Webscrape

A Web 'Screen Scraper'

Calling PageScrape from C++

The easiest way to use PageScrape from C++ (or C) is to use popen(), or as it's called in Microsoft's C runtime library _popen(). This function launches the specified program and returns a handle to its Stdout which can be simply read like a file.

#include <process.h>
#include <iostream>
#include <sstream>

using namespace std;

#define popen _popen
#define pclose _pclose

int main(int argc, char* argv[])
{
string program = "pscrape.exe";
string ticker = "msft";
string url = "moneycentral.msn.com/scripts/webquote.dll?iPage=lqd&Symbol=";

url += ticker;

string regEx = "Real-time quotes.*(\\d+\\.\\d+)<";

stringstream command;
command << program << " -u\"" << url << "\" -e\"" << regEx << "\"";

FILE* fp = popen(command.str().c_str(), "r");

if (fp == NULL)
{
    cerr << "Could not launch PageScrape" << endl;
    return -1;
}

char pBuf[2048];

while (!feof(fp))
{
    if (fgets(pBuf, 2047, fp) != NULL)
      cout << pBuf;
}

pclose(fp);

return 0;
}