├── .gitignore ├── LICENSE ├── README.md ├── composer.json ├── phpunit.xml.dist ├── resources ├── images │ └── known-image-css.txt └── text │ ├── LICENSE-GD │ ├── README.md │ ├── stopwords-ar.txt │ ├── stopwords-cs.txt │ ├── stopwords-da.txt │ ├── stopwords-de.txt │ ├── stopwords-en.txt │ ├── stopwords-es.txt │ ├── stopwords-fi.txt │ ├── stopwords-fr.txt │ ├── stopwords-hu.txt │ ├── stopwords-id.txt │ ├── stopwords-it.txt │ ├── stopwords-ja.txt │ ├── stopwords-ko.txt │ ├── stopwords-nb.txt │ ├── stopwords-nl.txt │ ├── stopwords-no.txt │ ├── stopwords-pl.txt │ ├── stopwords-pt.txt │ ├── stopwords-ru.txt │ ├── stopwords-sv.txt │ ├── stopwords-vi.txt │ └── stopwords-zh.txt ├── src ├── Article.php ├── Client.php ├── Configuration.php ├── Crawler.php ├── Exceptions │ └── MalformedURLException.php ├── Images │ ├── Image.php │ ├── ImageUtils.php │ └── LocallyStoredImage.php ├── Modules │ ├── AbstractModule.php │ ├── Cleaners │ │ └── DocumentCleaner.php │ ├── Extractors │ │ ├── AdditionalDataExtractor.php │ │ ├── ContentExtractor.php │ │ ├── ImageExtractor.php │ │ ├── MetaExtractor.php │ │ └── PublishDateExtractor.php │ ├── Formatters │ │ └── OutputFormatter.php │ └── ModuleInterface.php ├── Text │ ├── StopWords.php │ └── WordStats.php ├── Traits │ ├── ArticleMutatorTrait.php │ ├── DocumentMutatorTrait.php │ ├── NodeCommonTrait.php │ └── NodeGravityTrait.php └── Utils │ └── Helper.php └── tests ├── Harness └── TestTrait.php ├── Modules ├── Cleaners │ └── DocumentCleanerTest.php └── Extractors │ ├── AdditionalDataExtractorTest.php │ ├── MetaExtractorTest.php │ └── PublishDateExtractorTest.php └── Utils └── HelperTest.php /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/README.md -------------------------------------------------------------------------------- /composer.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/composer.json -------------------------------------------------------------------------------- /phpunit.xml.dist: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/phpunit.xml.dist -------------------------------------------------------------------------------- /resources/images/known-image-css.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/images/known-image-css.txt -------------------------------------------------------------------------------- /resources/text/LICENSE-GD: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/LICENSE-GD -------------------------------------------------------------------------------- /resources/text/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/README.md -------------------------------------------------------------------------------- /resources/text/stopwords-ar.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-ar.txt -------------------------------------------------------------------------------- /resources/text/stopwords-cs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-cs.txt -------------------------------------------------------------------------------- /resources/text/stopwords-da.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-da.txt -------------------------------------------------------------------------------- /resources/text/stopwords-de.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-de.txt -------------------------------------------------------------------------------- /resources/text/stopwords-en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-en.txt -------------------------------------------------------------------------------- /resources/text/stopwords-es.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-es.txt -------------------------------------------------------------------------------- /resources/text/stopwords-fi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-fi.txt -------------------------------------------------------------------------------- /resources/text/stopwords-fr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-fr.txt -------------------------------------------------------------------------------- /resources/text/stopwords-hu.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-hu.txt -------------------------------------------------------------------------------- /resources/text/stopwords-id.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-id.txt -------------------------------------------------------------------------------- /resources/text/stopwords-it.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-it.txt -------------------------------------------------------------------------------- /resources/text/stopwords-ja.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-ja.txt -------------------------------------------------------------------------------- /resources/text/stopwords-ko.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-ko.txt -------------------------------------------------------------------------------- /resources/text/stopwords-nb.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-nb.txt -------------------------------------------------------------------------------- /resources/text/stopwords-nl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-nl.txt -------------------------------------------------------------------------------- /resources/text/stopwords-no.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-no.txt -------------------------------------------------------------------------------- /resources/text/stopwords-pl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-pl.txt -------------------------------------------------------------------------------- /resources/text/stopwords-pt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-pt.txt -------------------------------------------------------------------------------- /resources/text/stopwords-ru.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-ru.txt -------------------------------------------------------------------------------- /resources/text/stopwords-sv.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-sv.txt -------------------------------------------------------------------------------- /resources/text/stopwords-vi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-vi.txt -------------------------------------------------------------------------------- /resources/text/stopwords-zh.