package mainimport ("fmt""strconv""net/http""regexp""strings""os"
)func main() {var start,end intfmt.Printf("请输入起始页( >= 1) :")fmt.Scan(&start)fmt.Printf("请输入终止页( >= 起始页) :")fmt.Scan(&end)DoWork(start,end) //工作函数
}func DoWork(start,end int) {fmt.Printf("准备爬取第%d页到%d页的网址\n", start, end)page := make(chan int)for i:= start; i<= end; i++{//定义一个函数 并发 爬主页面go SpiderPape(i,page)}for i:= start; i<= end;i++{fmt.Printf("第%d个页面爬取完成\n", <-page)}
}func SpiderPape(i int, page chan int) {url := "https://www.pengfu.com/xiaohua_"+ strconv.Itoa(i) + ".html"fmt.Printf("正在爬取第%d个网页：%s\n", i, url)//开始爬取页面内容result,err:= HttpGet(url)if err != nil{fmt.Println("HttpGet err = ",err)return}//写正则过滤 urlre := regexp.MustCompile(`<h1 class="dp-b"><a href="(?s:(.*?))"`)if re == nil{fmt.Println("regexp.MustCompile err")return}//取关键信息joyUrls := re.FindAllStringSubmatch(result, -1)fmt.Println("joyUrls = ", joyUrls)fileTitle := make([]string, 0)fileContent := make([]string, 0)//取网址//第一个返回下标，第二个返回内容for _, data := range joyUrls {//开始爬取每一个笑话，每一个段子title, content, err := SpiderOneJoy(data[1])if err != nil {fmt.Println("SpiderOneJoy err = ", err)continue}fileTitle = append(fileTitle, title)       //追加内容fileContent = append(fileContent, content) //追加内容}fmt.Println("fileTitle= ", fileTitle)fmt.Println("fileContent= ", fileContent)//把内容写入到文件StoreJoyToFile(i, fileTitle, fileContent)page <- i //写内容，写num
}func StoreJoyToFile(num int, fileTitle, fileContent []string)  {//新建文件f, err := os.Create(strconv.Itoa(num) + ".txt")if err != nil {fmt.Println("os.Create err = ", err)return}defer f.Close()//写内容n := len(fileTitle)for i := 0; i < n; i++ {//写标题f.WriteString(fileTitle[i] + "\n")//写内容f.WriteString(fileContent[i] + "\n")f.WriteString("\n=================================================================\n")}
}//开始爬取每一个笑话，每一个段子 title, content, err := SpiderOneJoy(url)
func SpiderOneJoy(url string)  (title,content string, err error){//开始爬取页面内容result,err1 := HttpGet(url)if err1!= nil{err = err1return}//取关键信息//取标题  <h1>  标题 </h1>  只取1个re1 := regexp.MustCompile(`<h1>(?s:(.*?))</h1>`)if re1 == nil{err = fmt.Errorf("%s", "regexp.MustCompile err")return}//取标题tmpTitle := re1.FindAllStringSubmatch(result, 1) //最后一个参数为1，只过滤第一个for _, data := range tmpTitle {title = data[1]title = strings.Replace(title, "\t", "", -1)break}//取内容 <div class="content-txt pt10"> 段子内容 <a id="prev" href="re2 := regexp.MustCompile(`<div class="content-txt pt10">(?s:(.*?))<a id="prev" href="`)if re2 == nil {//fmt.Println("regexp.MustCompile err")err = fmt.Errorf("%s", "regexp.MustCompile err2")return}//取内容tmpContent := re2.FindAllStringSubmatch(result, -1)for _, data := range tmpContent {content = data[1]content = strings.Replace(content, "\t", "", -1)content = strings.Replace(content, "\n", "", -1)content = strings.Replace(content, "\r", "", -1)content = strings.Replace(content, "<br />", "", -1)break}return
}func HttpGet(url string)(result string, err error) {resp,err1 := http.Get(url) //发送 get 请求.if err1 !=nil{err = err1return}defer resp.Body.Close()//读取网页内容.buf := make([]byte, 4*1024)for{n,_:= resp.Body.Read(buf)if n == 0{break}result += string(buf[:n]) //累加读取内容}return
}