connect.c

harvest是一个下载html网页得机器人

/***************************************************************************
 *                                  _   _ ____  _     
 *  Project                     ___| | | |  _ \| |    
 *                             / __| | | | |_) | |    
 *                            | (__| |_| |  _ <| |___ 
 *                             \___|\___/|_| \_\_____|
 *
 * Copyright (C) 1998 - 2003, Daniel Stenberg, <[e-mail]>, et al.
 *
 * This software is licensed as described in the file COPYING, which
 * you should have received as part of this distribution. The terms
 * are also available at http://curl.haxx.se/docs/copyright.html.
 * 
 * You may opt to use, copy, modify, merge, publish, distribute and/or sell
 * copies of the Software, and permit persons to whom the Software is
 * furnished to do so, under the terms of the COPYING file.
 *
 * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
 * KIND, either express or implied.
 *
 * $Id: connect.c,v 1.65 2003/10/18 20:34:33 bagder Exp $
 ***************************************************************************/

#include "setup.h"

#ifndef WIN32
/* headers for non-win32 */
#include <sys/time.h>
#include <sys/socket.h>
#include <sys/types.h>
#include <sys/ioctl.h>
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#ifdef HAVE_NETDB_H
#include <netdb.h>
#endif
#ifdef HAVE_FCNTL_H
#include <fcntl.h>
#endif
#ifdef HAVE_NETINET_IN_H
#include <netinet/in.h>
#endif
#ifdef HAVE_ARPA_INET_H
#include <arpa/inet.h>
#endif
#ifdef HAVE_STDLIB_H
#include <stdlib.h> /* required for free() prototype, without it, this crashes
                       on macos 68K */
#endif
#ifdef	VMS
#include <in.h>
#include <inet.h>
#endif

#endif
#include <stdio.h>
#include <errno.h>
#include <string.h>

#ifndef TRUE
#define TRUE 1
#define FALSE 0
#endif

#ifdef WIN32
#define HAVE_IOCTLSOCKET
#include <windows.h>
#define EINPROGRESS WSAEINPROGRESS
#define EWOULDBLOCK WSAEWOULDBLOCK
#define EISCONN     WSAEISCONN
#define ENOTSOCK    WSAENOTSOCK
#define ECONNREFUSED WSAECONNREFUSED
#endif

#include "urldata.h"
#include "sendf.h"
#include "if2ip.h"

/* The last #include file should be: */
#ifdef CURLDEBUG
#include "memdebug.h"
#endif

int Curl_ourerrno(void)
{
#ifdef WIN32
  return (int)GetLastError();
#else
  return errno;
#endif
}

/*************************************************************************
 * Curl_nonblock
 *
 * Description:
 *  Set the socket to either blocking or non-blocking mode.
 */

int Curl_nonblock(int sockfd,    /* operate on this */
                  int nonblock   /* TRUE or FALSE */)
{
#undef SETBLOCK
#ifdef HAVE_O_NONBLOCK
  /* most recent unix versions */
  int flags;

  flags = fcntl(sockfd, F_GETFL, 0);
  if (TRUE == nonblock)
    return fcntl(sockfd, F_SETFL, flags | O_NONBLOCK);
  else
    return fcntl(sockfd, F_SETFL, flags & (~O_NONBLOCK));
#define SETBLOCK 1
#endif

#ifdef HAVE_FIONBIO
  /* older unix versions */
  int flags;

  flags = nonblock;
  return ioctl(sockfd, FIONBIO, &flags);
#define SETBLOCK 2
#endif

#ifdef HAVE_IOCTLSOCKET
  /* Windows? */
  int flags;
  flags = nonblock;
  return ioctlsocket(sockfd, FIONBIO, &flags);
#define SETBLOCK 3
#endif

#ifdef HAVE_IOCTLSOCKET_CASE
  /* presumably for Amiga */
  return IoctlSocket(sockfd, FIONBIO, (long)nonblock);
#define SETBLOCK 4
#endif

#ifdef HAVE_SO_NONBLOCK
  /* BeOS */
  long b = nonblock ? 1 : 0;
  return setsockopt(sockfd, SOL_SOCKET, SO_NONBLOCK, &b, sizeof(b));
#define SETBLOCK 5
#endif

#ifdef HAVE_DISABLED_NONBLOCKING
  return 0; /* returns success */
#define SETBLOCK 6
#endif

#ifndef SETBLOCK
#error "no non-blocking method was found/used/set"
#endif
}

/*
 * waitconnect() returns:
 * 0    fine connect
 * -1   select() error
 * 1    select() timeout
 * 2    select() returned with an error condition
 */
static
int waitconnect(int sockfd, /* socket */
                int timeout_msec)
{
  fd_set fd;
  fd_set errfd;
  struct timeval interval;
  int rc;

  /* now select() until we get connect or timeout */
  FD_ZERO(&fd);
  FD_SET(sockfd, &fd);

  FD_ZERO(&errfd);
  FD_SET(sockfd, &errfd);

  interval.tv_sec = timeout_msec/1000;
  timeout_msec -= interval.tv_sec*1000;

  interval.tv_usec = timeout_msec*1000;

  rc = select(sockfd+1, NULL, &fd, &errfd, &interval);
  if(-1 == rc)
    /* error, no connect here, try next */
    return -1;
  
  else if(0 == rc)
    /* timeout, no connect today */
    return 1;

  if(FD_ISSET(sockfd, &errfd))
    /* error condition caught */
    return 2;

