package com.example.reptile;
import org.apache.commons.lang3.StringUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.chrome.ChromeDriver;
import org.openqa.selenium.phantomjs.PhantomJSDriver;
import org.openqa.selenium.remote.DesiredCapabilities;
public class JsoupForStock {
private static final String url="http://hq.sinajs.cn/list=sz000333,sz000651,sh600690";
public static void main(String[] args) {
// chromeDriver();
phantomjs();
}
public static void chromeDriver(){
System.setProperty("webdriver.chrome.driver","E:\\BaiduNetdiskDownload\\chromedriver.exe");
WebDriver driver = new ChromeDriver();
driver.get(url);
String pageSource = driver.getPageSource();
Document jsoup = Jsoup.parse(pageSource);
String rule1="body > pre";
Elements select = jsoup.select(rule1);
String node = select.first().childNodes().get(0).toString();
String[] split = node.split(";");
for(String s : split){
String aa = s.split("=")[1];
String substring = aa.substring(1, aa.length() - 1);
String[] value = substring.split(",");
System.out.println(value[0]+"--->"+value[3]);
}
}
public static void phantomjs() {
System.setProperty("phantomjs.binary.path","E:\\BaiduNetdiskDownload\\phantomjs.exe");
DesiredCapabilities desiredCapabilities = DesiredCapabilities.phantomjs();
desiredCapabilities.setCapability("phantomjs.page.settings.userAgent", "Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:50.0) Gecko/20100101 Firefox/50.0");
desiredCapabilities.setCapability("phantomjs.page.customHeaders.User-Agent", "Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:50.0) Gecko/20100101 Firefox/50.0");
WebDriver driver = new PhantomJSDriver(desiredCapabilities);
driver.get(url);
String pageSource = driver.getPageSource();
Document jsoup = Jsoup.parse(pageSource);
String rule1="body > pre";
Elements select = jsoup.select(rule1);
String node = select.first().childNodes().get(0).toString();
String[] split = node.split(";");
for(String s : split){
if(StringUtils.isBlank(s)) continue;
String aa = s.split("=")[1];
String substring = aa.substring(1, aa.length() - 1);
String[] value = substring.split(",");
System.out.println(value[0]+"--->"+value[3]);
}
}
}
Java爬虫(Jsoup)
最后编辑于 :
©著作权归作者所有,转载或内容合作请联系作者
- 文/潘晓璐 我一进店门,熙熙楼的掌柜王于贵愁眉苦脸地迎上来,“玉大人,你说我怎么就摊上这事。” “怎么了?”我有些...
- 文/花漫 我一把揭开白布。 她就那样静静地躺着,像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上,一...
- 文/苍兰香墨 我猛地睁开眼,长吁一口气:“原来是场噩梦啊……” “哼!你这毒妇竟也来了?” 一声冷哼从身侧响起,我...
推荐阅读更多精彩内容
- 在上一篇随笔《Java爬虫系列二:使用HttpClient抓取页面HTML》中介绍了怎么使用HttpClient进...