MCPcopy Create free account

hub / github.com/CrawlScript/WebCollector / functions

Functions510 in github.com/CrawlScript/WebCollector

MethodconnectFailed
(URI uri, SocketAddress sa, IOException ioe)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoRandomProxyCrawler.java:59
Methodcopy
(File origin, File newfile)
src/main/java/cn/edu/hfut/dmic/webcollector/util/FileUtils.java:45
MethodcopyDefault
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:216
MethodcopyMeta
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatum.java:219
MethodcopyMeta
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Page.java:477
MethodcreateGenerator
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBManager.java:214
MethodcreateGenerator
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBManager.java:223
MethodcreateGenerator
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/ram/RamDBManager.java:57
MethodcreateOkHttpClientBuilder
()
src/main/java/cn/edu/hfut/dmic/webcollector/example/AbuyunDynamicProxyRequester.java:49
MethodcreateOkHttpClientBuilder
()
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoRandomProxyCrawler.java:40
MethodcreateRequestBuilder
(CrawlDatum crawlDatum)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoPostCrawler.java:65
MethodcreateRequestBuilder
(CrawlDatum crawlDatum)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoCookieCrawler.java:26
MethodeditDistance
(String word1, String word2)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:399
Methodexecute
(CrawlDatum datum, CrawlDatums next)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoSeleniumCrawler.java:47
Methodexecute
(CrawlDatum datum, CrawlDatums next)
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/AutoParseCrawler.java:85
Methodfilter
(CrawlDatum nextItem, CrawlDatum referer)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoNextFilter.java:74
Methodfilter
(CrawlDatum nextItem, CrawlDatum referer)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/nextfilter/HashSetNextFilter.java:30
Methodfilter
(CrawlDatum datum)
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/StatusGeneratorFilter.java:7
MethodfilterByRegex
(RegexRule regexRule)
src/main/java/cn/edu/hfut/dmic/webcollector/model/Links.java:76
MethodgetBoolean
(String key)
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:61
MethodgetConf
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/CommonConfigured.java:26
MethodgetContentByDoc
(Document doc)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:463
MethodgetContentByUrl
(String url)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:481
MethodgetContentElement
()
src/main/java/cn/edu/hfut/dmic/contentextractor/News.java:79
MethodgetContentElementByUrl
(String url)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:456
MethodgetDBManager
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:417
MethodgetDBManager
返回任务管理器 @return 任务管理器
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:440
MethodgetDataSource
()
src/main/java/cn/edu/hfut/dmic/webcollector/util/MysqlHelper.java:61
MethodgetDouble
(String key)
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:68
MethodgetException
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Page.java:429
MethodgetExecutor
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:70
MethodgetExecutor
获取每个爬取任务的最大执行次数 @return 每个爬取任务的最大执行次数
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:396
MethodgetFilter
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/Generator.java:106
MethodgetGeneratorFilter
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:333
MethodgetLong
(String key)
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:65
MethodgetMaxExecuteCount
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:112
MethodgetMaxExecuteCount
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:377
MethodgetMaxReceiveSize
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:159
MethodgetMaxRedirect
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:152
MethodgetNextFilter
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:426
MethodgetNextFilter
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:453
MethodgetRegexRule
获取正则规则 @return 正则规则
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/AutoParseCrawler.java:126
MethodgetRequester
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/AutoParseCrawler.java:157
MethodgetResponse
(String url)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/net/OkHttpRequester.java:86
MethodgetResponse
(String url)
src/main/java/cn/edu/hfut/dmic/webcollector/net/CommonRequester.java:8
MethodgetSuccessCodeSet
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/net/OkHttpRequester.java:140
MethodgetTemplate
()
src/main/java/cn/edu/hfut/dmic/webcollector/util/MysqlHelper.java:53
MethodgetThreads
返回爬虫的线程数 @return 爬虫的线程数
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:404
MethodgetThreads
返回线程数 @return 线程数
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:364
MethodgetVisitor
获取Visitor @return Visitor
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/AutoParseCrawler.java:144
Methodhead
(Node node, int i)
src/main/java/cn/edu/hfut/dmic/webcollector/util/JsoupUtils.java:37
Methodhead
(Node node, int i)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:287
Methodinc
()
src/main/java/cn/edu/hfut/dmic/webcollector/util/Counter.java:37
MethodindexOf
(CrawlDatum datum)
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatums.java:201
MethodindexOf
(String url)
src/main/java/cn/edu/hfut/dmic/webcollector/model/Links.java:192
MethodinitSegmentWriter
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBManager.java:121
MethodinitSegmentWriter
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBManager.java:137
MethodinitSegmentWriter
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/ram/RamDBManager.java:116
Methodinject
(CrawlDatum datum, boolean force)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBManager.java:71
Methodinject
(CrawlDatum datum, boolean force)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBManager.java:79
Methodinject
(CrawlDatum datum, boolean force)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/ram/RamDBManager.java:71
Methodinject
(CrawlDatum datum, boolean force)
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/DBManager.java:49
MethodisAutoParse
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/VisitorMethodDispatcher.java:232
MethodisAutoParse
@return 返回是否自动抽取符合正则的链接并加入后续任务
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/AutoParseCrawler.java:108
MethodisDBExists
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBManager.java:200
MethodisDBExists
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBManager.java:209
MethodisDBExists
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/ram/RamDBManager.java:44
MethodisEmpty
()
src/main/java/cn/edu/hfut/dmic/webcollector/util/RegexRule.java:48
MethodisResumable
返回是否断点爬取 @return 是否断点爬取
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:346
Methoditerator
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatums.java:171
MethodjsonArray
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Page.java:109
Methodlist
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBManager.java:57
Methodlist
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBManager.java:55
Methodmain
(String[] args)
src/test/java/cn/edu/hfut/dmic/webcollector/util/CrawlDatumTest.java:32
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoHashSetNextFilter.java:67
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/TutorialCrawler.java:87
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoRedirectCrawler.java:67
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedAutoNewsCrawler.java:61
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedRedirectCrawler.java:66
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoExceptionCrawler.java:43
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoBingCrawler.java:137
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAutoNewsCrawler.java:60
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoTypeCrawler.java:75
Methodmain
@param args 参数 @throws Exception 异常
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoPostCrawler.java:131
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedBingCrawler.java:145
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoCookieCrawler.java:54
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoNextFilter.java:71
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedDepthCrawler.java:73
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedMatchTypeCrawler.java:100
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoMetaCrawler.java:81
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/AbuyunDynamicProxyRequester.java:66
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoSeleniumCrawler.java:45
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoRandomProxyCrawler.java:83
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedManualNewsCrawler.java:63
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoManualNewsCrawler.java:57
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/util/FileIdGenerator.java:55
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/util/MD5Utils.java:48
Methodmain
(String[] args)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:514
MethodmakeAbs
(Document doc,String url)
src/main/java/cn/edu/hfut/dmic/webcollector/util/JsoupUtils.java:31
MethodmatchContentType
判断当前Page的Http响应头的Content-Type是否符合正则 @param contentTypeRegex @return
src/main/java/cn/edu/hfut/dmic/webcollector/model/Page.java:98
← previousnext →301–400 of 510, ranked by callers