├── .gitignore ├── LICENSE ├── NOTICE ├── README.md ├── misc └── PSD │ └── graphics.psd ├── pom.xml └── src ├── main ├── resources │ └── com │ │ └── gravity │ │ └── goose │ │ ├── images │ │ └── known-image-css.txt │ │ ├── statichtml │ │ ├── aol1.txt │ │ ├── businessinsider1.txt │ │ ├── businessinsider2.txt │ │ ├── businessweek1.txt │ │ ├── businessweek2.txt │ │ ├── businessweek3.txt │ │ ├── cnbc1.txt │ │ ├── cnet1.txt │ │ ├── cnn1.txt │ │ ├── engadget1.txt │ │ ├── espn1.txt │ │ ├── foxnews1.txt │ │ ├── guardian1.txt │ │ ├── guardian1_result.txt │ │ ├── huffpo1.txt │ │ ├── huffpo2.txt │ │ ├── issue_24.txt │ │ ├── issue_24_result.txt │ │ ├── issue_25.txt │ │ ├── issue_28.txt │ │ ├── issue_32.txt │ │ ├── msn1.txt │ │ ├── msn1_result.txt │ │ ├── politico1.txt │ │ ├── scribd1.txt │ │ ├── techcrunch1.txt │ │ ├── time1.txt │ │ ├── time2.txt │ │ ├── usatoday1.txt │ │ ├── wired1.txt │ │ ├── wsj1.txt │ │ └── yahoo1.txt │ │ └── text │ │ └── stopwords-en.txt └── scala │ └── com │ └── gravity │ └── goose │ ├── Article.scala │ ├── Configuration.scala │ ├── Crawler.scala │ ├── Goose.scala │ ├── TalkToMeGoose.scala │ ├── cleaners │ ├── DocumentCleaner.scala │ └── StandardDocumentCleaner.scala │ ├── extractors │ ├── AdditionalDataExtractor.scala │ ├── ContentExtractor.scala │ ├── Extractor.scala │ ├── PublishDateExtractor.scala │ ├── StandardContentExtractor.scala │ └── TagsEvaluator.scala │ ├── images │ ├── Image.scala │ ├── ImageDetails.scala │ ├── ImageExtractor.scala │ ├── ImageSaver.scala │ ├── ImageUtils.scala │ ├── SecretGifException.scala │ ├── StandardImageExtractor.scala │ └── UpgradedImageIExtractor.scala │ ├── network │ ├── AbstractHtmlFetcher.scala │ ├── HtmlFetcher.scala │ ├── HttpExceptions.scala │ ├── MaxBytesException.scala │ └── NotHtmlException.scala │ ├── outputformatters │ ├── OutputFormatter.scala │ └── StandardOutputFormatter.scala │ ├── text │ ├── HashUtils.scala │ ├── ReplaceSequence.scala │ ├── StopWords.scala │ ├── StringReplacement.scala │ ├── StringSplitter.scala │ ├── WordStats.scala │ └── string.scala │ └── utils │ ├── FileHelper.scala │ ├── Logging.scala │ └── URLHelper.scala └── test ├── resources ├── akka.conf └── log4j.properties └── scala └── com └── gravity └── goose ├── ArticleTest.scala ├── ExtractionsTest.scala ├── GoldSitesTestIT.scala ├── GooseTest.scala ├── PerformanceTester.scala ├── TestUtils.scala ├── extractors └── VoicesContentExtractor.scala ├── images └── ImageUtilsIT.scala ├── text └── HashUtilsTest.scala └── utils ├── FileHelperTest.scala └── URLHelperTest.scala /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/LICENSE -------------------------------------------------------------------------------- /NOTICE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/NOTICE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/README.md -------------------------------------------------------------------------------- /misc/PSD/graphics.psd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/misc/PSD/graphics.psd -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/pom.xml -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/images/known-image-css.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/images/known-image-css.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/aol1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/aol1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/businessinsider1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/businessinsider1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/businessinsider2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/businessinsider2.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/businessweek1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/businessweek1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/businessweek2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/businessweek2.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/businessweek3.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/businessweek3.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/cnbc1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/cnbc1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/cnet1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/cnet1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/cnn1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/cnn1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/engadget1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/engadget1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/espn1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/espn1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/foxnews1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/foxnews1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/guardian1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/guardian1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/guardian1_result.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/guardian1_result.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/huffpo1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/huffpo1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/huffpo2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/huffpo2.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/issue_24.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/issue_24.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/issue_24_result.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/issue_24_result.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/issue_25.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/issue_25.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/issue_28.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/issue_28.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/issue_32.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/issue_32.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/msn1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/msn1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/msn1_result.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/msn1_result.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/politico1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/politico1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/scribd1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/scribd1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/techcrunch1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/techcrunch1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/time1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/time1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/time2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/time2.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/usatoday1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/usatoday1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/wired1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/wired1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/wsj1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/wsj1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/statichtml/yahoo1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/statichtml/yahoo1.txt -------------------------------------------------------------------------------- /src/main/resources/com/gravity/goose/text/stopwords-en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/resources/com/gravity/goose/text/stopwords-en.txt -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/Article.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/Article.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/Configuration.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/Configuration.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/Crawler.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/Crawler.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/Goose.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/Goose.