一、编写代码

下面代码实现的功能：找出html文件中的所有链接

/*
 * regex_test.cpp
 *
 */
#include <iostream>
#include <fstream>
#include <string>
#include <boost/regex.hpp>
using namespace std;
int main(int argc, char* argv[]) {
    if (argc != 2) {
        cerr << "usage: " << argv[0] << " <input_file>" << '\n';
        return 1;
    }
    ifstream fin(argv[1]);
    if (!fin) {
        cerr << "open file " << argv[1] << " failed." << '\n';
        return 1;
    }
    string content;
    char c;
    while (fin >> c) {
        content.push_back(c);
    }
    try {
        boost::regex re("href\\s*=\\s*\"([^\"]+)\"", boost::regex::icase);
        boost::sregex_token_iterator it(content.begin(), content.end(), re, 1,
                boost::match_default);
        boost::sregex_token_iterator end;
        while (it != end)
            cout << *it++ << endl;
    } catch (exception& e) {
        cerr << e.what() << '\n';
    }
}

二、编译代码

$ g++ -o"regex_test" -g3 -Wall regex_test.cpp -lboost_regex

三、运行程序 regex_test

$ ./regex_test