Question

我目前正在对rTorrent源进行一些更改。我有以下代码：

torrent::Object
apply_to_domain(const torrent::Object& rawArgs) {

 const char * url = rawArgs.as_string().c_str();
 char buffer[50];
 snprintf(buffer, 50, "URL: %s.", url);

  return std::string(buffer);
}

我需要从url中提取域名。源代码中包含了一个regex.h，但我不确定是否可以使用它，或者我是否需要使用不同的正则表达式库。

Link to regex.h

Answer 1

“regex”实现处理的唯一内容是通配符*。（顺便说一句，我只是假设它是一个通配符，因为它是唯一被认可的字符，而且评论似乎暗示了这一点，但我实际上并没有对其进行验证。）

使用正确的正则表达式库，例如Boost.Regex。

Answer 2

//这是一个被破解的整个字符串   模式匹配。替换为
  //当TR1变得广泛时，TR1的正则表达式   可用。它适用于
  //小   字符串。

这对于提取域名不起作用。请改用Boost或VSCRT TR1。

Answer 3

请参阅command_pyroscope.cc

中的* get_active_tracker_domain *

Answer 4

在Windows中：

#include <winsock2.h>
#include <windows.h>
#include <iostream>
#include <vector>
#include <string>
#include <algorithm>
#include <cctype>
#include <locale>
#pragma comment(lib,"ws2_32.lib")
using namespace std;

string website_HTML;
locale local;

//***************************
void get_Website(char *url );
void extract_URL();
//***************************


int main ()
{
    char *url="www.bbc.com";
    get_Website(url );
    extract_URL();

    return 0;
}



//***************************
void get_Website(char *url )
{
        WSADATA wsaData;
        SOCKET Socket;
        SOCKADDR_IN SockAddr;


        int lineCount=0;
        int rowCount=0;

        struct hostent *host;
        char *get_http= new char[256];

        memset(get_http,' ', sizeof(get_http) );
        strcpy(get_http,"GET / HTTP/1.1\r\nHost: ");
        strcat(get_http,url);
        strcat(get_http,"\r\nConnection: close\r\n\r\n");

        if (WSAStartup(MAKEWORD(2,2), &wsaData) != 0) 
        {
            cout << "WSAStartup failed.\n";
            exit(0);
        }

        Socket=socket(AF_INET,SOCK_STREAM,IPPROTO_TCP);
        host = gethostbyname(url);

        SockAddr.sin_port=htons(80);
        SockAddr.sin_family=AF_INET;
        SockAddr.sin_addr.s_addr = *((unsigned long*)host->h_addr);

        cout << "Connecting to ["<< url<<"]...\n";
        if(connect(Socket,(SOCKADDR*)(&SockAddr),sizeof(SockAddr)) != 0)
        {
            cout << "Could not connect\n";
            exit(0);
        }
        cout << "Connected. (success!)\n";
        std::cout << std::flush;
        send(Socket,get_http, strlen(get_http),0 );     
        char buffer[10000];
        int nDataLength;
        int i = 0;

        while ((nDataLength = recv(Socket,buffer,10000,0)) > 0)
        {       


            while (buffer[i] >= 32 || buffer[i] == '\n' || buffer[i] == '\r') 
            {       
                website_HTML+=buffer[i];                
                i += 1;

            }

        }
        cout<<"\n"<<i<<" bytes downloaded \n\n";
        closesocket(Socket);
        WSACleanup();
        delete[] get_http;
}


void extract_URL()
{
    for (size_t i=0; i<website_HTML.length(); ++i) website_HTML[i]= tolower(website_HTML[i],local);

    std::string to_find = "http:";
    std::vector<string> extracted_website_URL;
    std::string string_to_split;
    char chr_String[1000];
    int count = 0;
    char seps[]   = "\"";
    char *token;

    cout << "\nExtracting url..  ";
    for (int j = 0; j < website_HTML.length() - to_find.length(); j++) 
    {
        if (website_HTML.substr(j, to_find.length()) == to_find)
        {
            count++;
            string_to_split=website_HTML.substr(j, to_find.length()+256);
            strcpy(chr_String , string_to_split.c_str() );
            token = strtok( chr_String, seps );
            extracted_website_URL.push_back(token);
            //cout<<website_HTML.substr(j, to_find.length()+30)<<" \n";

        }

        std::cout << "\b\\" << std::flush;       
        std::cout << "\b|" << std::flush;        
        std::cout << "\b/" << std::flush;        
        std::cout << "\b-" << std::flush;
    }


    for(j=0;j<extracted_website_URL.size();j++) cout<<extracted_website_URL[j] <<"   \n";
    cout<<"\n"<<extracted_website_URL.size()<<" URL's extracted ";
    cout<<"\n\n";

}

Answer 5

基本的东西，但可以做到这一点：

#include <regex>

std::string getHostFromUrl(const std::string & url) {
  std::regex urlRe("^.*://([^/?:]+)/?.*$");

  return std::regex_replace(url, urlRe, "$1");
}

如何从URL中提取域名？

5 个答案: