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
↓ 2 callers
Method
getString
(String key)
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:58
↓ 2 callers
Method
iterator
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Links.java:71
↓ 2 callers
Method
metaAsLong
(String key)
src/main/java/cn/edu/hfut/dmic/webcollector/model/MetaGetter.java:11
↓ 2 callers
Method
open
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/DBManager.java:45
↓ 2 callers
Method
openFetchDatabase
(String crawlPath)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:63
↓ 2 callers
Method
openLinkDatabase
(String crawlPath)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:67
↓ 2 callers
Method
removeSuccessCode
(int successCode)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/net/OkHttpRequester.java:43
↓ 2 callers
Method
setConf
(Configuration conf)
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configured.java:25
↓ 2 callers
Method
setExecuteTime
(long executeTime)
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatum.java:168
↓ 2 callers
Method
setNextFilter
(NextFilter nextFilter)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:430
↓ 2 callers
Method
strSim
(String a, String b)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:262
↓ 2 callers
Method
testInject
(DBManager dbManager)
src/test/java/cn/edu/hfut/dmic/webcollector/util/DBManagerTest.java:18
↓ 2 callers
Method
toString
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatum.java:256
↓ 2 callers
Method
toString
()
src/main/java/cn/edu/hfut/dmic/contentextractor/News.java:74
↓ 2 callers
Method
writeDatum
(RocksDB rocksDB,CrawlDatum datum)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:97
↓ 2 callers
Method
writeDatum
(Database database,CrawlDatum datum)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBUtils.java:46
↓ 1 callers
Method
addBySelector
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 callers
Method
addFetchItem
(FetchItem item)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:104
↓ 1 callers
Method
addFromElement
(Element ele)
src/main/java/cn/edu/hfut/dmic/webcollector/model/Links.java:93
↓ 1 callers
Method
addNegative
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 callers
Method
addSocksProxy
(String ip, int port)
src/main/java/cn/edu/hfut/dmic/webcollector/net/Proxies.java:70
↓ 1 callers
Method
afterStop
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:151
↓ 1 callers
Method
buildMessage
(Visitor visitor, Method method)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Visitor.java:88
↓ 1 callers
Method
clean
()
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:69
↓ 1 callers
Method
clear
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:96
↓ 1 callers
Method
clear
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Links.java:183
↓ 1 callers
Method
clear
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/DBManager.java:34
↓ 1 callers
Method
close
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/ram/RamGenerator.java:51
↓ 1 callers
Method
close
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/Generator.java:104
↓ 1 callers
Method
closeGenerator
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:156
↓ 1 callers
Method
closeSegmentWriter
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/SegmentWriter.java:36
↓ 1 callers
Method
code
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatum.java:136
↓ 1 callers
Method
computeInfo
(Node node)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:73
↓ 1 callers
Method
computeScore
(Element tag)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:122
↓ 1 callers
Method
computeVar
(ArrayList<Integer> data)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:129
↓ 1 callers
Method
copy
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:95
↓ 1 callers
Method
crawlDatum
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Page.java:437
↓ 1 callers
Method
createBingUrl
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 callers
Method
createBingUrl
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 callers
Method
createBingUrl
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 callers
Method
createBingUrl
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 callers
Method
createDataSource
(String url, String username, String password, int initialSize, int maxPoolSize)
src/main/java/cn/edu/hfut/dmic/webcollector/util/MysqlHelper.java:41
↓ 1 callers
Method
createDefaultDBConfig
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/berkeley/BerkeleyDBUtils.java:39
↓ 1 callers
Method
createOkHttpClientBuilder
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/net/OkHttpRequester.java:58
↓ 1 callers
Method
createRequestBuilder
(CrawlDatum crawlDatum)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/net/OkHttpRequester.java:68
↓ 1 callers
Method
createSuccessCodeSet
()
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/net/OkHttpRequester.java:48
↓ 1 callers
Method
destroyFetchDatabase
(String crawlPath)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:72
↓ 1 callers
Method
destroyLinkDatabase
(String crawlPath)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:76
↓ 1 callers
Method
dispatch
(Page page, CrawlDatums next)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/VisitorMethodDispatcher.java:199
↓ 1 callers
Method
dump
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:119
