($val), strtolower($nodeKeyValue)); - } else { - $check = $this->match($exp, $val, $nodeKeyValue); - } - if (is_object($debugObject)) {$debugObject->debugLog(2, "after match: " . ($check ? "true" : "false"));} - - // handle multiple class - if (!$check && strcasecmp($key, 'class')===0) { - foreach (explode(' ',$node->attr[$key]) as $k) { - // Without this, there were cases where leading, trailing, or double spaces lead to our comparing blanks - bad form. - if (!empty($k)) { - if ($lowercase) { - $check = $this->match($exp, strtolower($val), strtolower($k)); - } else { - $check = $this->match($exp, $val, $k); - } - if ($check) break; - } - } - } - if (!$check) $pass = false; - } - if ($pass) $ret[$i] = 1; - unset($node); - } - // It's passed by reference so this is actually what this function returns. - if (is_object($debugObject)) {$debugObject->debugLog(1, "EXIT - ret: ", $ret);} - } - - protected function match($exp, $pattern, $value) { - global $debugObject; - if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} - - switch ($exp) { - case '=': - return ($value===$pattern); - case '!=': - return ($value!==$pattern); - case '^=': - return preg_match("/^".preg_quote($pattern,'/')."/", $value); - case '$=': - return preg_match("/".preg_quote($pattern,'/')."$/", $value); - case '*=': - if ($pattern[0]=='/') { - return preg_match($pattern, $value); - } - return preg_match("/".$pattern."/i", $value); - } - return false; - } - - protected function parse_selector($selector_string) { - global $debugObject; - if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} - - // pattern of CSS selectors, modified from mootools - // Paperg: Add the colon to the attrbute, so that it properly finds like google does. - // Note: if you try to look at this attribute, yo MUST use getAttribute since $dom->x:y will fail the php syntax check. -// Notice the \[ starting the attbute? and the @? following? This implies that an attribute can begin with an @ sign that is not captured. -// This implies that an html attribute specifier may start with an @ sign that is NOT captured by the expression. -// farther study is required to determine of this should be documented or removed. -// $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; - $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-:]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; - preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER); - if (is_object($debugObject)) {$debugObject->debugLog(2, "Matches Array: ", $matches);} - - $selectors = array(); - $result = array(); - //print_r($matches); - - foreach ($matches as $m) { - $m[0] = trim($m[0]); - if ($m[0]==='' || $m[0]==='/' || $m[0]==='//') continue; - // for browser generated xpath - if ($m[1]==='tbody') continue; - - list($tag, $key, $val, $exp, $no_key) = array($m[1], null, null, '=', false); - if (!empty($m[2])) {$key='id'; $val=$m[2];} - if (!empty($m[3])) {$key='class'; $val=$m[3];} - if (!empty($m[4])) {$key=$m[4];} - if (!empty($m[5])) {$exp=$m[5];} - if (!empty($m[6])) {$val=$m[6];} - - // convert to lowercase - if ($this->dom->lowercase) {$tag=strtolower($tag); $key=strtolower($key);} - //elements that do NOT have the specified attribute - if (isset($key[0]) && $key[0]==='!') {$key=substr($key, 1); $no_key=true;} - - $result[] = array($tag, $key, $val, $exp, $no_key); - if (trim($m[7])===',') { - $selectors[] = $result; - $result = array(); - } - } - if (count($result)>0) - $selectors[] = $result; - return $selectors; - } - - function __get($name) { - if (isset($this->attr[$name])) - { - return $this->convert_text($this->attr[$name]); - } - switch ($name) { - case 'outertext': return $this->outertext(); - case 'innertext': return $this->innertext(); - case 'plaintext': return $this->text(); - case 'xmltext': return $this->xmltext(); - default: return array_key_exists($name, $this->attr); - } - } - - function __set($name, $value) { - switch ($name) { - case 'outertext': return $this->_[HDOM_INFO_OUTER] = $value; - case 'innertext': - if (isset($this->_[HDOM_INFO_TEXT])) return $this->_[HDOM_INFO_TEXT] = $value; - return $this->_[HDOM_INFO_INNER] = $value; - } - if (!isset($this->attr[$name])) { - $this->_[HDOM_INFO_SPACE][] = array(' ', '', ''); - $this->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE; - } - $this->attr[$name] = $value; - } - - function __isset($name) { - switch ($name) { - case 'outertext': return true; - case 'innertext': return true; - case 'plaintext': return true; - } - //no value attr: nowrap, checked selected... - return (array_key_exists($name, $this->attr)) ? true : isset($this->attr[$name]); - } - - function __unset($name) { - if (isset($this->attr[$name])) - unset($this->attr[$name]); - } - - // PaperG - Function to convert the text from one character set to another if the two sets are not the same. - function convert_text($text) - { - global $debugObject; - if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} - - $converted_text = $text; - - $sourceCharset = ""; - $targetCharset = ""; - - if ($this->dom) - { - $sourceCharset = strtoupper($this->dom->_charset); - $targetCharset = strtoupper($this->dom->_target_charset); - } - if (is_object($debugObject)) {$debugObject->debugLog(3, "source charset: " . $sourceCharset . " target charaset: " . $targetCharset);} - - if (!empty($sourceCharset) && !empty($targetCharset) && (strcasecmp($sourceCharset, $targetCharset) != 0)) - { - // Check if the reported encoding could have been incorrect and the text is actually already UTF-8 - if ((strcasecmp($targetCharset, 'UTF-8') == 0) && ($this->is_utf8($text))) - { - $converted_text = $text; - } - else - { - $converted_text = iconv($sourceCharset, $targetCharset, $text); - } - } - - // Lets make sure that we don't have that silly BOM issue with any of the utf-8 text we output. - if ($targetCharset == 'UTF-8') - { - if (substr($converted_text, 0, 3) == "\xef\xbb\xbf") - { - $converted_text = substr($converted_text, 3); - } - if (substr($converted_text, -3) == "\xef\xbb\xbf") - { - $converted_text = substr($converted_text, 0, -3); - } - } - - return $converted_text; - } - - /** - * Returns true if $string is valid UTF-8 and false otherwise. - * - * @param mixed $str String to be tested - * @return boolean - */ - static function is_utf8($str) - { - $c=0; $b=0; - $bits=0; - $len=strlen($str); - for($i=0; $i<$len; $i++) - { - $c=ord($str[$i]); - if($c > 128) - { - if(($c >= 254)) return false; - elseif($c >= 252) $bits=6; - elseif($c >= 248) $bits=5; - elseif($c >= 240) $bits=4; - elseif($c >= 224) $bits=3; - elseif($c >= 192) $bits=2; - else return false; - if(($i+$bits) > $len) return false; - while($bits > 1) - { - $i++; - $b=ord($str[$i]); - if($b < 128 || $b > 191) return false; - $bits--; - } - } - } - return true; - } - /* - function is_utf8($string) - { - //this is buggy - return (utf8_encode(utf8_decode($string)) == $string); - } - */ - - /** - * Function to try a few tricks to determine the displayed size of an img on the page. - * NOTE: This will ONLY work on an IMG tag. Returns FALSE on all other tag types. - * - * @author John Schlick - * @version April 19 2012 - * @return array an array containing the 'height' and 'width' of the image on the page or -1 if we can't figure it out. - */ - function get_display_size() - { - global $debugObject; - - $width = -1; - $height = -1; - - if ($this->tag !== 'img') - { - return false; - } - - // See if there is aheight or width attribute in the tag itself. - if (isset($this->attr['width'])) - { - $width = $this->attr['width']; - } - - if (isset($this->attr['height'])) - { - $height = $this->attr['height']; - } - - // Now look for an inline style. - if (isset($this->attr['style'])) - { - // Thanks to user gnarf from stackoverflow for this regular expression. - $attributes = array(); - preg_match_all("/([\w-]+)\s*:\s*([^;]+)\s*;?/", $this->attr['style'], $matches, PREG_SET_ORDER); - foreach ($matches as $match) { - $attributes[$match[1]] = $match[2]; - } - - // If there is a width in the style attributes: - if (isset($attributes['width']) && $width == -1) - { - // check that the last two characters are px (pixels) - if (strtolower(substr($attributes['width'], -2)) == 'px') - { - $proposed_width = substr($attributes['width'], 0, -2); - // Now make sure that it's an integer and not something stupid. - if (filter_var($proposed_width, FILTER_VALIDATE_INT)) - { - $width = $proposed_width; - } - } - } - - // If there is a width in the style attributes: - if (isset($attributes['height']) && $height == -1) - { - // check that the last two characters are px (pixels) - if (strtolower(substr($attributes['height'], -2)) == 'px') - { - $proposed_height = substr($attributes['height'], 0, -2); - // Now make sure that it's an integer and not something stupid. - if (filter_var($proposed_height, FILTER_VALIDATE_INT)) - { - $height = $proposed_height; - } - } - } - - } - - // Future enhancement: - // Look in the tag to see if there is a class or id specified that has a height or width attribute to it. - - // Far future enhancement - // Look at all the parent tags of this image to see if they specify a class or id that has an img selector that specifies a height or width - // Note that in this case, the class or id will have