Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/CrawlScript/WebCollector
/ functions
Functions
510 in github.com/CrawlScript/WebCollector
⨍
Functions
510
◇
Types & classes
97
Method
connectFailed
(URI uri, SocketAddress sa, IOException ioe)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoRandomProxyCrawler.java:59
Method
copy
(File origin, File newfile)
src/main/java/cn/edu/hfut/dmic/webcollector/util/FileUtils.java:45
Method
copyDefault
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:216
Method
copyMeta
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatum.java:219
Method
copyMeta
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Page.java:477
Method
createGenerator
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBManager.java:214
Method
createGenerator
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBManager.java:223
Method
createGenerator
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/ram/RamDBManager.java:57
Method
createOkHttpClientBuilder
()
src/main/java/cn/edu/hfut/dmic/webcollector/example/AbuyunDynamicProxyRequester.java:49
Method
createOkHttpClientBuilder
()
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoRandomProxyCrawler.java:40
Method
createRequestBuilder
(CrawlDatum crawlDatum)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoPostCrawler.java:65
Method
createRequestBuilder
(CrawlDatum crawlDatum)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoCookieCrawler.java:26
Method
editDistance
(String word1, String word2)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:399
Method
execute
(CrawlDatum datum, CrawlDatums next)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoSeleniumCrawler.java:47
Method
execute
(CrawlDatum datum, CrawlDatums next)
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/AutoParseCrawler.java:85
Method
filter
(CrawlDatum nextItem, CrawlDatum referer)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoNextFilter.java:74
Method
filter
(CrawlDatum nextItem, CrawlDatum referer)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/nextfilter/HashSetNextFilter.java:30
Method
filter
(CrawlDatum datum)
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/StatusGeneratorFilter.java:7
Method
filterByRegex
(RegexRule regexRule)
src/main/java/cn/edu/hfut/dmic/webcollector/model/Links.java:76
Method
getBoolean
(String key)
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:61
Method
getConf
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/CommonConfigured.java:26
Method
getContentByDoc
(Document doc)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:463
Method
getContentByUrl
(String url)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:481
Method
getContentElement
()
src/main/java/cn/edu/hfut/dmic/contentextractor/News.java:79
Method
getContentElementByUrl
(String url)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:456
Method
getDBManager
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:417
Method
getDBManager
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
Method
getDataSource
()
src/main/java/cn/edu/hfut/dmic/webcollector/util/MysqlHelper.java:61
Method
getDouble
(String key)
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:68
Method
getException
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Page.java:429
Method
getExecutor
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:70
Method
getExecutor
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
Method
getFilter
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/Generator.java:106
Method
getGeneratorFilter
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:333
Method
getLong
(String key)
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:65
Method
getMaxExecuteCount
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:112
Method
getMaxExecuteCount
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:377
Method
getMaxReceiveSize
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:159
Method
getMaxRedirect
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:152
Method
getNextFilter
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:426
Method
getNextFilter
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:453
Method
getRegexRule
获取正则规则 @return 正则规则
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/AutoParseCrawler.java:126
Method
getRequester
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/AutoParseCrawler.java:157
Method
getResponse
(String url)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/net/OkHttpRequester.java:86
Method
getResponse
(String url)
src/main/java/cn/edu/hfut/dmic/webcollector/net/CommonRequester.java:8
Method
getSuccessCodeSet
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/net/OkHttpRequester.java:140
Method
getTemplate
()
src/main/java/cn/edu/hfut/dmic/webcollector/util/MysqlHelper.java:53
Method
getThreads
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
Method
getThreads
返回线程数 @return 线程数
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:364
Method
getVisitor
获取Visitor @return Visitor
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/AutoParseCrawler.java:144
Method
head
(Node node, int i)
src/main/java/cn/edu/hfut/dmic/webcollector/util/JsoupUtils.java:37
Method
head
(Node node, int i)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:287
Method
inc
()
src/main/java/cn/edu/hfut/dmic/webcollector/util/Counter.java:37
Method
indexOf
(CrawlDatum datum)
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatums.java:201
Method
indexOf
(String url)
src/main/java/cn/edu/hfut/dmic/webcollector/model/Links.java:192
Method
initSegmentWriter
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBManager.java:121
Method
initSegmentWriter
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBManager.java:137
Method
initSegmentWriter
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/ram/RamDBManager.java:116
Method
inject
(CrawlDatum datum, boolean force)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBManager.java:71
Method
inject
(CrawlDatum datum, boolean force)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBManager.java:79
Method
inject
(CrawlDatum datum, boolean force)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/ram/RamDBManager.java:71
Method
inject
(CrawlDatum datum, boolean force)
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/DBManager.java:49
Method
isAutoParse
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/VisitorMethodDispatcher.java:232
Method
isAutoParse
@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
Method
isDBExists
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBManager.java:200
Method
isDBExists
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBManager.java:209
Method
isDBExists
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/ram/RamDBManager.java:44
Method
isEmpty
()
src/main/java/cn/edu/hfut/dmic/webcollector/util/RegexRule.java:48
Method
isResumable
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
Method
iterator
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatums.java:171
Method
jsonArray
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Page.java:109
Method
list
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBManager.java:57
Method
list
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBManager.java:55
Method
main
(String[] args)
src/test/java/cn/edu/hfut/dmic/webcollector/util/CrawlDatumTest.java:32
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoHashSetNextFilter.java:67
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/TutorialCrawler.java:87
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoRedirectCrawler.java:67
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedAutoNewsCrawler.java:61
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedRedirectCrawler.java:66
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoExceptionCrawler.java:43
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoBingCrawler.java:137
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAutoNewsCrawler.java:60
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoTypeCrawler.java:75
Method
main
@param args 参数 @throws Exception 异常
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoPostCrawler.java:131
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedBingCrawler.java:145
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoCookieCrawler.java:54
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoNextFilter.java:71
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedDepthCrawler.java:73
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedMatchTypeCrawler.java:100
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoMetaCrawler.java:81
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/AbuyunDynamicProxyRequester.java:66
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoSeleniumCrawler.java:45
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoRandomProxyCrawler.java:83
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoAnnotatedManualNewsCrawler.java:63
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/example/DemoManualNewsCrawler.java:57
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/util/FileIdGenerator.java:55
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/webcollector/util/MD5Utils.java:48
Method
main
(String[] args)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:514
Method
makeAbs
(Document doc,String url)
src/main/java/cn/edu/hfut/dmic/webcollector/util/JsoupUtils.java:31
Method
matchContentType
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
← previous
next →
301–400 of 510, ranked by callers