Qt5 爬取某小说网页并使用正则提取正文

爬取的目标网页

网页源码


运行示例

项目结构

源代码

robotsandre.h

#ifndef ROBOTSANDRE_H
#define ROBOTSANDRE_H

#endif // ROBOTSANDRE_H

#include<QCoreApplication>
#include<QRegularExpression>
#include<QRegularExpressionMatch>
#include<QRegularExpressionMatchIterator>
#include<QString>
#include<QDebug>
#include <QCoreApplication>
#include<QtCore>
#include<QNetworkAccessManager>
#include<QUrl>
#include<QNetworkRequest>
#include<QNetworkReply>
#include<QObject>

QString Robots(QString url);//爬取页面
QString RegularExpression(QString HTML,QString re);//正则提取爬到的页面

robotsandre.cpp

#include "robotsandre.h"

QString Robots(QString url)//爬取页面
{
    QUrl URL=url;
    QNetworkAccessManager manager;
    QEventLoop Loop;
    QNetworkReply *reply=manager.get(QNetworkRequest(URL));
    QObject::connect(reply,SIGNAL(finished()),&Loop,SLOT(quit()));
    Loop.exec();
    QString HtmlText=reply->readAll();
    return HtmlText;
}

QString RegularExpression(QString  HTML,QString re)//正则提取爬到的页面正文
{
    QString TextAfterRe="          ";
    QRegularExpression Re(re);
    QRegularExpressionMatchIterator Matchs=Re.globalMatch(HTML);
    QRegularExpressionMatch match=Matchs.next();
    TextAfterRe=TextAfterRe+match.captured("bt");//标题
    TextAfterRe=TextAfterRe+"\n"+"\n";

    while(Matchs.hasNext()==true)
    {
        match=Matchs.next();
        QString temp=match.captured("zw");
        TextAfterRe=TextAfterRe+temp;
    }
    return TextAfterRe;
}

提示:请勿将此文章内容用于非法用途,此文仅供学习参考.