download.c

youtube的视频下载工具

/*

U2B Downloader is a simple program with a user interface to download videos
from youTube.com and convert them to mpeg format (optional). 

          Copyright (c) 2007, Fabio Bruno Pereira <[e-mail]>

This file is part of U2B Downloader.

    U2B Downloader is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation, either version 3 of the License, or
    (at your option) any later version.

    U2B Downloader is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU General Public License for more details.

    You should have received a copy of the GNU General Public License
    along with U2B Downloader.  If not, see <http://www.gnu.org/licenses/>.

*/

#include <gtk/gtk.h>

#include <sys/socket.h>
#include <arpa/inet.h>
#include <netdb.h>

#include <errno.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <strings.h>
#include <regex.h>

#include "download.h"

extern GtkWidget *label_percent;

char * http_post(const char * url, const char * params);
#define MAX_BUFFER 204800
char buffer[MAX_BUFFER+1];
int size = 0; 

char* match(const char *string, const char *pattern)
{
    int    status;
    regex_t    re;
    regmatch_t match;
    char * tparam = NULL;

    if ((status = regcomp(&re, pattern, REG_EXTENDED)) != 0) {
       if(status == REG_NOMATCH)
          printf("regex REG_NOMATCH\n");
       if(status == REG_BADPAT)
          printf("regex REG_BADPAT\n");
       if(status == REG_BADRPT)
          printf("regex REG_BADRPT\n");
       if(status == REG_ERANGE)
          printf("regex REG_ERANGE\n");
        return NULL;      /* report error */
    }
    
    status = regexec(&re, string, 1, &match, 0);
    regfree(&re);
    if (status != 0) {
        return NULL;      /* report error */
    }
    size = match.rm_eo - match.rm_so ;
    if( size > 5 ){
       tparam = (char*)malloc(sizeof(char) * size);
       memset(tparam,0,sizeof(char) * size);
       strncpy(tparam,&(string[match.rm_so+4]),size-5);
    }
    return tparam;
}

static char * metacafe_download(char * url){
   char * ret = NULL;
   char * endURL = NULL;
   char * mediaURL = NULL ;
   char video_id[256] ;
   static char data_location[256];
   memset(video_id,0,256);
   
   ret = strstr(url,"com/");
   if(ret == NULL)
      return NULL;
   
   strcpy(video_id,&(ret[3]));

   gdk_threads_enter();
   gtk_label_set_text(GTK_LABEL(label_percent), "connecting www.metacafe.com..." );
   gdk_threads_leave();
   ret = http_post("www.metacafe.com",video_id);
   if(ret == NULL)
      return NULL;
   
   mediaURL = strstr(ret,"mediaURL");
   if(mediaURL == NULL)
      return NULL;
   mediaURL += 9;
   endURL = strstr(mediaURL,".flv");
   if(endURL == NULL)
      return NULL;

   int i =0 ;
   for(i = 0; i < (endURL-mediaURL)+4;i++){
      data_location[i] = mediaURL[i] ;
   }
   data_location[i] = '\0' ;

   return (char*)&data_location;
}

char * find_url_to_download(char * url){
 
   int connectionFd; 
   struct sockaddr_in servaddr;
   struct hostent * hptr = NULL;
   static char data_location[256];
   char * tparam = NULL;
   char video_id[256] ;
   char * ret;
   
   memset(data_location,0,256);
   memset(video_id,0,256);
   
   if((ret = strstr(url,"metacafe")) != NULL){
      printf("fazendo download do metacafe!\n");
      return metacafe_download(url);
   }
   ret = strstr(url,"com/");
   if(ret == NULL)
      return NULL;
   
   strcpy(video_id,&(ret[3]));
   gdk_threads_enter();
   gtk_label_set_text(GTK_LABEL(label_percent), "connecting www.youtube.com..." );
   gdk_threads_leave();
   ret = http_post("www.youtube.com",video_id);
   if(ret == NULL)
      return NULL;
   
   ret = strstr(url,"?v=");
   if(ret == NULL)
      return NULL;
   
   char vparam[126];
   memset(vparam,0,126);
   sprintf(vparam,"/v/%s",(ret+3));
   ret = http_post("www.youtube.com",vparam);
   
