-
大小: 1.4MB文件類型: .rar金幣: 2下載: 0 次發(fā)布日期: 2023-09-21
- 語(yǔ)言: 其他
- 標(biāo)簽: 網(wǎng)絡(luò)爬蟲(chóng)??
資源簡(jiǎn)介
包括知識(shí)介紹和最全面的網(wǎng)絡(luò)爬蟲(chóng)源代碼,分開(kāi)講解,更加細(xì)致入微,非常好的代碼,很實(shí)用

代碼片段和文件信息
package?com.cn.simepu.auto.crawling.config;
import?java.io.File;
import?java.io.FileInputStream;
import?java.util.Properties;
public?class?SystemConfig?{
private?int?poolSize?=?0;?//?線程池最大數(shù)
private?int?threadSize?=?0;?//?線程池最大線程數(shù)
private?int?uriLength?=?0;//URI鏈接的最大長(zhǎng)度
private?long?sleepTime?=?0L;?//?一次循環(huán)休眠時(shí)間
private?String?siteSource?=?null;?//?配置文件來(lái)源
private?String[]?indexOfs?=?null;//?要截取的特殊字符
private?String?regFileType?=?null;//?要保存的文件格式
private?String?siteFilePath?=?null;?//?配置文件路徑
private?String?saveRootPath?=?null;?//?保存的根目錄
private?static?boolean?isWhileCrawl=false;?//是否循環(huán)抓取
private?static?SystemConfig?systemConfig?=?null;?//?當(dāng)前系統(tǒng)配置實(shí)例
protected?static?final?String?CONFIG_PREFIX?=?“config_“;?//?配置文件屬性前綴
protected?static?final?String?configPath?=?“autocrawling_system.properties“;?//?配置文件名字
private?String?dbUserName?=?null;
private?String?dbUserPass?=?null;
private?String?dbDriver?=?null;
private?String?dbConnection?=?null;
public?synchronized?static?SystemConfig?init()?{
if?(systemConfig?==?null)?{
systemConfig?=?new?SystemConfig();
systemConfig.loadSystemConfig();
}
return?systemConfig;
}
protected?void?loadSystemConfig()?{
try?{
File?file?=?new?File(configPath);
//?URL?resource?=
//?super.getClass().getClassLoader().getResource(configPath);
//?if?(resource?!=?null)?{
//?Properties?patternFile?=?new?Properties();
//?patternFile.load(resource.openStream());
//?loadSystemConfigParmater(patternFile);
//?}else{
//?return;
//?}
if?(file?!=?null)?{
Properties?patternFile?=?new?Properties();
patternFile.load(new?FileInputStream(file));
loadSystemConfigParmater(patternFile);
}?else?{
return;
}
}?catch?(Exception?ex)?{}
}
protected?void?loadSystemConfigParmater(Properties?patternFile)?{
try?{
String?isWhileCrawlType=patternFile.getProperty(“config_isWhileCrawl“);
isWhileCrawl?=?isWhileCrawlType.equals(“true“)???true:?false;
this.dbDriver?=?patternFile.getProperty(CONFIG_PREFIX?+?“dbDriver“);
this.dbUserName?=?patternFile.getProperty(CONFIG_PREFIX?+?“dbUserName“);
this.dbUserPass?=?patternFile.getProperty(CONFIG_PREFIX?+?“dbUserPass“);
this.siteSource?=?patternFile.getProperty(CONFIG_PREFIX?+?“siteSource“);
this.regFileType?=?patternFile.getProperty(CONFIG_PREFIX?+?“regFileType“);
this.saveRootPath?=?patternFile.getProperty(CONFIG_PREFIX?+?“saveRootPath“);
this.dbConnection?=?patternFile.getProperty(CONFIG_PREFIX?+?“dbConnection“);
this.siteFilePath?=?patternFile.getProperty(CONFIG_PREFIX?+?“siteFilePath“);
this.indexOfs?=?patternFile.getProperty(CONFIG_PREFIX?+?“indexOfs“).split(““);
this.poolSize?=?Integer.parseInt(patternFile.getProperty(CONFIG_PREFIX?+?“poolSize“));
this.sleepTime?=?Long.parseLong(patternFile.getProperty(CONFIG_PREFIX?+?“sleepTime“));
