MCPcopy Create free account

hub / github.com/CrawlScript/WebCollector / functions

Functions510 in github.com/CrawlScript/WebCollector

↓ 2 callersMethodgetString
(String key)
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:58
↓ 2 callersMethoditerator
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Links.java:71
↓ 2 callersMethodmetaAsLong
(String key)
src/main/java/cn/edu/hfut/dmic/webcollector/model/MetaGetter.java:11
↓ 2 callersMethodopen
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/DBManager.java:45
↓ 2 callersMethodopenFetchDatabase
(String crawlPath)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:63
↓ 2 callersMethodopenLinkDatabase
(String crawlPath)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:67
↓ 2 callersMethodremoveSuccessCode
(int successCode)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/net/OkHttpRequester.java:43
↓ 2 callersMethodsetConf
(Configuration conf)
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configured.java:25
↓ 2 callersMethodsetExecuteTime
(long executeTime)
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatum.java:168
↓ 2 callersMethodsetNextFilter
(NextFilter nextFilter)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:430
↓ 2 callersMethodstrSim
(String a, String b)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:262
↓ 2 callersMethodtestInject
(DBManager dbManager)
src/test/java/cn/edu/hfut/dmic/webcollector/util/DBManagerTest.java:18
↓ 2 callersMethodtoString
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatum.java:256
↓ 2 callersMethodtoString
()
src/main/java/cn/edu/hfut/dmic/contentextractor/News.java:74
↓ 2 callersMethodwriteDatum
(RocksDB rocksDB,CrawlDatum datum)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:97
↓ 2 callersMethodwriteDatum
(Database database,CrawlDatum datum)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBUtils.java:46
↓ 1 callersMethodaddBySelector
添加ele中,满足选择器的元素中的链接 选择器cssSelector必须定位到具体的超链接 例如我们想抽取id为content的div中的所有超链接,这里 就要将cssSelector定义为div[id=content] a
src/main/java/cn/edu/hfut/dmic/webcollector/model/Links.java:114
↓ 1 callersMethodaddFetchItem
(FetchItem item)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:104
↓ 1 callersMethodaddFromElement
(Element ele)
src/main/java/cn/edu/hfut/dmic/webcollector/model/Links.java:93
↓ 1 callersMethodaddNegative
添加一个反正则规则 @param negativeregex @return 自身
src/main/java/cn/edu/hfut/dmic/webcollector/util/RegexRule.java:101
↓ 1 callersMethodaddSocksProxy
(String ip, int port)
src/main/java/cn/edu/hfut/dmic/webcollector/net/Proxies.java:70
↓ 1 callersMethodafterStop
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:151
↓ 1 callersMethodbuildMessage
(Visitor visitor, Method method)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Visitor.java:88
↓ 1 callersMethodclean
()
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:69
↓ 1 callersMethodclear
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:96
↓ 1 callersMethodclear
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Links.java:183
↓ 1 callersMethodclear
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/DBManager.java:34
↓ 1 callersMethodclose
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/ram/RamGenerator.java:51
↓ 1 callersMethodclose
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/Generator.java:104
↓ 1 callersMethodcloseGenerator
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:156
↓ 1 callersMethodcloseSegmentWriter
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/SegmentWriter.java:36
↓ 1 callersMethodcode
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatum.java:136
↓ 1 callersMethodcomputeInfo
(Node node)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:73
↓ 1 callersMethodcomputeScore
(Element tag)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:122
↓ 1 callersMethodcomputeVar
(ArrayList<Integer> data)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:129
↓ 1 callersMethodcopy
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:95
↓ 1 callersMethodcrawlDatum
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Page.java:437
↓ 1 callersMethodcreateBingUrl
construct the Bing Search url by the search keyword and the pageIndex @param keyword @param pageIndex @return the constructed url @throws Exception
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoRedirectCrawler.java:79
↓ 1 callersMethodcreateBingUrl
construct the Bing Search url by the search keyword and the pageIndex @param keyword @param pageIndex @return the constructed url @throws Exception
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedRedirectCrawler.java:78
↓ 1 callersMethodcreateBingUrl
construct the Bing Search url by the search keyword and the pageIndex @param keyword @param pageIndex @return the constructed url @throws Exception
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoBingCrawler.java:152
↓ 1 callersMethodcreateBingUrl
construct the Bing Search url by the search keyword and the pageIndex @param keyword @param pageIndex @return the constructed url @throws Exception
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedBingCrawler.java:157
↓ 1 callersMethodcreateDataSource
(String url, String username, String password, int initialSize, int maxPoolSize)
src/main/java/cn/edu/hfut/dmic/webcollector/util/MysqlHelper.java:41
↓ 1 callersMethodcreateDefaultDBConfig
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBUtils.java:39
↓ 1 callersMethodcreateOkHttpClientBuilder
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/net/OkHttpRequester.java:58
↓ 1 callersMethodcreateRequestBuilder
(CrawlDatum crawlDatum)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/net/OkHttpRequester.java:68
↓ 1 callersMethodcreateSuccessCodeSet
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/net/OkHttpRequester.java:48
↓ 1 callersMethoddestroyFetchDatabase
(String crawlPath)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:72