   //****************
   
   tparam = strstr(ret,"&t=");
   if(tparam == NULL)
      return NULL;
   
   char * breakline = strchr(tparam,'\r');
   if(breakline != NULL)
      *(breakline) = '\0' ;
   
   char tparam_ok[126];
   int i = 0 ;
   for(i=0; i < 125 && *tparam ; i++){
      tparam_ok[i] = *tparam;
      tparam++;
   }
   tparam_ok[i] = '\0' ;
   
   //*************************
   
   
   
   
  char tmp[160];
  memset(tmp,0,160);
  sprintf(tmp,"/get_video?video_id=%s%s",&(video_id[9]),tparam_ok);
  
  gdk_threads_enter();
  gtk_label_set_text(GTK_LABEL(label_percent), "fetching video url..." );
  gdk_threads_leave();
  ret = http_post("www.youtube.com", tmp);
  if(ret == NULL)
     return NULL ; 
  
   char * ptr = strstr(buffer,"Location:"); 
   if(ptr != NULL){   
      char *ptr_end = strstr(ptr+10,"\n");
      int i = 0;
      while(ptr+10 < ptr_end){
         data_location[i] = *(ptr+10) ;
         i++; ptr++;
      }
      data_location[i-1] = 0 ;
     
      ptr = index(&(data_location[7]),'/'); // jump the http:// 
      char domain[265] ;
      memset(domain,0,256);
      strncpy(domain,&(data_location[7]),ptr-&(data_location[7]));
      connectionFd = socket(AF_INET,SOCK_STREAM,0);
      memset(&servaddr,0,sizeof(servaddr));
      servaddr.sin_family = AF_INET;
      servaddr.sin_port = htons(80);
      hptr = gethostbyname2(domain,AF_INET);
      
      if(hptr == NULL){
         return NULL;
      } 
     //printf("addr=%x\n",*(unsigned long *) *(hptr->h_addr_list));
      servaddr.sin_addr.s_addr	=   *(unsigned long *) *(hptr->h_addr_list);
      //printf("addr=%s\n",inet_ntoa(servaddr.sin_addr));
      sprintf(data_location,"http://%s%s",inet_ntoa(servaddr.sin_addr),ptr);
      //printf("data_location=%s*\n",data_location);
      
   }else
      return NULL ;
  
   return (char*)&data_location ;
}


char * http_post(const char * url, const char * params){
   int connectionFd; 
   int in; 
   unsigned long limit = MAX_BUFFER ,index =0;
   struct sockaddr_in servaddr;
   struct hostent * hptr = NULL;
   char tmp[512];
   
   memset(buffer,0,MAX_BUFFER+1);
   memset(tmp,0,512);
   sprintf(tmp,"GET %s HTTP/1.0\r\nHost: %s\r\nUser-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1) Gecko/20061010 Firefox/2.0\r\nAccept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7\r\nAccept: text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png, */*;q=0.5\r\nAccept-Language: en-us,en;q=0.5\r\n\n",params,url); 
  
  // printf("link:%s\n",tmp);
      char * string = (char*)malloc(sizeof(char)*strlen(tmp)+1);
      memset(string, 0, sizeof(char)*strlen(tmp)+1);
      strcpy(string,tmp);
      connectionFd = socket(AF_INET,SOCK_STREAM,0);
      memset(&servaddr,0,sizeof(servaddr));
      servaddr.sin_family = AF_INET;
      servaddr.sin_port = htons(80);
      hptr = gethostbyname2(url, AF_INET);
      
      if(hptr == NULL){
         return NULL;
      } 
     // printf("addr=%x\n",*(unsigned long *) *(hptr->h_addr_list));
      servaddr.sin_addr.s_addr	=   *(unsigned long *) *(hptr->h_addr_list);
   
      if(connect(connectionFd,(struct sockaddr*)&servaddr,sizeof(servaddr)) ){
         return NULL ;
      }
  
      write(connectionFd, string, strlen(string));
      while((in=read(connectionFd, &(buffer[index]), limit)) >0 ){
         index += in;
         limit -= in;
      }
     
      close(connectionFd); 
      buffer[index] = 0 ;
   // printf("return=%s\n",buffer);
      return buffer;
}