Пишу парсер google wordpress сайтов (usa-интернет) для спама.

yoweb · 17 Jan 2015

Парсер google 2015 с++ qt

Парсер google выдачи 2015
Скрин проги:
http://saveimg.ru/show-image.php?id=13ec33561533027ec05d31acfcb92caa

-Парсит за раз до 500 сайтов.
-может понадобиться для парсинга seo блогов для ручного спама по комментариям. Запросом "add to comment"
-можно парсить админки wordpress, запросом "inurl"wp-admin"

Инструкция:
1)Нажимаем вверху слева кнопку "start.."
2)программа проходит выдачу google по запросу до 500 сайтов, далее останавливается
3)Нажимаем кнопку writeToFile, резльтаты пишутся в файл links.txt.

Исходный код c++ qt
для компиляции в qt-creator (windows,linux,mac os)
Создано в qt creator 5.
untitled.pro

#-------------------------------------------------
#
# Project created by QtCreator 2015-01-17T21:44:55
#
#-------------------------------------------------

QT += core gui network webkit webkitwidgets webview

greaterThan(QT_MAJOR_VERSION, 4): QT += widgets

TARGET = untitled
TEMPLATE = app

SOURCES += main.cpp\
mainwindow.cpp \
methods.cpp

HEADERS += mainwindow.h \
methods.h

FORMS += mainwindow.ui
Click to expand...

MainWindow.h

#ifndef MAINWINDOW_H
#define MAINWINDOW_H

#include <QMainWindow>
#include "methods.h"

namespace Ui {
class MainWindow;
}

class MainWindow : public QMainWindow
{
Q_OBJECT

public:
explicit MainWindow(QWidget *parent = 0);
~MainWindow();

public slots:
void startLoad();
void start();
void insertQuery();
void grab();
void nextPage();
void writeToFile();
void update();
private:
Ui::MainWindow *ui;
};

#endif // MAINWINDOW_H
Click to expand...

methods.h

#ifndef METHODS_H
#define METHODS_H
#include "QWebFrame"
#include "QString"
#include "QWebView"

class methods
{
public:
methods();

public slots:
static void full(QWebFrame * frame,QString query);
static void buttonClick(QWebView * webView,int x,int y);
static QStringList grabPage(QWebFrame * frame);
static QStringList pageMenu(QWebFrame * frame);
static void writeToFile(QStringList masLinks);
};

#endif // METHODS_H
Click to expand...

main.cpp

#include "mainwindow.h"
#include <QApplication>

int main(int argc, char *argv[])
{
QApplication a(argc, argv);
MainWindow w;
w.show();

return a.exec();
}
Click to expand...

mainwindow.cpp

#include "mainwindow.h"
#include "ui_mainwindow.h"
#include "QWebView"
#include "QtWebKitWidgets"
#include "QDebug"
#include <QTimer>

int urlCurrentI = 0;
QStringList linksFromParsing;
bool startProgram = false;
bool startGrab = false;

MainWindow::MainWindow(QWidget *parent) :
QMainWindow(parent),
ui(new Ui::MainWindow)
{
ui->setupUi(this);

ui->webView->load(QUrl("https://www.google.com/advanced_search"));

connect(ui->webView, SIGNAL(loadFinished(bool)), this, SLOT(startLoad()));
connect(ui->pushButton, SIGNAL(clicked(bool)), this, SLOT(insertQuery()));
connect(ui->pushButton_3, SIGNAL(clicked(bool)), this, SLOT(grab()));
connect(ui->pushButton_4, SIGNAL(clicked(bool)), this, SLOT(nextPage()));
connect(ui->pushButton_5, SIGNAL(clicked(bool)), this, SLOT(writeToFile()));

ui->lineEdit->setText(QString("\"add to comment\""));

QTimer *timer = new QTimer(this);
connect(timer, SIGNAL(timeout()), this, SLOT(update()));
timer->start(5000);
}
void MainWindow::update(){
if (startProgram == true) {
qDebug() << "startProgram";
if (startGrab == false) {
grab();
} else {
nextPage();
}
}
}

void MainWindow::startLoad(){
ui->lineEdit_2->setText(ui->webView->url().toString().toUtf8());
}
void MainWindow::start(){
ui->webView->load(QUrl("https://www.google.com/advanced_search"));
}
void MainWindow::grab(){
linksFromParsing << methods::grabPage(ui->webView->page()->currentFrame());
//qDebug() << linksFromParsing;
ui->label_3->setText(QString::number(linksFromParsing.count()));
startGrab = true;
}
void MainWindow::insertQuery(){
methods::full(ui->webView->page()->currentFrame(),QString(ui->lineEdit->text().toUtf8()));
startProgram = true;
}
void MainWindow::nextPage(){
methods:ageMenu(ui->webView->page()->currentFrame());
startGrab = false;
}
void MainWindow::writeToFile(){
methods::writeToFile(linksFromParsing);
}

