【GO语言】加正则表达式的爬虫练习

package main

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

//爬取指定url的页面，返回result
func HttpGet2(url string) (result string, err error) {
	resp, err1 := http.Get(url)
	if err1 != nil {
		err = err1
		return
	}
	defer resp.Body.Close()
	buf := make([]byte, 4096)
	//循环爬取整页数据
	for {
		n, err2 := resp.Body.Read(buf)
		if n == 0 {
			break
		}
		if err2 != nil && err2 != io.EOF {
			err = err2
			return
		}
		result += string(buf[:n])
	}
	return
}
func Save2file(idx int, filmName, filmScore, filmpeople [][]string) {
	f, err := os.Create("第" + strconv.Itoa(idx) + "页.txt")
	if err != nil {
		fmt.Println("os.Create err:", err)
		return
	}
	defer f.Close()
	n := len(filmName) //得到条目数。
	//先打印抬头  电影名称    评分     评分人数
	f.WriteString("电影名称" + "\t\t\t" + "评分" + "\t\t" + "评分人数" + "\n")
	for i := 0; i < n; i++ {
		f.WriteString(filmName[i][1] + "\t\t\t" + filmScore[i][1] + "\t\t" + filmpeople[i][0] + "\n")
	}
}

//爬取一个页面信息
func SpiderPage2(idx int) {
	//获取url
	url := "http://imdb.kxapps.com/default.aspx?page=" + strconv.Itoa(idx)
	//url := "https://movie.douban.com/top250"
	//封装httpget2爬取url对应页面
	result, err := HttpGet2(url)
	if err != nil {
		fmt.Println("HttpGet2 err:", err)
		return
	}
	//fmt.Println("result=", result)
	//解析，编译正则表达式——电影名称
	ret1 := regexp.MustCompile(` )
	//提取需要信息
	//电影名称
	filmName := ret1.FindAllStringSubmatch(result, -1)
	//评分
	ret2 := regexp.MustCompile(``)
	filmScore := ret2.FindAllStringSubmatch(result, -1)
	//评分人数
	ret3 := regexp.MustCompile(`>(.*?)人评分`)
	filmpeople := ret3.FindAllStringSubmatch(result, -1)
	//将提前的有用信息封装到文件中
	Save2file(idx, filmName, filmScore, filmpeople)
}
func toWork(start, end int) {
	fmt.Printf("正在爬取%d到%d页...\n", start, end)
	for i := start; i <= end; i++ {
		SpiderPage2(i)
	}
}
func main() {
	//指定爬取起始，终止页
	var start, end int
	fmt.Print("请输入爬取的起始页（>=1）:")
	fmt.Scan(&start)
	fmt.Print("请输入爬取的终止页（>=strart）:")
	fmt.Scan(&end)
	toWork(start, end)
}