基于http协议的天气爬虫

该系统将基于目前比较流行的网络爬虫技术， 对网站上的天气数据进行查询分析， 最终使客户能够通过简单的操作， 快速， 准确的获取目标天气数据。主要包括两部分的功能， 第一部分是天气数据查询， 包括时间段数据查询， 实时天气数据查询；第二部分是打印查询出的天气数据。

实现这个项目时，可以先学习一下cJSON

main.c

#include <stdio.h>
#include <unistd.h>#include "grab.h"int main(int argc,const char *argv[])
{char city[128] = {0};int choose = 0;int sockfd = init_cli();           //初始化客户端while(1){menu();                        //打印一个菜单printf("input need find city:");scanf("%s",city);printf("input need find weather:");scanf("%d",&choose);switch(choose){case 1:find_now_weather(sockfd,city);    //查找当前天气recv_weather(sockfd);             //接收并打印当前天气break;case 2:find_future_weather(sockfd,citi);   //查找未来天气recv_weather1(sockfd);              //接收并打印未来天气}}close(sockfd);return 0;
}

grab.c:

#include <stdio.h>
#include <string.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <arpa/inet.h>
#include <netinet/in.h>
#include "cJSON.h"int init_cli()
{int sockfd = socket(AF_INET,SOCK_STREAM,0);if(sockfd < 0){return -1;}struct sockaddr_in ser;ser.sin_family = AF_INET;ser.sin_port = htons(80);ser.sin_addr.s_addr = inet_addr("103.205.5.228");int ret = connect(sockfd,(struct sockaddr *)&ser,sizeof(ser));if(ret < 0){perror("fail connect:");return -1;}return sockfd;
}void menu()
{printf("---------1.查询实时天气----------\n");printf("---------2.查询未来天气----------\n");
}void find_now_weather(int sockfd,char *city)
{char buff[1024] = {0};memset(buff,0,sizeof(buff));sprintf(buff,"GET /?app=weather.today&cityNm=%s&appkey=75258&sign=368fe47199076f69e8509979b1d9eeff&format=json HTTP/1.1\r\n""Host: api.k780.com\r\n""User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36 Edg/131.0.0.0\r\n""Accept:text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.Z\r\n""Accept-Language: zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6\r\n""connection: close\r\n\r\n",city);                 //请求报文，把要查询的城市拼进去，实现城市天气的查询ssize_t size = send(sockfd,buff,strlen(buff),0);if(size < 0){perror("fail send:");return;}return;
}Void recv_weather(int sockfd)
{char buff[10240] = {0};ssize_t size = recv(sockfd,buff,sizeof(buff) - 1,0);if(size < 1){    perror("fail recv:");return;}printf("%s\n",buff);int i=0;                            //从这里开始使用cJSON进行解析while(1)                              //首先定位到cJSON数据的开头{    if('{' == buff[i]){    break;}i++;}const char *json_string = &buff[i];cJSON *root = cJSoN_Parse(json_string);if(!root){printf("fail get root\n");   return;}cJSoN *success = cJsoN_GetobjectItem(root,"success"); //先解析未被嵌套的键值对，根结点cJSON *result = cJsoN_GetobjectItem(root,"result");printf("success:%s\n",success->valuestring);if(cJsoN_IsArray(result)) //判断result中有没有数组，如果有使用数组的解析方法{i = 0;for(i = 0;i < soN_GetArraySize(result);++i){cJSON *item = cJSoN_GetArrayItem(result,i); //解析result键值对数组cJSON *weaid = cJSON_GetobjectItem(item,"weaid");//根据得到的item解析键值对成员printf("weaid:%s\n",weaid->valuestring);}return;}cJSON *weaid = cJsoN_GetobjectItem(result,"weaid"); //再解析嵌套中的键值对，result结点printf("weaid:%s\n",weaid->valuestring);cJSON *days = cJSON_GetobjectItem(result,"days");printf("days:%s\n",days->valuestring);cJSON *week = cJSON_GetobjectItem(result,"week");printf("week:%s\n",week->valuestring);cJSON *citynm = cJsoN_GetobjectItem(result,"citynm");printf("citynm:%s\n",citynm->valuestring);   return;
}