this.uriLength?=?Integer.parseInt(patternFile.getProperty(CONFI
?屬性????????????大小?????日期????時(shí)間???名稱
-----------?---------??----------?-----??----
?????文件????????344??2010-07-01?10:46??AutoCrawling\.classpath
?????文件????????365??2010-07-01?10:46??AutoCrawling\.fatjar
?????文件????????388??2010-06-30?18:28??AutoCrawling\.project
?????文件????????923??2010-08-02?15:38??AutoCrawling\autocrawling_example.properties
?????文件???????1426??2010-07-30?09:32??AutoCrawling\autocrawling_system.properties
?????文件?????582656??2010-08-02?15:33??AutoCrawling\crawl.log
?????文件????????363??2010-08-02?15:29??AutoCrawling\bin\autocrawling_http_parser.properties
?????文件???????1305??2010-05-27?10:16??AutoCrawling\bin\log4j.xm
?????文件???????6109??2010-08-02?15:00??AutoCrawling\bin\com\cn\simepu\auto\crawling\config\SystemConfig.class
?????文件???????3631??2010-08-02?14:47??AutoCrawling\bin\com\cn\simepu\auto\crawling\config\ThreadPoolConfig.class
?????文件???????2070??2010-08-02?14:47??AutoCrawling\bin\com\cn\simepu\auto\crawling\db\DBHelper.class
?????文件???????1334??2010-08-02?14:47??AutoCrawling\bin\com\cn\simepu\auto\crawling\main\MainClass.class
?????文件???????9340??2010-08-02?14:47??AutoCrawling\bin\com\cn\simepu\auto\crawling\main\ProgramEntry.class
?????文件???????3801??2010-08-02?14:47??AutoCrawling\bin\com\cn\simepu\auto\crawling\thread\MyThread.class
?????文件???????7564??2010-08-02?14:47??AutoCrawling\bin\com\cn\simepu\auto\crawling\thread\MyThreadPool.class
?????文件???????3531??2010-08-02?14:47??AutoCrawling\bin\com\cn\simepu\auto\crawling\thread\MyThreadPoolControl.class
?????文件???????3300??2010-08-02?15:27??AutoCrawling\bin\com\cn\simepu\auto\crawling\util\BloomFilter.class
?????文件???????6796??2010-08-02?14:47??AutoCrawling\bin\com\cn\simepu\auto\crawling\util\FileManager.class
?????文件???????3109??2010-08-02?14:47??AutoCrawling\bin\com\cn\simepu\auto\crawling\util\Tools.class
?????文件???????3951??2010-08-02?14:47??AutoCrawling\bin\com\cn\simepu\auto\crawling\util\UrlExtractor.class
?????文件???????5626??2010-06-30?17:42??AutoCrawling\lib\jocky-ant.jar
?????文件?????515600??2010-06-30?18:03??AutoCrawling\lib\jocky.jar
?????文件?????352291??2010-06-30?17:32??AutoCrawling\lib\log4j-1.2.9.jar
?????文件?????583286??2010-06-30?17:32??AutoCrawling\lib\sqljdbc.jar
?????文件????????363??2010-08-02?15:29??AutoCrawling\src\autocrawling_http_parser.properties
?????文件???????1305??2010-05-27?10:16??AutoCrawling\src\log4j.xm
?????文件???????5922??2010-08-02?15:00??AutoCrawling\src\com\cn\simepu\auto\crawling\config\SystemConfig.java
?????文件???????2604??2010-05-27?09:54??AutoCrawling\src\com\cn\simepu\auto\crawling\config\ThreadPoolConfig.java
?????文件???????1518??2010-05-20?20:29??AutoCrawling\src\com\cn\simepu\auto\crawling\db\DBHelper.java
?????文件????????420??2010-07-01?09:45??AutoCrawling\src\com\cn\simepu\auto\crawling\main\MainClass.java
............此處省略35個(gè)文件信息
- 上一篇:USB-PPI編程電纜驅(qū)動(dòng)
- 下一篇:j2me飛行射擊demo
評(píng)論
共有 條評(píng)論