go语言应用：爬虫

1.爬虫思路：

1）明确目标（要知道你准备在哪个范围或网站去搜索）

2）爬（将所有的网站的内容全部爬下来）

3）取（去掉对我们没用处的数据）

4）处理数据（按照我们想要的方式存储和使用）

2.百度贴吧爬虫

package main

import (
	"fmt"
	"net/http"
	"os"
	"strconv"
)
//爬取网页内容
func HttpGet(url string) (result string, err error) {
	resp, err1 := http.Get(url)
	if err1 != nil {
		fmt.Println("http.Get err=", err)
		return
	}
	defer resp.Body.Close()
//读取网页Body中的内容
	buf := make([]byte, 4*1024)
	for {
		n, err := resp.Body.Read(buf)
		if n == 0 {//读取结束或者出现问题了
			fmt.Println("resp.Body.Read err=", err)
			break
		}
		result += string(buf[:n])
	}
	return
}
func DoWork(start, end int) {
	fmt.Printf("正在爬取%d到%d的页面", start, end)
//明确目标（要知道准备在哪个范围或网站去搜索）
//下一页+50
	for i := start; i <= end; i++ {
		url := "https://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=" + strconv.Itoa((i-1)*50)
//爬（将所有的网站的内容全部爬下来）
		result, err := HttpGet(url)
		if err != nil {
			fmt.Println("HttpGet err=", err)
			continue
		}
//把爬下来的内容写到文件中
		fileName := strconv.Itoa(i) + ".html"
		f, err1 := os.Create(fileName)
		if err1 != nil {
			fmt.Println("os.Create err=", err1)
			continue
		}
		f.WriteString(result)
		f.Close()//关闭文件
	}
}
func main() {
	var start, end int
	fmt.Printf("请输入起始页（大于等于1）：")
	fmt.Scan(&start)
	fmt.Printf("请输入终止页（大于等于起始页）：")
	fmt.Scan(&end)
	DoWork(start, end)
}

3.并发百度贴吧爬虫

package main

import (
	"fmt"
	"net/http"
	"os"
	"strconv"
)
//爬取网站内容
func HttpGet(url string) (result string, err error) {
	resp, err1 := http.Get(url)
	if err1 != nil {
		err = err1
		return
	}
	defer resp.Body.Close()
//读取网页内容
	buf := make([]byte, 4*1024)
	for {
		n, err := resp.Body.Read(buf)
		if n == 0 {
			fmt.Println("resp.Body.Read err=", err)
			break
		}
		result += string(buf[:n])
	}
	return
}
//爬取一个网页
func SpiderPage(i int, page chan int) {
	url := "https://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=" + strconv.Itoa((i-1)*50)
//爬（将所有的网站的内容全部爬下来）
	result, err := HttpGet(url)
	if err != nil {
		fmt.Println("HttpGet err", err)
		return
	}
//把内容写入到文件
	fileName := strconv.Itoa(i) + ".html"
	f, err1 := os.Create(fileName)
	if err1 != nil {
		fmt.Println("os.Create err=", err1)
		return
	}
	f.WriteString(result)
	f.Close()//关闭文件
	page <- i
}
func DoWork(start, end int) {
	fmt.Printf("正在爬取第%d页到第%d页\n", start, end)
	page := make(chan int) //不能光声明不给分配空间
//明确目标（要知道准备在哪个范围或网站去搜索），下一页+50
	for i := start; i <= end; i++ {
		go SpiderPage(i, page)
	}
	for i := start; i <= end; i++ {
		fmt.Printf("第%d个页面爬取完成", <-page)
	}
}
func main() {
	var start, end int
	fmt.Printf("请输入起始页（大于等于1）：")
	fmt.Scan(&start)
	fmt.Printf("请输入终止页（大于等于起始页）：")
	fmt.Scan(&end)
	DoWork(start, end)
}

4.并发，爬取网页链接

package main

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

func HttpGet(url string) (result string, err error) {
	resp, err1 := http.Get(url)//发送Get请求
	if err1 != nil {
		err = err1
		return
	}
	defer resp.Body.Close()
    //读取网页内容
	buf := make([]byte, 4*1024)
	for {
		n, err := resp.Body.Read(buf)
		if n == 0 {
			fmt.Println("resp.Body.Read err=", err)
			break
		}
		result += string(buf[:n])
	}
	return
}
func SpiderOneJoy(url string) (title, content string, err error) {
	result, err1 := HttpGet(url)
	if err1 != nil {
		err = err1
		return
	}
    //取标题：<h1>标题</h1>
	re := regexp.MustCompile(`<h1>(?s:(.*?))</h1>`)
	if re == nil {
		err = fmt.Errorf("%s", "regexp.MustCompile err")
		return
	}
	tmpTitle := re.FindAllStringSubmatch(result, 1)
	for _, data := range tmpTitle {
		title = data[1]
		title = strings.Replace(title, "\t", "", -1)
		break
	}
    //取内容：
	re = regexp.MustCompile(`<div class="content-txt pt10">(?s:(.*?))<a id="prev" href="`)
	if re == nil {
		err = fmt.Errorf("%s", "regexp.MustCompile err")
		return
	}
	tmpContent := re.FindAllStringSubmatch(result, -1)
	for _, data := range tmpContent {
		content = data[1]
		content = strings.Replace(content, "\r\n", "", -1)
		content = strings.Replace(content, "\n", "", -1)
		content = strings.Replace(content, "\r", "", -1)
		content = strings.Replace(content, " ", "", -1)
		content = strings.Replace(content, "\t", "", -1)
		content = strings.Replace(content, "<br/>", "", -1)
		content = strings.Replace(content, "<br />", "", -1)
		break
	}
	return
}
func StoreJoyToFile(i int, fileTitle, fileContent []string) {
	//新建文件
    fileName := strconv.Itoa(i) + ".txt"
	f, err := os.Create(fileName)
	if err != nil {
		fmt.Println("os.Create err=", err)
		return
	}
	defer f.Close()
	len := len(fileTitle)
    //往文件里写内容
	for i := 0; i < len; i++ {
		f.WriteString(fileTitle[i] + "\n")
		f.WriteString(fileContent[i] + "\n")
		f.WriteString("---------\n")
	}
}
func SpiderPage(i int, page chan int) {
    //明确爬取的网址
	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)
    //开始爬取页面的内容
	result, err := HttpGet(url)
	if err != nil {
		fmt.Println("HttpGet err=", err)
		return
	}
    //取内容，<h1 class="dp-b"><a href="一个段子url连接 "
	re := 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)
	fileTitle := make([]string, 0)
	fileContent := make([]string, 0)
	for _, data := range joyUrls {
		url := data[1]
        //爬子页面
		title, content, err := SpiderOneJoy(url)
		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
	}
	StoreJoyToFile(i, fileTitle, fileContent)
	page <- i//爬完之后，将页编号加入通道
}
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，爬主页面
		go SpiderPage(i, page)
	}
	for i := start; i <= end; i++ {
		fmt.Printf("第%d页爬取结束\n", <-page)
	}
}
func main() {
	var start, end int
	fmt.Printf("请输入起始页（大于等于1）：")
	fmt.Scan(&start)
	fmt.Printf("请输入终止页（大于等于起始页）：")
	fmt.Scan(&end)
	DoWork(start, end)//工作函数
}