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/resources/text/stopwords-zh.txt -------------------------------------------------------------------------------- /src/Article.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Article.php -------------------------------------------------------------------------------- /src/Client.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Client.php -------------------------------------------------------------------------------- /src/Configuration.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Configuration.php -------------------------------------------------------------------------------- /src/Crawler.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Crawler.php -------------------------------------------------------------------------------- /src/Exceptions/MalformedURLException.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Exceptions/MalformedURLException.php -------------------------------------------------------------------------------- /src/Images/Image.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Images/Image.php -------------------------------------------------------------------------------- /src/Images/ImageUtils.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Images/ImageUtils.php -------------------------------------------------------------------------------- /src/Images/LocallyStoredImage.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Images/LocallyStoredImage.php -------------------------------------------------------------------------------- /src/Modules/AbstractModule.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Modules/AbstractModule.php -------------------------------------------------------------------------------- /src/Modules/Cleaners/DocumentCleaner.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Modules/Cleaners/DocumentCleaner.php -------------------------------------------------------------------------------- /src/Modules/Extractors/AdditionalDataExtractor.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Modules/Extractors/AdditionalDataExtractor.php -------------------------------------------------------------------------------- /src/Modules/Extractors/ContentExtractor.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Modules/Extractors/ContentExtractor.php -------------------------------------------------------------------------------- /src/Modules/Extractors/ImageExtractor.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Modules/Extractors/ImageExtractor.php -------------------------------------------------------------------------------- /src/Modules/Extractors/MetaExtractor.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Modules/Extractors/MetaExtractor.php -------------------------------------------------------------------------------- /src/Modules/Extractors/PublishDateExtractor.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Modules/Extractors/PublishDateExtractor.php -------------------------------------------------------------------------------- /src/Modules/Formatters/OutputFormatter.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Modules/Formatters/OutputFormatter.php -------------------------------------------------------------------------------- /src/Modules/ModuleInterface.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Modules/ModuleInterface.php -------------------------------------------------------------------------------- /src/Text/StopWords.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Text/StopWords.php -------------------------------------------------------------------------------- /src/Text/WordStats.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Text/WordStats.php -------------------------------------------------------------------------------- /src/Traits/ArticleMutatorTrait.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Traits/ArticleMutatorTrait.php -------------------------------------------------------------------------------- /src/Traits/DocumentMutatorTrait.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Traits/DocumentMutatorTrait.php -------------------------------------------------------------------------------- /src/Traits/NodeCommonTrait.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Traits/NodeCommonTrait.php -------------------------------------------------------------------------------- /src/Traits/NodeGravityTrait.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Traits/NodeGravityTrait.php -------------------------------------------------------------------------------- /src/Utils/Helper.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/src/Utils/Helper.php -------------------------------------------------------------------------------- /tests/Harness/TestTrait.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/tests/Harness/TestTrait.php -------------------------------------------------------------------------------- /tests/Modules/Cleaners/DocumentCleanerTest.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/tests/Modules/Cleaners/DocumentCleanerTest.php -------------------------------------------------------------------------------- /tests/Modules/Extractors/AdditionalDataExtractorTest.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/tests/Modules/Extractors/AdditionalDataExtractorTest.php -------------------------------------------------------------------------------- /tests/Modules/Extractors/MetaExtractorTest.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/tests/Modules/Extractors/MetaExtractorTest.php -------------------------------------------------------------------------------- /tests/Modules/Extractors/PublishDateExtractorTest.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/tests/Modules/Extractors/PublishDateExtractorTest.php -------------------------------------------------------------------------------- /tests/Utils/HelperTest.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scotteh/php-goose/HEAD/tests/Utils/HelperTest.php --------------------------------------------------------------------------------