报错如下
D:javasoftwarejdkinjava.exe "-javaagent:D:loading softwareIntelliJ IDEA 2020.2.3libidea_rt.jar=62089:D:loading softwareIntelliJ IDEA 2020.2.3in" -Dfile.encoding=UTF-8 -classpath D:javasoftwarejdkjrelibcharsets.jar;D:javasoftwarejdkjrelibdeploy.jar;D:javasoftwarejdkjrelibextaccess-bridge-64.jar;D:javasoftwarejdkjrelibextcldrdata.jar;D:javasoftwarejdkjrelibextdnsns.jar;D:javasoftwarejdkjrelibextjaccess.jar;D:javasoftwarejdkjrelibextjfxrt.jar;D:javasoftwarejdkjrelibextlocaledata.jar;D:javasoftwarejdkjrelibext
ashorn.jar;D:javasoftwarejdkjrelibextsunec.jar;D:javasoftwarejdkjrelibextsunjce_provider.jar;D:javasoftwarejdkjrelibextsunmscapi.jar;D:javasoftwarejdkjrelibextsunpkcs11.jar;D:javasoftwarejdkjrelibextzipfs.jar;D:javasoftwarejdkjrelibjavaws.jar;D:javasoftwarejdkjrelibjce.jar;D:javasoftwarejdkjrelibjfr.jar;D:javasoftwarejdkjrelibjfxswt.jar;D:javasoftwarejdkjrelibjsse.jar;D:javasoftwarejdkjrelibmanagement-agent.jar;D:javasoftwarejdkjrelibplugin.jar;D:javasoftwarejdkjrelib
esources.jar;D:javasoftwarejdkjrelib
t.jar;D:javaprojectEPSpiderargetclasses;C:UsersAdministrator.m2
epositoryorgapachehttpcomponentshttpclient4.5.12httpclient-4.5.12.jar;C:UsersAdministrator.m2
epositoryorgapachehttpcomponentshttpcore4.4.13httpcore-4.4.13.jar;C:UsersAdministrator.m2
epositorycommons-loggingcommons-logging1.2commons-logging-1.2.jar;C:UsersAdministrator.m2
epositorycommons-codeccommons-codec1.11commons-codec-1.11.jar;C:UsersAdministrator.m2
epositorycommons-httpclientcommons-httpclient3.1commons-httpclient-3.1.jar;C:UsersAdministrator.m2
epositorydom4jdom4j1.6.1dom4j-1.6.1.jar;C:UsersAdministrator.m2
epositoryxml-apisxml-apis1.0.b2xml-apis-1.0.b2.jar;C:UsersAdministrator.m2
epositoryorgjsoupjsoup1.12.1jsoup-1.12.1.jar main.Main
这是第1页内容
java.util.UnknownFormatConversionException: Conversion = 'F'
at java.util.Formatter$FormatSpecifier.conversion(Formatter.java:2691)
at java.util.Formatter$FormatSpecifier.<init>(Formatter.java:2720)
at java.util.Formatter.parse(Formatter.java:2560)
at java.util.Formatter.format(Formatter.java:2501)
at java.io.PrintStream.format(PrintStream.java:970)
at java.io.PrintStream.printf(PrintStream.java:871)
at com.company.MingLuSpider.GetRequestData(MingLuSpider.java:43)
at main.Main.main(Main.java:15)
这是第2页内容
java.util.UnknownFormatConversionException: Conversion = 'F'
at java.util.Formatter$FormatSpecifier.conversion(Formatter.java:2691)
at java.util.Formatter$FormatSpecifier.<init>(Formatter.java:2720)
at java.util.Formatter.parse(Formatter.java:2560)
at java.util.Formatter.format(Formatter.java:2501)
at java.io.PrintStream.format(PrintStream.java:970)
at java.io.PrintStream.printf(PrintStream.java:871)
at com.company.MingLuSpider.GetRequestData(MingLuSpider.java:43)
at main.Main.main(Main.java:21)
这是第3页内容
Process finished with exit code -1
package main;
import com.company.MingLuSpider;
import java.io.IOException;
import java.net.URLDecoder;
public class Main {
public static void main(String[] args) throws IOException {
for (int i = 0; i < 11; i++) {
if (i == 0) {
System.out.printf("这是第%d页内容",i+1);
new MingLuSpider().GetRequestData("https://gongshang.mingluji.com/beijing/diqu/%E4%B8%9C%E5%9F%8E");