↓ 1 callers
Method
fetchAll
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 callers
Method
filter
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 callers
Method
filter
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 callers
Method
generate
()
src/main/java/cn/edu/hfut/dmic/webcollector/util/FileIdGenerator.java:42
↓ 1 callers
Method
getAutoDetectImg
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:182
↓ 1 callers
Method
getByIndex
(List<T> list, int index)
src/main/java/cn/edu/hfut/dmic/webcollector/util/ListUtils.java:7
↓ 1 callers
Method
getConnectTimeout
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:119
↓ 1 callers
Method
getContentByHtml
(String html)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:469
↓ 1 callers
Method
getContentElementByHtml
(String html)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:442
↓ 1 callers
Method
getCrawldbPath
(String crawlPath)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:54
↓ 1 callers
Method
getDate
(Element contentElement)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:234
↓ 1 callers
Method
getDefaultCookie
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:173
↓ 1 callers
Method
getDefaultUserAgent
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:166
↓ 1 callers
Method
getExecuteInterval
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:130
↓ 1 callers
Method
getFetchItem
()
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/Fetcher.java:112
↓ 1 callers
Method
getMethodAccessibility
(Method method)
src/main/java/cn/edu/hfut/dmic/webcollector/util/ReflectionUtils.java:27
↓ 1 callers
Method
getMethodByCode
(Page page)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/VisitorMethodDispatcher.java:170
↓ 1 callers
Method
getMethodByType
(Page page)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/VisitorMethodDispatcher.java:175
↓ 1 callers
Method
getMethodByUrlRegex
(Page page)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/VisitorMethodDispatcher.java:180
↓ 1 callers
Method
getMethodByUrlRegexRule
(Page page)
src/main/java/cn/edu/hfut/dmic/webcollector/fetcher/VisitorMethodDispatcher.java:189
↓ 1 callers
Method
getMethodDeclaration
(Method method)
src/main/java/cn/edu/hfut/dmic/webcollector/util/ReflectionUtils.java:7
↓ 1 callers
Method
getNews
()
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:171
↓ 1 callers
Method
getNewsByHtml
(String html)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:495
↓ 1 callers
Method
getNewsByUrl
(String url)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:507
↓ 1 callers
Method
getOrDefault
(String key, T defaultValue)
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:77
↓ 1 callers
Method
getReadTimeout
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:126
↓ 1 callers
Method
getThreadKiller
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:137
↓ 1 callers
Method
getTime
()
src/main/java/cn/edu/hfut/dmic/contentextractor/News.java:66
↓ 1 callers
Method
getTime
(Element contentElement)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:200
↓ 1 callers
Method
getTitle
()
src/main/java/cn/edu/hfut/dmic/contentextractor/News.java:43
↓ 1 callers
Method
getTitle
(final Element contentElement)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:280
↓ 1 callers
Method
getTitleByEditDistance
(Element contentElement)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:341
↓ 1 callers
Method
getTopN
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:102
↓ 1 callers
Method
getTotalGenerate
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/Generator.java:100
↓ 1 callers
Method
getUrl
()
src/main/java/cn/edu/hfut/dmic/contentextractor/News.java:35
↓ 1 callers
Method
getWaitThreadEndTime
()
src/main/java/cn/edu/hfut/dmic/webcollector/conf/Configuration.java:145
↓ 1 callers
Method
guessEncodingByNutch
(byte[] content)
src/main/java/cn/edu/hfut/dmic/webcollector/util/CharsetDetector.java:45
↓ 1 callers
Method
incrExecuteCount
(int count)
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatum.java:121
↓ 1 callers
Method
initLastId
()
src/main/java/cn/edu/hfut/dmic/webcollector/util/FileIdGenerator.java:30
↓ 1 callers
Method
initSegmentWriter
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/SegmentWriter.java:30
↓ 1 callers
Method
inject
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:72
↓ 1 callers
Method
injectForcedSeeds
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawler/Crawler.java:76
↓ 1 callers
Method
isDBExists
()
src/main/java/cn/edu/hfut/dmic/webcollector/crawldb/DBManager.java:32
↓ 1 callers
Method
isEmpty
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatums.java:196
↓ 1 callers
Method
jsonObject
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/Page.java:105
↓ 1 callers
Method
keyOrValueToStr
(byte[] keyOrValue)
src/main/java/cn/edu/hfut/dmic/webcollector/plugin/rocks/RocksDBUtils.java:116
↓ 1 callers
Method
lcs
(String x, String y)
src/main/java/cn/edu/hfut/dmic/contentextractor/ContentExtractor.java:376
↓ 1 callers
Method
location
()
src/main/java/cn/edu/hfut/dmic/webcollector/model/CrawlDatum.java:145
↓ 1 callers
Method
matchUrlRegexRule
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 callers
Method
md5
(byte[] original)
src/main/java/cn/edu/hfut/dmic/webcollector/util/MD5Utils.java:32
← previous
next →
101–200 of 510, ranked by callers