↓ 1 callersMethoddestroyLinkDatabase
(String crawlPath)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:76
↓ 1 callersMethoddispatch
(Page page, CrawlDatums next)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/VisitorMethodDispatcher.java:199
↓ 1 callersMethoddump
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:119
↓ 1 callersMethodfetchAll
抓取当前所有任务,会阻塞到爬取完成 @throws IOException 异常
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:304
↓ 1 callersMethodfilter
if the crawler visit http://a.com/ and detect http://a.com/b.html then nextItem = http://a.com/b.html and referer = http://a.com/ if you want to filte
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/NextFilter.java:38
↓ 1 callersMethodfilter
return datum if you want to generate datum return null if you want to filter datum @param datum @return
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/GeneratorFilter.java:13
↓ 1 callersMethodgenerate
()
src/main/java/cn/edu/hfut/dmic/webcollector/util/FileIdGenerator.java:42
↓ 1 callersMethodgetAutoDetectImg
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:182
↓ 1 callersMethodgetByIndex
(List<T> list, int index)
src/main/java/cn/edu/hfut/dmic/webcollector/util/ListUtils.java:7
↓ 1 callersMethodgetConnectTimeout
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:119
↓ 1 callersMethodgetContentByHtml
(String html)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:469
↓ 1 callersMethodgetContentElementByHtml
(String html)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:442
↓ 1 callersMethodgetCrawldbPath
(String crawlPath)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:54
↓ 1 callersMethodgetDate
(Element contentElement)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:234
↓ 1 callersMethodgetDefaultCookie
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:173
↓ 1 callersMethodgetDefaultUserAgent
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:166
↓ 1 callersMethodgetExecuteInterval
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:130
↓ 1 callersMethodgetFetchItem
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:112
↓ 1 callersMethodgetMethodAccessibility
(Method method)
src/main/java/cn/edu/hfut/dmic/webcollector/util/ReflectionUtils.java:27
↓ 1 callersMethodgetMethodByCode
(Page page)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/VisitorMethodDispatcher.java:170
↓ 1 callersMethodgetMethodByType
(Page page)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/VisitorMethodDispatcher.java:175
↓ 1 callersMethodgetMethodByUrlRegex
(Page page)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/VisitorMethodDispatcher.java:180
↓ 1 callersMethodgetMethodByUrlRegexRule
(Page page)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/VisitorMethodDispatcher.java:189
↓ 1 callersMethodgetMethodDeclaration
(Method method)
src/main/java/cn/edu/hfut/dmic/webcollector/util/ReflectionUtils.java:7
↓ 1 callersMethodgetNews
()
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:171
↓ 1 callersMethodgetNewsByHtml
(String html)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:495
↓ 1 callersMethodgetNewsByUrl
(String url)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:507
↓ 1 callersMethodgetOrDefault
(String key, T defaultValue)
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:77
↓ 1 callersMethodgetReadTimeout
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:126
↓ 1 callersMethodgetThreadKiller
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:137
↓ 1 callersMethodgetTime
()
src/main/java/cn/edu/hfut/dmic/contentextractor/News.java:66
↓ 1 callersMethodgetTime
(Element contentElement)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:200
↓ 1 callersMethodgetTitle
()
src/main/java/cn/edu/hfut/dmic/contentextractor/News.java:43
↓ 1 callersMethodgetTitle
(final Element contentElement)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:280
↓ 1 callersMethodgetTitleByEditDistance
(Element contentElement)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:341
↓ 1 callersMethodgetTopN
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:102
↓ 1 callersMethodgetTotalGenerate
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/Generator.java:100
↓ 1 callersMethodgetUrl
()
src/main/java/cn/edu/hfut/dmic/contentextractor/News.java:35
↓ 1 callersMethodgetWaitThreadEndTime
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:145
↓ 1 callersMethodguessEncodingByNutch
(byte[] content)
src/main/java/cn/edu/hfut/dmic/webcollector/util/CharsetDetector.java:45
↓ 1 callersMethodincrExecuteCount
(int count)
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatum.java:121
↓ 1 callersMethodinitLastId
()
src/main/java/cn/edu/hfut/dmic/webcollector/util/FileIdGenerator.java:30
↓ 1 callersMethodinitSegmentWriter
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/SegmentWriter.java:30
↓ 1 callersMethodinject
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:72
↓ 1 callersMethodinjectForcedSeeds
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:76
↓ 1 callersMethodisDBExists
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/DBManager.java:32
↓ 1 callersMethodisEmpty
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatums.java:196
↓ 1 callersMethodjsonObject
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Page.java:105
↓ 1 callersMethodkeyOrValueToStr
(byte[] keyOrValue)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:116
↓ 1 callersMethodlcs
(String x, String y)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:376
↓ 1 callersMethodlocation
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatum.java:145
↓ 1 callersMethodmatchUrlRegexRule
判断当前Page的URL是否和输入正则规则匹配 @param urlRegexRule @return
src/main/java/cn/edu/hfut/dmic/webcollector/model/Page.java:78
↓ 1 callersMethodmd5
(byte[] original)
src/main/java/cn/edu/hfut/dmic/webcollector/util/MD5Utils.java:32
← previousnext →101–200 of 510, ranked by callers