  /* we have a connect! */
  return 0;
}

static CURLcode bindlocal(struct connectdata *conn,
                          int sockfd)
{
#ifdef HAVE_INET_NTOA

  struct SessionHandle *data = conn->data;

  /*************************************************************
   * Select device to bind socket to
   *************************************************************/
  if (strlen(data->set.device)<255) {
    struct sockaddr_in sa;
    struct Curl_dns_entry *h=NULL;
    size_t size;
    char myhost[256] = "";
    in_addr_t in;
    int rc;

    /* First check if the given name is an IP address */
    in=inet_addr(data->set.device);
      
    if((in == CURL_INADDR_NONE) &&
       Curl_if2ip(data->set.device, myhost, sizeof(myhost))) {
      /*
       * We now have the numerical IPv4-style x.y.z.w in the 'myhost' buffer
       */
      rc = Curl_resolv(conn, myhost, 0, &h);
      if(rc == 1)
        rc = Curl_wait_for_resolv(conn, &h);

    }
    else {
      if(strlen(data->set.device)>1) {
        /*
         * This was not an interface, resolve the name as a host name
         * or IP number
         */
        rc = Curl_resolv(conn, data->set.device, 0, &h);
        if(rc == 1)
          rc = Curl_wait_for_resolv(conn, &h);

        if(h)
          /* we know data->set.device is shorter than the myhost array */
          strcpy(myhost, data->set.device);

      }
    }

    if(! *myhost) {
      /* need to fix this
         h=Curl_gethost(data,
         getmyhost(*myhost,sizeof(myhost)),
         hostent_buf,
         sizeof(hostent_buf));
      */
      return CURLE_HTTP_PORT_FAILED;
    }

    infof(data, "We bind local end to %s\n", myhost);

    in=inet_addr(myhost);
    if (CURL_INADDR_NONE != in) {

      if ( h ) {
        Curl_addrinfo *addr = h->addr;

        Curl_resolv_unlock(data, h);
        /* we don't need it anymore after this function has returned */

#ifdef ENABLE_IPV6
        (void)sa; /* prevent compiler warning */
        if( bind(sockfd, addr->ai_addr, addr->ai_addrlen) >= 0) {
          /* we succeeded to bind */
          struct sockaddr_in6 add;
	
          size = sizeof(add);
          if(getsockname(sockfd, (struct sockaddr *) &add,
                         (socklen_t *)&size)<0) {
            failf(data, "getsockname() failed");
            return CURLE_HTTP_PORT_FAILED;
          }
        }
#else
        memset((char *)&sa, 0, sizeof(sa));
        memcpy((char *)&sa.sin_addr, addr->h_addr, addr->h_length);
        sa.sin_family = AF_INET;
        sa.sin_addr.s_addr = in;
        sa.sin_port = 0; /* get any port */
	
        if( bind(sockfd, (struct sockaddr *)&sa, sizeof(sa)) >= 0) {
          /* we succeeded to bind */
          struct sockaddr_in add;
	
          size = sizeof(add);
          if(getsockname(sockfd, (struct sockaddr *) &add,
                         (socklen_t *)&size)<0) {
            failf(data, "getsockname() failed");
            return CURLE_HTTP_PORT_FAILED;
          }
        }
#endif
        else {
          switch(errno) {
          case EBADF:
            failf(data, "Invalid descriptor: %d", errno);
            break;
          case EINVAL:
            failf(data, "Invalid request: %d", errno);
            break;
          case EACCES:
            failf(data, "Address is protected, user not superuser: %d", errno);
            break;
          case ENOTSOCK:
            failf(data,
                  "Argument is a descriptor for a file, not a socket: %d",
                  errno);
            break;
          case EFAULT:
            failf(data, "Inaccessable memory error: %d", errno);
            break;
          case ENAMETOOLONG:
            failf(data, "Address too long: %d", errno);
            break;
          case ENOMEM:
            failf(data, "Insufficient kernel memory was available: %d", errno);
            break;
          default:
            failf(data, "errno %d", errno);
            break;
          } /* end of switch(errno) */
	
          return CURLE_HTTP_PORT_FAILED;
        } /* end of else */
	
      } /* end of if  h */
      else {
	failf(data,"could't find my own IP address (%s)", myhost);
	return CURLE_HTTP_PORT_FAILED;
      }
    } /* end of inet_addr */

    else {
      failf(data, "could't find my own IP address (%s)", myhost);
      return CURLE_HTTP_PORT_FAILED;
    }

    return CURLE_OK;

  } /* end of device selection support */
#endif /* end of HAVE_INET_NTOA */

  return CURLE_HTTP_PORT_FAILED;
}

/*
 * verifyconnect() returns TRUE if the connect really has happened.
 */
static bool verifyconnect(int sockfd)
{
#if defined(SO_ERROR) && !defined(WIN32)
  int err = 0;
  socklen_t errSize = sizeof(err);
  if( -1 == getsockopt(sockfd, SOL_SOCKET, SO_ERROR,
                       (void *)&err, &errSize))
    err = Curl_ourerrno();

  if ((0 == err) || (EISCONN == err))
    /* we are connected, awesome! */
    return TRUE;
  
  /* This wasn't a successful connect */
  return FALSE;
#else