c++ 获取一个网页下所有子链接

g++ get.cpp -std=c++11 -stdlib=libc++

获取网址下子链接的地址：

--------

#include <iostream>
#include <fstream>
#include <string>
#include <regex>
#include <cstdlib>

using namespace std;

int main(){

	string begin("<a href=\"");
	string end("\">");
	
	regex reg("><a href=\"([^(/|\?)].*?)(?=\">)");
	string baseurl("http://www.opensource.apple.com/source/CF/CF-476.14/");

	ifstream in("./a.html");

	string line;
	smatch file_match;
	while (getline(in,line)) {
		while (regex_search(line,file_match,reg)) {
			for (size_t i = 1;i < file_match.size(); i ++) {
				string name = file_match[i];
				string url(baseurl + name + "?txt");
				//cout<<name<<endl;	
				string cmd("curl ");
				cmd.append(url);
				cmd.append(" -o ");
				cmd.append(name);
				system(cmd.c_str());
			}
			line = file_match.suffix().str();
		}
	}



	return 0;
}