我是否很厚或者是否真的无法以编程方式通过某些
Java代码调用Apache Nutch？关于如何执行此操作的文档(或指南或教程)在哪里？谷歌让我失望了.所以我实际上尝试了Bing. (是的,我知道,可悲.)想法？提前致谢.
(另外,如果Nutch是一个废话,那么用Java编写的任何其他爬行器在互联网规模上都可以用实际文档证明是可靠的吗？)
解决方法
如果您查看bin / nutch脚本,您将看到它调用与您的命令对应的Java类：
@H_403_8@# figure out which class to run
if [ "$COMMAND" = "crawl" ] ; then
CLASS=org.apache.nutch.crawl.Crawl
elif [ "$COMMAND" = "inject" ] ; then
CLASS=org.apache.nutch.crawl.Injector
elif [ "$COMMAND" = "generate" ] ; then
CLASS=org.apache.nutch.crawl.Generator
elif [ "$COMMAND" = "freegen" ] ; then
CLASS=org.apache.nutch.tools.FreeGenerator
elif [ "$COMMAND" = "fetch" ] ; then
CLASS=org.apache.nutch.fetcher.Fetcher
elif [ "$COMMAND" = "fetch2" ] ; then
CLASS=org.apache.nutch.fetcher.Fetcher2
elif [ "$COMMAND" = "parse" ] ; then
CLASS=org.apache.nutch.parse.ParseSegment
elif [ "$COMMAND" = "readdb" ] ; then
CLASS=org.apache.nutch.crawl.CrawlDbReader
elif [ "$COMMAND" = "convdb" ] ; then
CLASS=org.apache.nutch.tools.compat.CrawlDbConverter
elif [ "$COMMAND" = "mergedb" ] ; then
CLASS=org.apache.nutch.crawl.CrawlDbMerger
elif [ "$COMMAND" = "readlinkdb" ] ; then
CLASS=org.apache.nutch.crawl.LinkDbReader
elif [ "$COMMAND" = "readseg" ] ; then
CLASS=org.apache.nutch.segment.SegmentReader
elif [ "$COMMAND" = "segread" ] ; then
echo "[DEPRECATED] Command 'segread' is deprecated,use 'readseg' instead."
CLASS=org.apache.nutch.segment.SegmentReader
elif [ "$COMMAND" = "mergesegs" ] ; then
CLASS=org.apache.nutch.segment.SegmentMerger
elif [ "$COMMAND" = "updatedb" ] ; then
CLASS=org.apache.nutch.crawl.CrawlDb
elif [ "$COMMAND" = "invertlinks" ] ; then
CLASS=org.apache.nutch.crawl.LinkDb
elif [ "$COMMAND" = "mergelinkdb" ] ; then
CLASS=org.apache.nutch.crawl.LinkDbMerger
elif [ "$COMMAND" = "index" ] ; then
CLASS=org.apache.nutch.indexer.Indexer
elif [ "$COMMAND" = "solrindex" ] ; then
CLASS=org.apache.nutch.indexer.solr.SolrIndexer
elif [ "$COMMAND" = "dedup" ] ; then
CLASS=org.apache.nutch.indexer.DeleteDuplicates
elif [ "$COMMAND" = "solrdedup" ] ; then
CLASS=org.apache.nutch.indexer.solr.SolrDeleteDuplicates
elif [ "$COMMAND" = "merge" ] ; then
CLASS=org.apache.nutch.indexer.IndexMerger
elif [ "$COMMAND" = "plugin" ] ; then
CLASS=org.apache.nutch.plugin.PluginRepository
elif [ "$COMMAND" = "server" ] ; then
CLASS='org.apache.nutch.searcher.DistributedSearch$Server'
else
CLASS=$COMMAND
fi
# run it
exec "$JAVA" $JAVA_HEAP_MAX $NUTCH_OPTS -classpath "$CLASSPATH" $CLASS "$@"
