hadoop分布式网络爬虫

[{"title":"（ 59 个子文件 70KB ） hadoop分布式网络爬虫","children":[{"title":"CrawlerDriver-master","children":[{"title":"a.jpg <span style='color:#111;'> 2.41KB </span>","children":null,"spread":false},{"title":"bin","children":[{"title":"org","children":[{"title":"crawler","children":[{"title":"crawlerdriver","children":[{"title":"CrawlerRecordReader$NewLineReader.class <span style='color:#111;'> 3.35KB </span>","children":null,"spread":false},{"title":"CrawlerDriver.class <span style='color:#111;'> 2.54KB </span>","children":null,"spread":false},{"title":"CrawlerRecordReader.class <span style='color:#111;'> 5.53KB </span>","children":null,"spread":false},{"title":"CrawlerDriver$CrawlerReducer.class <span style='color:#111;'> 2.70KB </span>","children":null,"spread":false},{"title":"CrawlerDriver$InverseMapper.class <span style='color:#111;'> 2.04KB </span>","children":null,"spread":false},{"title":"HostPartitioner.class <span style='color:#111;'> 1.40KB </span>","children":null,"spread":false},{"title":"CrawlerInputFormat.class <span style='color:#111;'> 1.94KB </span>","children":null,"spread":false}],"spread":true},{"title":"htmltoxmldriver","children":[{"title":"HtmlToXMLDriver.class <span style='color:#111;'> 2.11KB </span>","children":null,"spread":false},{"title":"HtmlToXMLDriver$HtmlToXMLMapper.class <span style='color:#111;'> 2.10KB </span>","children":null,"spread":false}],"spread":true},{"title":"parserdriver","children":[{"title":"ParserInputFormat.class <span style='color:#111;'> 1.09KB </span>","children":null,"spread":false},{"title":"ParserDriver$ParserMapper.class <span style='color:#111;'> 3.96KB </span>","children":null,"spread":false},{"title":"ParserPartitioner.class <span style='color:#111;'> 1.41KB </span>","children":null,"spread":false},{"title":"ParserDriver.class <span style='color:#111;'> 2.13KB </span>","children":null,"spread":false},{"title":"ParserRecordReader.class <span style='color:#111;'> 4.89KB </span>","children":null,"spread":false}],"spread":true},{"title":"mergedriver","children":[{"title":"MergeDriver.class <span style='color:#111;'> 2.00KB </span>","children":null,"spread":false},{"title":"HashPartitioner.class <span style='color:#111;'> 1.40KB </span>","children":null,"spread":false},{"title":"MergeDriver$IdentityMapper.class <span style='color:#111;'> 1.85KB </span>","children":null,"spread":false},{"title":"MergeDriver$MergeDocReducer.class <span style='color:#111;'> 2.32KB </span>","children":null,"spread":false}],"spread":true},{"title":"util","children":[{"title":"TextArrayWritable.class <span style='color:#111;'> 606B </span>","children":null,"spread":false},{"title":"OutLinksWritable.class <span style='color:#111;'> 3.39KB </span>","children":null,"spread":false},{"title":"DocumentWritable.class <span style='color:#111;'> 3.16KB </span>","children":null,"spread":false},{"title":"Parser.class <span style='color:#111;'> 1.78KB </span>","children":null,"spread":false},{"title":"HttpDownloader.class <span style='color:#111;'> 3.53KB </span>","children":null,"spread":false},{"title":"Downloader.class <span style='color:#111;'> 2.29KB </span>","children":null,"spread":false},{"title":"MetaParser.class <span style='color:#111;'> 1.17KB </span>","children":null,"spread":false}],"spread":true},{"title":"optimizerdriver","children":[{"title":"OptimizerDriver$OptimizerReducer.class <span style='color:#111;'> 2.92KB </span>","children":null,"spread":false},{"title":"OptimizerRecordReader.class <span style='color:#111;'> 5.32KB </span>","children":null,"spread":false},{"title":"OptimizerInputFormat.class <span style='color:#111;'> 1.19KB </span>","children":null,"spread":false},{"title":"OptimizerDriver.class <span style='color:#111;'> 2.45KB </span>","children":null,"spread":false},{"title":"OptimizerDriver$OptimizerMapper.class <span style='color:#111;'> 2.95KB </span>","children":null,"spread":false},{"title":"OptimizerPartitioner.class <span style='color:#111;'> 1.43KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}],"spread":true},{"title":"README2.md <span style='color:#111;'> 71B </span>","children":null,"spread":false},{"title":"src","children":[{"title":"org","children":[{"title":"crawler","children":[{"title":"crawlerdriver","children":[{"title":"CrawlerRecordReader.java <span style='color:#111;'> 8.24KB </span>","children":null,"spread":false},{"title":"CrawlerDriver.java <span style='color:#111;'> 2.83KB </span>","children":null,"spread":false},{"title":"CrawlerInputFormat.java <span style='color:#111;'> 1.08KB </span>","children":null,"spread":false},{"title":"HostPartitioner.java <span style='color:#111;'> 834B </span>","children":null,"spread":false}],"spread":true},{"title":"htmltoxmldriver","children":[{"title":"HtmlToXMLDriver.java <span style='color:#111;'> 1.81KB </span>","children":null,"spread":false}],"spread":true},{"title":"parserdriver","children":[{"title":"ParserPartitioner.java <span style='color:#111;'> 615B </span>","children":null,"spread":false},{"title":"ParserInputFormat.java <span style='color:#111;'> 603B </span>","children":null,"spread":false},{"title":"ParserRecordReader.java <span style='color:#111;'> 4.11KB </span>","children":null,"spread":false},{"title":"ParserDriver.java <span style='color:#111;'> 3.47KB </span>","children":null,"spread":false}],"spread":true},{"title":"mergedriver","children":[{"title":"MergeDriver.java <span style='color:#111;'> 2.03KB </span>","children":null,"spread":false},{"title":"HashPartitioner.java <span style='color:#111;'> 576B </span>","children":null,"spread":false}],"spread":true},{"title":"util","children":[{"title":"MetaParser.java <span style='color:#111;'> 684B </span>","children":null,"spread":false},{"title":"TextArrayWritable.java <span style='color:#111;'> 312B </span>","children":null,"spread":false},{"title":"DocumentWritable.java <span style='color:#111;'> 3.02KB </span>","children":null,"spread":false},{"title":"OutLinksWritable.java <span style='color:#111;'> 2.41KB </span>","children":null,"spread":false},{"title":"HttpDownloader.java <span style='color:#111;'> 1.98KB </span>","children":null,"spread":false},{"title":"Parser.java <span style='color:#111;'> 1.17KB </span>","children":null,"spread":false},{"title":"Downloader.java <span style='color:#111;'> 1.28KB </span>","children":null,"spread":false}],"spread":true},{"title":"optimizerdriver","children":[{"title":"OptimizerDriver.java <span style='color:#111;'> 3.04KB </span>","children":null,"spread":false},{"title":"OptimizerPartitioner.java <span style='color:#111;'> 584B </span>","children":null,"spread":false},{"title":"OptimizerInputFormat.java <span style='color:#111;'> 688B </span>","children":null,"spread":false},{"title":"OptimizerRecordReader.java <span style='color:#111;'> 3.87KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}],"spread":true},{"title":".project <span style='color:#111;'> 418B </span>","children":null,"spread":false},{"title":".classpath <span style='color:#111;'> 15.73KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 617B </span>","children":null,"spread":false},{"title":".gitattributes <span style='color:#111;'> 378B </span>","children":null,"spread":false}],"spread":true}],"spread":true}]