the img subselector for it to apply to the image. - - // ridiculously far future development - // If the class or id is specified in a SEPARATE css file thats not on the page, go get it and do what we were just doing for the ones on the page. - - $result = array('height' => $height, - 'width' => $width); - return $result; - } - - // camel naming conventions - function getAllAttributes() {return $this->attr;} - function getAttribute($name) {return $this->__get($name);} - function setAttribute($name, $value) {$this->__set($name, $value);} - function hasAttribute($name) {return $this->__isset($name);} - function removeAttribute($name) {$this->__set($name, null);} - function getElementById($id) {return $this->find("#$id", 0);} - function getElementsById($id, $idx=null) {return $this->find("#$id", $idx);} - function getElementByTagName($name) {return $this->find($name, 0);} - function getElementsByTagName($name, $idx=null) {return $this->find($name, $idx);} - function parentNode() {return $this->parent();} - function childNodes($idx=-1) {return $this->children($idx);} - function firstChild() {return $this->first_child();} - function lastChild() {return $this->last_child();} - function nextSibling() {return $this->next_sibling();} - function previousSibling() {return $this->prev_sibling();} - function hasChildNodes() {return $this->has_child();} - function nodeName() {return $this->tag;} - function appendChild($node) {$node->parent($this); return $node;} - -} - -/** - * simple html dom parser - * Paperg - in the find routine: allow us to specify that we want case insensitive testing of the value of the selector. - * Paperg - change $size from protected to public so we can easily access it - * Paperg - added ForceTagsClosed in the constructor which tells us whether we trust the html or not. Default is to NOT trust it. - * - * @package PlaceLocalInclude - */ -class simple_html_dom -{ - public $root = null; - public $nodes = array(); - public $callback = null; - public $lowercase = false; - // Used to keep track of how large the text was when we started. - public $original_size; - public $size; - protected $pos; - protected $doc; - protected $char; - protected $cursor; - protected $parent; - protected $noise = array(); - protected $token_blank = " \t\r\n"; - protected $token_equal = ' =/>'; - protected $token_slash = " />\r\n\t"; - protected $token_attr = ' >'; - // Note that this is referenced by a child node, and so it needs to be public for that node to see this information. - public $_charset = ''; - public $_target_charset = ''; - protected $default_br_text = ""; - public $default_span_text = ""; - - // use isset instead of in_array, performance boost about 30%... - protected $self_closing_tags = array('img'=>1, 'br'=>1, 'input'=>1, 'meta'=>1, 'link'=>1, 'hr'=>1, 'base'=>1, 'embed'=>1, 'spacer'=>1); - protected $block_tags = array('root'=>1, 'body'=>1, 'form'=>1, 'div'=>1, 'span'=>1, 'table'=>1); - // Known sourceforge issue #2977341 - // B tags that are not closed cause us to return everything to the end of the document. - protected $optional_closing_tags = array( - 'tr'=>array('tr'=>1, 'td'=>1, 'th'=>1), - 'th'=>array('th'=>1), - 'td'=>array('td'=>1), - 'li'=>array('li'=>1), - 'dt'=>array('dt'=>1, 'dd'=>1), - 'dd'=>array('dd'=>1, 'dt'=>1), - 'dl'=>array('dd'=>1, 'dt'=>1), - 'p'=>array('p'=>1), - 'nobr'=>array('nobr'=>1), - 'b'=>array('b'=>1), - 'option'=>array('option'=>1), - ); - - function __construct($str=null, $lowercase=true, $forceTagsClosed=true, $target_charset=DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) - { - if ($str) - { - if (preg_match("/^http:\/\//i",$str) || is_file($str)) - { - $this->load_file($str); - } - else - { - $this->load($str, $lowercase, $stripRN, $defaultBRText, $defaultSpanText); - } - } - // Forcing tags to be closed implies that we don't trust the html, but it can lead to parsing errors if we SHOULD trust the html. - if (!$forceTagsClosed) { - $this->optional_closing_array=array(); - } - $this->_target_charset = $target_charset; - } - - function __destruct() - { - $this->clear(); - } - - // load html from string - function load($str, $lowercase=true, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) - { - global $debugObject; - - // prepare - $this->prepare($str, $lowercase, $stripRN, $defaultBRText, $defaultSpanText); - // strip out comments - $this->remove_noise("''is"); - // strip out cdata - $this->remove_noise("''is", true); - // Per sourceforge http://sourceforge.net/tracker/?func=detail&aid=2949097&group_id=218559&atid=1044037 - // Script tags removal now preceeds style tag removal. - // strip out