知乎爬虫最新版

java写的爬虫多线程爬取知乎用户详细信息,方便简单,重要的是这是最新的

package com.crawl;

import com.crawl.proxy.ProxyHttpClient;
import com.crawl.zhihu.ZhiHuHttpClient;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/**
 * 爬虫入口
 */
public class Main {
    private static Logger logger = LoggerFactory.getLogger（Main.class）;
    public static void main（String args []）{
        ProxyHttpClient.getInstance（）.startCrawl（）;
        ZhiHuHttpClient.getInstance（）.startCrawl（）;
    }
}

 属性            大小     日期    时间   名称
----------- ---------  ---------- -----  ----

     文件       1226  2018-07-10 20:03  zhihu-crawler-2.0\.classpath

     文件         94  2018-07-09 20:32  zhihu-crawler-2.0\.gitignore

     文件        565  2018-07-10 20:03  zhihu-crawler-2.0\.project

     文件        138  2018-07-10 20:36  zhihu-crawler-2.0\.settings\org.eclipse.core.resources.prefs

     文件        243  2018-07-10 20:03  zhihu-crawler-2.0\.settings\org.eclipse.jdt.core.prefs

     文件         90  2018-07-10 20:03  zhihu-crawler-2.0\.settings\org.eclipse.m2e.core.prefs

    .......     80693  2018-07-09 20:32  zhihu-crawler-2.0\lib\accessors-smart-1.1.jar

    .......     53231  2018-07-09 20:32  zhihu-crawler-2.0\lib\asm-5.0.3.jar

    .......    263965  2018-07-09 20:32  zhihu-crawler-2.0\lib\commons-codec-1.9.jar

    .......     61829  2018-07-09 20:32  zhihu-crawler-2.0\lib\commons-logging-1.2.jar

    .......     45024  2018-07-09 20:32  zhihu-crawler-2.0\lib\hamcrest-core-1.3.jar

    .......    727567  2018-07-09 20:32  zhihu-crawler-2.0\lib\httpclient-4.5.jar

    .......    322234  2018-07-09 20:32  zhihu-crawler-2.0\lib\httpcore-4.4.1.jar

    .......    207058  2018-07-09 20:32  zhihu-crawler-2.0\lib\json-path-2.2.0.jar

    .......    120501  2018-07-09 20:32  zhihu-crawler-2.0\lib\json-smart-2.2.1.jar

    .......    293671  2018-07-09 20:32  zhihu-crawler-2.0\lib\jsoup-1.7.2.jar

    .......    245039  2018-07-09 20:32  zhihu-crawler-2.0\lib\junit-4.11.jar

    .......    481535  2018-07-09 20:32  zhihu-crawler-2.0\lib\log4j-1.2.16.jar

    .......    703265  2018-07-09 20:32  zhihu-crawler-2.0\lib\mysql-connector-java-5.1.6.jar

    .......     28688  2018-07-09 20:32  zhihu-crawler-2.0\lib\slf4j-api-1.7.6.jar

    .......      8869  2018-07-09 20:32  zhihu-crawler-2.0\lib\slf4j-log4j12-1.7.6.jar

    .......     10249  2018-07-09 20:32  zhihu-crawler-2.0\License

     文件       1943  2018-07-09 20:32  zhihu-crawler-2.0\pom.xml

     文件       5630  2018-07-09 20:32  zhihu-crawler-2.0\README.md

    .......       404  2018-07-09 20:32  zhihu-crawler-2.0\src\main\java\com\crawl\core\dao\baseDao.java

     文件       1871  2018-07-09 20:32  zhihu-crawler-2.0\src\main\java\com\crawl\core\dao\ConnectionManager.java

    .......      2590  2018-07-09 20:32  zhihu-crawler-2.0\src\main\java\com\crawl\core\httpclient\AbstractHttpClient.java

    .......       299  2018-07-09 20:32  zhihu-crawler-2.0\src\main\java\com\crawl\core\httpclient\IHttpClient.java

    .......       195  2018-07-09 20:32  zhihu-crawler-2.0\src\main\java\com\crawl\core\parser\DetailPageParser.java

    .......       179  2018-07-09 20:32  zhihu-crawler-2.0\src\main\java\com\crawl\core\parser\ListPageParser.java

............此处省略217个文件信息