我想用boost :: asio来阅读thml页面的源代码。
以下是我的示例代码:
#include "stdafx.h"
#include <boost/algorithm/string/replace.hpp>
#include <boost/asio.hpp>
#include <vector>
#include <string>
#include <algorithm>
#include <sstream>
#include <ostream>
int _tmain(int argc, _TCHAR* argv[])
{
std::string strHost = "www.fdj.fr";
std::string strPort = "80";
std::string strUrlPath = "https://www.fdj.fr/jeux/jeux-de-tirage/keno/resultats";
std::string strUserAgent = "Fiddler";
//std::vector<std::string> header;
unsigned int TimeOut = 5000;
//do_get(strHost, strPort, strUrlPath, header, TimeOut);
try
{
using boost::asio::ip::tcp;
boost::asio::io_service io_service;
// Get a list of endpoints corresponding to the server name.
tcp::resolver resolver(io_service);
tcp::resolver::query query(strHost, "http");
tcp::resolver::iterator endpoint_iterator = resolver.resolve(query);
tcp::resolver::iterator end;
// Try each endpoint until we successfully establish a connection.
tcp::socket socket(io_service);
boost::system::error_code error = boost::asio::error::host_not_found;
while (error && endpoint_iterator != end)
{
socket.close();
socket.connect(*endpoint_iterator++, error);
}
if (error)
throw boost::system::system_error(error);
// Form the request. We specify the "Connection: close" header so that the
// server will close the socket after transmitting the response. This will
// allow us to treat all data up until the EOF as the content.
boost::asio::streambuf request;
std::ostream request_stream(&request);
request_stream << "GET " << strUrlPath << " HTTP/1.0\r\n";
request_stream << "User-Agent: " << strUserAgent << "\r\n";
request_stream << "Host: " << strHost << "\r\n";
request_stream << "Accept: */*\r\n";
request_stream << "Connection: close\r\n\r\n";
// Send the request.
boost::asio::write(socket, request);
// Read the response status line.
boost::asio::streambuf response;
boost::asio::read_until(socket, response, "\r\n");
// Check that response is OK.
std::istream response_stream(&response);
std::string http_version;
response_stream >> http_version;
unsigned int status_code;
response_stream >> status_code;
std::string status_message;
std::getline(response_stream, status_message);
if (!response_stream || http_version.substr(0, 5) != "HTTP/")
{
std::cout << "Invalid response\n";
//return 1;
}
/*if (status_code != 200)
{
std::cout << "Response returned with status code " << status_code << "\n";
//return 1;
}*/
// Read the response headers, which are terminated by a blank line.
boost::asio::read_until(socket, response, "\r\n\r\n");
// Process the response headers.
std::string header;
while (std::getline(response_stream, header) && header != "\r")
std::cout << header << "\n";
std::cout << "\n";
// Write whatever content we already have to output.
if (response.size() > 0)
std::cout << &response;
// Read until EOF, writing data to output as we go.
while (boost::asio::read(socket, response,
boost::asio::transfer_at_least(1), error))
std::cout << &response;
if (error != boost::asio::error::eof)
throw boost::system::system_error(error);
char a;
std::cin>>a ;
}
catch (std::exception& e)
{
std::cout << "Exception: " << e.what() << "\n";
}
return 0;
}
发出的请求是:
GET https://www.fdj.fr/jeux/jeux-de-tirage/keno/resultats HTTP/1.0
User-Agent: Fiddler
Host: www.fdj.fr
Accept: */*
Connection: close
如果我运行我的程序,我有:
如果我在fiddler中运行此请求(通过复制/粘贴),我有:
return code=200
(已接受)并且页面已加载!
任何人都知道为什么我有这个301错误? 我认为这是由于boost :: asio参数,但是哪个?
非常感谢,
致以最诚挚的问候,
Nixeus
答案 0 :(得分:3)
这里发生了两件事:
您正在尝试通过纯HTTP加载HTTPS URI。这会导致301重定向,使您通过HTTPS返回原始页面。这表明托管服务器不通过不安全的HTTP提供此资源。
您的HTTP实施不支持重定向。您正在提出请求并发送第一个回复。完整的HTTP客户端将检查301响应并使用301的位置标头中的URI重试。
要解决此问题,您需要实现对TLS / HTTPS的支持,理想情况是HTTP重定向。