System.out.printf("%n");
} else {
System.out.printf("这是第%d页内容%n",i+1);
new MingLuSpider().GetRequestData("https://gongshang.mingluji.com/beijing/diqu/%E4%B8%9C%E5%9F%8E?page=%d" + i);
System.out.printf("%n");
}
}
}
}
package com.company;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.HttpClientBuilder;
import org.apache.http.message.BasicHeader;
import org.apache.http.util.EntityUtils;
import org.apache.http.HttpEntity;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.TimeUnit;
public class MingLuSpider {
public void MingLuSpider() {
MingLuSpider mingspider = new MingLuSpider();
}
public void GetRequestData(String url) throws IOException {
String ResponseBody ;
String ResponseInsideBody ;
String ResponseFounderBody;
try {
List headers = new ArrayList();
headers.add(new BasicHeader("User-Agent", "Mozilla/5.0(Windows NT 6.1;Win64; x64; rv:50.0) Gecko/20100101 Firefox/50.0"));
HttpClientBuilder httpClient = HttpClientBuilder.create().setDefaultHeaders(headers);
HttpGet httpGet = new HttpGet(url);
CloseableHttpResponse response = httpClient.build().execute(httpGet);
TimeUnit.SECONDS.sleep((int) (1+Math.random()*(5-1)+1));
HttpEntity httpEntity = response.getEntity();
ResponseBody = EntityUtils.toString(httpEntity, "utf-8");
Document document = Jsoup.parse(ResponseBody);
Elements getItems = document.select("td[class='views-field views-field-name']");
for (Element getItem : getItems) {
String link = "https://gongshang.mingluji.com" + getItem.select("a").attr("href");
System.out.printf("每个公司链接为:%n" + link);
HttpGet GetInsideData = new HttpGet(link);
CloseableHttpResponse ResponseInside = httpClient.build().execute(GetInsideData);
TimeUnit.SECONDS.sleep((int) (1+Math.random()*(5-1)+1));
HttpEntity httpinsideEntity = ResponseInside.getEntity();
ResponseInsideBody = EntityUtils.toString(httpinsideEntity, "utf-8");
Document DoucumentIns = Jsoup.parse(ResponseInsideBody);
String CompanyName = DoucumentIns.selectFirst("span[class='field-item'] span[itemprop='name']").text();
String FounderName=DoucumentIns.selectFirst("span[class='field-item'] span[itemprop='founder']").text();
String RelatedCompany=DoucumentIns.selectFirst("span[class='field-item'] span[itemprop='founder'] a").attr("href");
System.out.println(CompanyName);
System.out.println(FounderName);
System.out.println("https://gongshang.mingluji.com" +RelatedCompany);
HttpGet GetFounderLink = new HttpGet("https://gongshang.mingluji.com" +RelatedCompany);
CloseableHttpResponse ResponseFounderData = httpClient.build().execute(GetFounderLink);
TimeUnit.SECONDS.sleep((int) (1+Math.random()*(5-1)+1));
HttpEntity HttpFounderEntity = ResponseFounderData.getEntity();
ResponseFounderBody = EntityUtils.toString(HttpFounderEntity, "utf-8");
Document DoucumentFounderComs = Jsoup.parse(ResponseFounderBody);
System.out.println("这是创始人的相关公司数据");
Elements GetFounderComs =DoucumentFounderComs.select("div[class='views-field views-field-name'] span[class='field-content']");
System.out.println(GetFounderComs);
System.out.println("完结了");
System.out.printf("%n");
}
} catch (Exception e) {
e.printStackTrace();
}
}
public void HandlerDate(){
}
}
与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…