MainWindow::~MainWindow()
{
delete ui;
}
Click to expand...

methods.cpp

#include "methods.h"
#include "QWebElement"
#include "QWebElementCollection"
#include "QString"
#include "QWebFrame"
#include "QMouseEvent"
#include "QEvent"
#include "QCoreApplication"
#include <QFile>
#include <QStringList>
#include <QTextStream>
#include <cstdlib>
#include <iostream>

methods::methods()
{
}

void methods::full(QWebFrame * frame,QString query)
{
QWebElementCollection collection = frame->findAllElements("input");

int i = 0;

foreach (QWebElement element, collection)
{

if (element.attribute("class") == "jfk-textinput") {
i++;

if (i == 1) {
element.setAttribute("value",query);
}
}

}

foreach (QWebElement element, collection)
{
//qDebug() << element.attribute("class");

if (element.attribute("class") == "jfk-button jfk-button-action _JQ") {

element.evaluateJavaScript("this.click()");
}
}

}

QStringList methods::grabPage(QWebFrame * frame)
{
QStringList masLinks;

QWebElementCollection collection = frame->findAllElements("h3");

foreach (QWebElement element, collection)
{
//qDebug() << element.attribute("class");
if (element.attribute("class") == "r") {

QWebElementCollection collection1 = element.findAll("a");
foreach (QWebElement element, collection1)
{
QString link = element.attribute("href").remove("/url?q=").toUtf8();

int i;
bool iter = false;
int symbol;
for(i=0; i<link.count(); i++) {
if (link == '&' && link[i+1] == 's' && link[i+2] == 'a') {
break;
}
}
link.remove(i,link.count());
masLinks << link;
}
//element.setAttribute("value",query);
}
}
return masLinks;
}

QStringList methods:ageMenu(QWebFrame * frame)
{
QStringList urls;
QWebElementCollection collection = frame->findAllElements("span");
foreach (QWebElement element, collection) {

if (element.attribute("style") == "display:block;margin-left:53px") {
qDebug() << element.toPlainText();
element.evaluateJavaScript("this.click()");
}
}

return urls;
}

void methods::buttonClick(QWebView * webView,int x,int y){

QMouseEvent event0(QEvent::MouseButtonPress, QPointF(x,y), Qt::LeftButton,Qt::LeftButton, Qt::NoModifier);
QCoreApplication::sendEvent(webView, &event0);
QMouseEvent event1(QEvent::MouseButtonRelease, QPointF(x,y), Qt::LeftButton,Qt::LeftButton, Qt::NoModifier);
QCoreApplication::sendEvent(webView, &event1);
}
void methods::writeToFile(QStringList masLinks){
// write data
QFile fOut("links.txt");
if (fOut.open(QFile::WriteOnly | QFile::Text)) {
QTextStream s(&fOut);
for (int i = 0; i < masLinks.size(); ++i)
s << masLinks.at(i) << '\n';
}
fOut.close();
}

Click to expand...

