├── .gitignore ├── LICENSE ├── README.md ├── bin ├── build.sh ├── docker-data │ ├── cassandra │ │ └── .gitkeep │ └── nutch │ │ └── .gitkeep ├── ipof.sh ├── nodes.sh ├── restart.sh ├── start.sh └── stop.sh ├── cassandra ├── Dockerfile └── docker-entrypoint.sh └── nutch ├── Dockerfile ├── bootstrap.sh ├── config └── nutch-site.xml ├── plugin └── nutch2-index-html │ ├── .gitignore │ ├── LICENSE │ ├── README.md │ ├── build │ └── index-html │ │ ├── classes │ │ └── org │ │ │ └── apache │ │ │ └── nutch │ │ │ └── indexer │ │ │ └── html │ │ │ └── HtmlIndexingFilter.class │ │ └── index-html.jar │ └── src │ └── plugin │ └── index-html │ ├── build.xml │ ├── ivy.xml │ ├── plugin.xml │ └── src │ └── java │ └── org │ └── apache │ └── nutch │ └── indexer │ └── html │ ├── HtmlIndexingFilter.java │ └── package.html └── testUrls └── seed.txt /.gitignore: -------------------------------------------------------------------------------- 1 | .idea 2 | atlassian-ide-plugin.xml -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/README.md -------------------------------------------------------------------------------- /bin/build.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/bin/build.sh -------------------------------------------------------------------------------- /bin/docker-data/cassandra/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /bin/docker-data/nutch/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /bin/ipof.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/bin/ipof.sh -------------------------------------------------------------------------------- /bin/nodes.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/bin/nodes.sh -------------------------------------------------------------------------------- /bin/restart.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/bin/restart.sh -------------------------------------------------------------------------------- /bin/start.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/bin/start.sh -------------------------------------------------------------------------------- /bin/stop.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/bin/stop.sh -------------------------------------------------------------------------------- /cassandra/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/cassandra/Dockerfile -------------------------------------------------------------------------------- /cassandra/docker-entrypoint.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/cassandra/docker-entrypoint.sh -------------------------------------------------------------------------------- /nutch/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/nutch/Dockerfile -------------------------------------------------------------------------------- /nutch/bootstrap.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/nutch/bootstrap.sh -------------------------------------------------------------------------------- /nutch/config/nutch-site.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/nutch/config/nutch-site.xml -------------------------------------------------------------------------------- /nutch/plugin/nutch2-index-html/.gitignore: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /nutch/plugin/nutch2-index-html/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/nutch/plugin/nutch2-index-html/LICENSE -------------------------------------------------------------------------------- /nutch/plugin/nutch2-index-html/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/nutch/plugin/nutch2-index-html/README.md -------------------------------------------------------------------------------- /nutch/plugin/nutch2-index-html/build/index-html/classes/org/apache/nutch/indexer/html/HtmlIndexingFilter.class: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/nutch/plugin/nutch2-index-html/build/index-html/classes/org/apache/nutch/indexer/html/HtmlIndexingFilter.class -------------------------------------------------------------------------------- /nutch/plugin/nutch2-index-html/build/index-html/index-html.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/nutch/plugin/nutch2-index-html/build/index-html/index-html.jar -------------------------------------------------------------------------------- /nutch/plugin/nutch2-index-html/src/plugin/index-html/build.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/nutch/plugin/nutch2-index-html/src/plugin/index-html/build.xml -------------------------------------------------------------------------------- /nutch/plugin/nutch2-index-html/src/plugin/index-html/ivy.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/nutch/plugin/nutch2-index-html/src/plugin/index-html/ivy.xml -------------------------------------------------------------------------------- /nutch/plugin/nutch2-index-html/src/plugin/index-html/plugin.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/nutch/plugin/nutch2-index-html/src/plugin/index-html/plugin.xml -------------------------------------------------------------------------------- /nutch/plugin/nutch2-index-html/src/plugin/index-html/src/java/org/apache/nutch/indexer/html/HtmlIndexingFilter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/nutch/plugin/nutch2-index-html/src/plugin/index-html/src/java/org/apache/nutch/indexer/html/HtmlIndexingFilter.java -------------------------------------------------------------------------------- /nutch/plugin/nutch2-index-html/src/plugin/index-html/src/java/org/apache/nutch/indexer/html/package.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/meabed/nutch-cassandra-docker/HEAD/nutch/plugin/nutch2-index-html/src/plugin/index-html/src/java/org/apache/nutch/indexer/html/package.html -------------------------------------------------------------------------------- /nutch/testUrls/seed.txt: -------------------------------------------------------------------------------- 1 | http://www.google.com 2 | --------------------------------------------------------------------------------