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/TalkToMeGoose.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/TalkToMeGoose.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/cleaners/DocumentCleaner.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/cleaners/DocumentCleaner.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/cleaners/StandardDocumentCleaner.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/cleaners/StandardDocumentCleaner.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/extractors/AdditionalDataExtractor.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/extractors/AdditionalDataExtractor.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/extractors/ContentExtractor.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/extractors/ContentExtractor.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/extractors/Extractor.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/extractors/Extractor.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/extractors/PublishDateExtractor.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/extractors/PublishDateExtractor.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/extractors/StandardContentExtractor.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/extractors/StandardContentExtractor.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/extractors/TagsEvaluator.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/extractors/TagsEvaluator.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/images/Image.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/images/Image.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/images/ImageDetails.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/images/ImageDetails.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/images/ImageExtractor.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/images/ImageExtractor.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/images/ImageSaver.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/images/ImageSaver.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/images/ImageUtils.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/images/ImageUtils.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/images/SecretGifException.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/images/SecretGifException.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/images/StandardImageExtractor.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/images/StandardImageExtractor.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/images/UpgradedImageIExtractor.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/images/UpgradedImageIExtractor.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/network/AbstractHtmlFetcher.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/network/AbstractHtmlFetcher.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/network/HtmlFetcher.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/network/HtmlFetcher.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/network/HttpExceptions.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/network/HttpExceptions.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/network/MaxBytesException.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/network/MaxBytesException.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/network/NotHtmlException.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/network/NotHtmlException.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/outputformatters/OutputFormatter.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/outputformatters/OutputFormatter.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/outputformatters/StandardOutputFormatter.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/outputformatters/StandardOutputFormatter.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/text/HashUtils.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/text/HashUtils.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/text/ReplaceSequence.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/text/ReplaceSequence.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/text/StopWords.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/text/StopWords.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/text/StringReplacement.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/text/StringReplacement.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/text/StringSplitter.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/text/StringSplitter.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/text/WordStats.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/text/WordStats.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/text/string.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/text/string.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/utils/FileHelper.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/utils/FileHelper.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/utils/Logging.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/utils/Logging.scala -------------------------------------------------------------------------------- /src/main/scala/com/gravity/goose/utils/URLHelper.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/main/scala/com/gravity/goose/utils/URLHelper.scala -------------------------------------------------------------------------------- /src/test/resources/akka.conf: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /src/test/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/test/resources/log4j.properties -------------------------------------------------------------------------------- /src/test/scala/com/gravity/goose/ArticleTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/test/scala/com/gravity/goose/ArticleTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/gravity/goose/ExtractionsTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/test/scala/com/gravity/goose/ExtractionsTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/gravity/goose/GoldSitesTestIT.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/test/scala/com/gravity/goose/GoldSitesTestIT.scala -------------------------------------------------------------------------------- /src/test/scala/com/gravity/goose/GooseTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/test/scala/com/gravity/goose/GooseTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/gravity/goose/PerformanceTester.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/test/scala/com/gravity/goose/PerformanceTester.scala -------------------------------------------------------------------------------- /src/test/scala/com/gravity/goose/TestUtils.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/test/scala/com/gravity/goose/TestUtils.scala -------------------------------------------------------------------------------- /src/test/scala/com/gravity/goose/extractors/VoicesContentExtractor.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/test/scala/com/gravity/goose/extractors/VoicesContentExtractor.scala -------------------------------------------------------------------------------- /src/test/scala/com/gravity/goose/images/ImageUtilsIT.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/test/scala/com/gravity/goose/images/ImageUtilsIT.scala -------------------------------------------------------------------------------- /src/test/scala/com/gravity/goose/text/HashUtilsTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/test/scala/com/gravity/goose/text/HashUtilsTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/gravity/goose/utils/FileHelperTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/test/scala/com/gravity/goose/utils/FileHelperTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/gravity/goose/utils/URLHelperTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GravityLabs/goose/HEAD/src/test/scala/com/gravity/goose/utils/URLHelperTest.scala --------------------------------------------------------------------------------