mainwindow.ui

<?xml version="1.0" encoding="UTF-8"?>
<ui version="4.0">
<class>MainWindow</class>
<widget class="QMainWindow" name="MainWindow">
<property name="geometry">
<rect>
<x>0</x>
<y>0</y>
<width>1023</width>
<height>510</height>
</rect>
</property>
<property name="windowTitle">
<string>Google Parser</string>
</property>
<widget class="QWidget" name="centralWidget">
<widget class="QWebView" name="webView">
<property name="geometry">
<rect>
<x>10</x>
<y>80</y>
<width>921</width>
<height>361</height>
</rect>
</property>
<property name="url">
<url>
<string>about:blank</string>
</url>
</property>
</widget>
<widget class="QLineEdit" name="lineEdit">
<property name="geometry">
<rect>
<x>100</x>
<y>0</y>
<width>831</width>
<height>31</height>
</rect>
</property>
</widget>
<widget class="QPushButton" name="pushButton">
<property name="geometry">
<rect>
<x>10</x>
<y>0</y>
<width>85</width>
<height>27</height>
</rect>
</property>
<property name="text">
<string>Start parsing</string>
</property>
</widget>
<widget class="QLineEdit" name="lineEdit_2">
<property name="geometry">
<rect>
<x>10</x>
<y>40</y>
<width>921</width>
<height>31</height>
</rect>
</property>
</widget>
<widget class="QPushButton" name="pushButton_3">
<property name="geometry">
<rect>
<x>940</x>
<y>10</y>
<width>71</width>
<height>27</height>
</rect>
</property>
<property name="text">
<string>ParseList</string>
</property>
</widget>
<widget class="QLabel" name="label">
<property name="geometry">
<rect>
<x>10</x>
<y>450</y>
<width>541</width>
<height>101</height>
</rect>
</property>
<property name="text">
<string>TextLabel</string>
</property>
</widget>
<widget class="QPushButton" name="pushButton_4">
<property name="geometry">
<rect>
<x>940</x>
<y>40</y>
<width>71</width>
<height>27</height>
</rect>
</property>
<property name="text">
<string>next</string>
</property>
</widget>
<widget class="QLabel" name="label_2">
<property name="geometry">
<rect>
<x>934</x>
<y>110</y>
<width>81</width>
<height>20</height>
</rect>
</property>
<property name="text">
<string>currentPage</string>
</property>
</widget>
<widget class="QPushButton" name="pushButton_5">
<property name="geometry">
<rect>
<x>930</x>
<y>150</y>
<width>85</width>
<height>27</height>
</rect>
</property>
<property name="text">
<string>WriteToFile</string>
</property>
</widget>
<widget class="QLabel" name="label_3">
<property name="geometry">
<rect>
<x>934</x>
<y>210</y>
<width>81</width>
<height>20</height>
</rect>
</property>
<property name="text">
<string>count of links</string>
</property>
</widget>
</widget>
<widget class="QMenuBar" name="menuBar">
<property name="geometry">
<rect>
<x>0</x>
<y>0</y>
<width>1023</width>
<height>27</height>
</rect>
</property>
</widget>
<widget class="QToolBar" name="mainToolBar">
<attribute name="toolBarArea">
<enum>TopToolBarArea</enum>
</attribute>
<attribute name="toolBarBreak">
<bool>false</bool>
</attribute>
</widget>
<widget class="QStatusBar" name="statusBar"/>
</widget>
<layoutdefault spacing="6" margin="11"/>
<customwidgets>
<customwidget>
<class>QWebView</class>
<extends>QWidget</extends>
<header>QtWebKitWidgets/QWebView</header>
</customwidget>
</customwidgets>
<resources/>
<connections/>
</ui>
Click to expand...

При вводе запроса "add to comment" вывести сайты с формами комментариев спарсено 125 сайтов

http://en.forums.wordpress.com/topic/changing-background-color-of-comment-boxes
https://www.facebook.com/dctfHomeToTheSpinnersNotebook/posts/771742562844971
http://fmforums.com/forum/topic/90773-structuring-tables-erd-question/
http://forum.kooboo.com/yaf_postst4409_Spam-Comment-KooBoo-4-x--434-record.aspx
http://forums.steampowered.com/forums/showthread.php%3Fp%3D19134451
http://commentart.com/users/signin
http://askubuntu.com/questions/448575/apt-get-crashes-with-relocation-error-libapt-pkg-so-4-12
http://www.discmainland.ca/englrevs.htm
http://forum.bittorrent.com/topic/31586-synologynastentative-solution-to-resolve-cannot-accept-eula-cannot-see-folders-in-add-folder-view/
http://www.amazon.com/Nutribiotic-Defenseplus-Tablets-250-Count/dp/B00014DRNW
http://www.hotukdeals.com/vouchers/rakuten.co.uk
http://spanish.fansshare.com/gallery/photos/197538/Reon-Kadena-Add-To-Comment-Liv-Tyler-Hair/
http://www.redd-monitor.org/2012/05/01/the-story-of-redd-a-real-solution-to-deforestation/
Click to expand...

Useful Searches

Пишу парсер google wordpress сайтов (usa-интернет) для спама.

yoweb Banned