├── .gitignore ├── .travis.yml ├── LICENSE.txt ├── README.md ├── nb-configuration.xml └── src ├── main ├── java │ └── de │ │ └── fhopf │ │ └── akka │ │ ├── Execution.java │ │ ├── Executor.java │ │ ├── HtmlParserPageRetriever.java │ │ ├── Indexer.java │ │ ├── IndexerImpl.java │ │ ├── PageContent.java │ │ ├── PageRetriever.java │ │ ├── RetrievalException.java │ │ ├── VisitedPageStore.java │ │ ├── actor │ │ ├── IndexedMessage.java │ │ ├── IndexingActor.java │ │ ├── Master.java │ │ ├── PageParsingActor.java │ │ ├── SimpleActorExecution.java │ │ ├── SimpleActorMaster.java │ │ └── parallel │ │ │ ├── ChaosMonkeyPageRetriever.java │ │ │ ├── FailingExecution.java │ │ │ ├── FetchInParallelExecution.java │ │ │ ├── FetchSupervisedExecution.java │ │ │ ├── ParallelMaster.java │ │ │ ├── ResendingPageParsingActor.java │ │ │ └── SupervisingActor.java │ │ └── sequential │ │ └── SequentialExecution.java └── resources │ ├── application.conf │ └── log4j.properties └── test └── java └── de └── fhopf └── akka ├── HtmlParserPageRetrieverTest.java ├── HtmlParserTest.java └── IndexerImplTest.java /.gitignore: -------------------------------------------------------------------------------- 1 | target/ 2 | .gradle/ 3 | build/ 4 | -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- 1 | language: java 2 | -------------------------------------------------------------------------------- /LICENSE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/LICENSE.txt -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/README.md -------------------------------------------------------------------------------- /nb-configuration.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/nb-configuration.xml -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/Execution.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/Execution.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/Executor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/Executor.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/HtmlParserPageRetriever.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/HtmlParserPageRetriever.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/Indexer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/Indexer.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/IndexerImpl.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/IndexerImpl.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/PageContent.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/PageContent.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/PageRetriever.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/PageRetriever.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/RetrievalException.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/RetrievalException.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/VisitedPageStore.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/VisitedPageStore.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/actor/IndexedMessage.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/actor/IndexedMessage.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/actor/IndexingActor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/actor/IndexingActor.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/actor/Master.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/actor/Master.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/actor/PageParsingActor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/actor/PageParsingActor.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/actor/SimpleActorExecution.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/actor/SimpleActorExecution.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/actor/SimpleActorMaster.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/actor/SimpleActorMaster.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/actor/parallel/ChaosMonkeyPageRetriever.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/actor/parallel/ChaosMonkeyPageRetriever.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/actor/parallel/FailingExecution.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/actor/parallel/FailingExecution.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/actor/parallel/FetchInParallelExecution.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/actor/parallel/FetchInParallelExecution.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/actor/parallel/FetchSupervisedExecution.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/actor/parallel/FetchSupervisedExecution.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/actor/parallel/ParallelMaster.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/actor/parallel/ParallelMaster.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/actor/parallel/ResendingPageParsingActor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/actor/parallel/ResendingPageParsingActor.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/actor/parallel/SupervisingActor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/actor/parallel/SupervisingActor.java -------------------------------------------------------------------------------- /src/main/java/de/fhopf/akka/sequential/SequentialExecution.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/java/de/fhopf/akka/sequential/SequentialExecution.java -------------------------------------------------------------------------------- /src/main/resources/application.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/resources/application.conf -------------------------------------------------------------------------------- /src/main/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/main/resources/log4j.properties -------------------------------------------------------------------------------- /src/test/java/de/fhopf/akka/HtmlParserPageRetrieverTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/test/java/de/fhopf/akka/HtmlParserPageRetrieverTest.java -------------------------------------------------------------------------------- /src/test/java/de/fhopf/akka/HtmlParserTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/test/java/de/fhopf/akka/HtmlParserTest.java -------------------------------------------------------------------------------- /src/test/java/de/fhopf/akka/IndexerImplTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fhopf/akka-crawler-example/HEAD/src/test/java/de/fhopf/akka/IndexerImplTest.java --------------------------------------------------------------------------------