[boost] 利用boost.asio提取网页中的网址

参考网址: http://blog.jobbole.com/82628/

文件名：a.cpp

/*
	功能: 演示了利用boost中的asio和regex提取网页中符合指定格式的网址
	环境: Fedora20
	编译: g++ -o a a.cpp -Wall -Os -std=c++11 -lboost_system -lboost_regex

	说明: 默认Fedora20中未安装boost库, 可通过在终端执行"yum install boost-devel"来安装
*/

#include <iostream>
#include <exception>
#include <boost/regex.hpp>	// 正则表达式库
#include <boost/asio.hpp>	// asio网络库

using namespace std;
using namespace boost;

set<string> get_strings(istream& is, regex pat)	// 从is中取出所有的网址
{
	set<string> res;
	smatch m;
	for(string s; getline(is, s); )
	{
		if(regex_search(s, m, pat))
			res.insert(m[0]);
	}
	return res;
}

void connect_to_file(iostream& s, const string& server, const string& file)
{
	if(!s)
		throw runtime_error{"can't connect\n"};

	s << "GET " << "http://" + server + "/" + file << " HTTP/1.0\r\n";
	s << "Host: " << server << "\r\n";
	s << "Accept: */*\r\n";
	s << "Connection: close\r\n\r\n";

	string http_version;
	unsigned int status_code;
	s >> http_version >> status_code;
	cout << http_version << ", " << status_code << endl;

	string status_message;
	getline(s, status_message);
	if(!s || http_version.substr(0, 5) != "HTTP/")
		throw runtime_error{"Invalid response"};

	if(status_code != 200)
	{
		char buf[64] = {0};
		sprintf(buf, "Response returned with status code: %d", status_code);
		throw runtime_error{buf};
	}

	string header;
	while(getline(s, header) && header != "\r")
		;
}

int main()
{
	try
	{
		string server = "www.stroustrup.com";
		asio::ip::tcp::iostream s {server, "http"};
		connect_to_file(s, server, "C++.html");

		regex pat{R"((http://)?www([./#\+-]\w*)+)"};	// 网址正则表达式
		for (auto x: get_strings(s, pat))
			cout << x << endl;
	}
	catch(std::exception& e)	// boost中也有exception, 所以这里要写全
	{
		cout << "Exception: " << e.what() << endl;
		return -1;
	}
	return 0;
}