go寫爬蟲

package main

import (
	"fmt"
	"net/http"
	"os"
	"regexp"
	"strconv"
	"strings"
)

func main() {
	var start, end int
	fmt.Printf("請輸入起始頁( >= 1) :")
	fmt.Scan(&start)
	fmt.Printf("請輸入終止頁( >= 起始頁) :")
	fmt.Scan(&end)

	DoWork(start, end) //工作函數
}

//開啓協程
func DoWork(start, end int) {
	fmt.Printf("準備爬取第%d頁到%d頁的網址\n", start, end)

	page := make(chan int)

	for i := start; i <= end; i++ {
		//開協程爬
		go SpiderPape(i, page)
	}

	for i := start; i <= end; i++ {
		fmt.Printf("第%d個頁面爬取完成\n", <-page)
	}
}

//爬取頁面
func SpiderPape(i int, page chan int) {

	//這裏需要分析頁面的規律
	url := "https://m.pengfu.com/xiaohua_" + strconv.Itoa(i) + ".html"
	fmt.Printf("正在爬取第%d個網頁：%s\n", i, url)

	//開始爬取頁面內容
	result, err := HttpGet(url)
	if err != nil {
		fmt.Println("HttpGet err = ", err)
		return
	}

	//這裏需要分析內容頁面url的規律
	re := regexp.MustCompile(`<h1 class="f18"><a href="(?s:(.*?))"`)
	if re == nil {
		fmt.Println("regexp.MustCompile err")
		return
	}

	//取內容的url
	joyUrls := re.FindAllStringSubmatch(result, -1)

	fileTitle := make([]string, 0)
	fileContent := make([]string, 0)

	//根據內容url爬取標題和內容
	//第一個返回下標，第二個返回內容
	for _, data := range joyUrls {

		//開始爬取每一個笑話，每一個段子
		title, content, err := SpiderOneJoy(data[1])
		if err != nil {
			fmt.Println("SpiderOneJoy err = ", err)
			continue
		}

		fileTitle = append(fileTitle, title)       //追加內容
		fileContent = append(fileContent, content) //追加內容
	}

	//把內容寫入到文件
	fmt.Println("title = ", fileTitle)
	fmt.Println("content = ", fileContent)
	StoreJoyToFile(i, fileTitle, fileContent)

	page <- i //寫內容，寫num

}

//通過get請求獲取網頁內容
func HttpGet(url string) (result string, err error) {
	resp, err1 := http.Get(url) //發送get請求
	if err1 != nil {
		err = err1
		return
	}

	defer resp.Body.Close()

	//讀取網頁內容
	buf := make([]byte, 4*1024)
	for {
		n, _ := resp.Body.Read(buf)
		if n == 0 {
			break
		}
		result += string(buf[:n]) //累加讀取的內容
	}
	return
}

//開始爬取每一個笑話，每一個段子 title, content, err := SpiderOneJoy(url)
func SpiderOneJoy(url string) (title, content string, err error) {

	//開始爬取頁面內容
	result, err1 := HttpGet(url)
	if err1 != nil {
		err = err1
		return
	}

	//這裏需要分析標題的規律
	re1 := regexp.MustCompile(`<title>(?s:(.*?))</title>`)
	if re1 == nil {
		//fmt.Println("regexp.MustCompile err")
		err = fmt.Errorf("%s", "regexp.MustCompile err")
		return
	}
	//取內容
	tmpTitle := re1.FindAllStringSubmatch(result, 1) //最後一個參數爲1，只過濾第一個
	for _, data := range tmpTitle {
		title = data[1]
		title = strings.Replace(title, "\t", "", -1)
		break
	}

	//這裏需要分析內容的規律
	re2 := regexp.MustCompile(`<div class="con-txt">(?s:(.*?))</div`)
	if re2 == nil {
		err = fmt.Errorf("%s", "regexp.MustCompile err2")
		return
	}

	//取內容
	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
}

//把內容寫入到文件
func StoreJoyToFile(i int, fileTitle, fileContent []string) {
	//新建文件
	f, err := os.Create(strconv.Itoa(i) + ".txt")
	if err != nil {
		fmt.Println("os.Create err = ", err)
		return
	}

	defer f.Close()

	//寫內容
	n := len(fileTitle)
	for i := 0; i < n; i++ {
		//寫標題
		f.WriteString(fileTitle[i] + "\n")
		//寫內容
		f.WriteString(fileContent[i] + "\n")

		f.WriteString("\n=================================================================\n")
	}

}