当前位置:主页 > 脚本语言 > Golang >

Golang爬虫及正则表达式的实现示例

时间:2023-03-20 10:27:30 | 栏目:Golang | 点击:

最近学习go,爬取网站数据用到正则表达式,做个总结;

Go中正则表达式采用RE2语法(具体是啥咱也不清楚);

字符

数量限定

其他

方法

//参数正则字符串,返回值*Regexp
str := regexp.MustCompile(string) 
//参数要查找的数据,查找次数-1为全局,返回值二维数组,查找出的字符串+正则字符串
var result [][]string = str.FindAllStringSubmatch(data, -1)

爬虫

爬取博客园所有文章阅读量,评论,推荐;

package main

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

var readCount int = 0
var commentCount int = 0
var diggCount int = 0

//http读取网页数据写入result返回
func HttpGet(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)

 for {
  n, err2 := resp.Body.Read(buf)
  //fmt.Println(url)
  if n == 0 {
   break
  }
  if err2 != nil && err2 != io.EOF {
   err = err2
   return
  }
  result += string(buf[:n])
 }
 return result, err
}

//横向纵向爬取文章标题数据,并累计数值
func SpiderPageDB(index int, page chan int) {
 url := "https://www.cnblogs.com/littleperilla/default.html?page=" + strconv.Itoa(index)
    
 result, err := HttpGet(url)

 if err != nil {
  fmt.Println("HttpGet err:", err)
  return
 }

 str := regexp.MustCompile("post-view-count\">阅读[(](?s:(.*?))[)]</span>")
 alls := str.FindAllStringSubmatch(result, -1)
 for _, j := range alls {
  temp, err := strconv.Atoi(j[1])
  if err != nil {
   fmt.Println("string2int err:", err)
  }
  readCount += temp
 }

 str = regexp.MustCompile("post-comment-count\">评论[(](?s:(.*?))[)]</span>")
 alls = str.FindAllStringSubmatch(result, -1)
 for _, j := range alls {
  temp, err := strconv.Atoi(j[1])
  if err != nil {
   fmt.Println("string2int err:", err)
  }
  commentCount += temp
 }

 str = regexp.MustCompile("post-digg-count\">推荐[(](?s:(.*?))[)]</span>")
 alls = str.FindAllStringSubmatch(result, -1)
 for _, j := range alls {
  temp, err := strconv.Atoi(j[1])
  if err != nil {
   fmt.Println("string2int err:", err)
  }
  diggCount += temp
 }

 page <- index
}

//主要工作方法
func working(start, end int) {
 fmt.Printf("正在从%d到%d爬取中...\n", start, end)

 //channel通知主线程是否所有go都结束
 page := make(chan int)

 //多线程go程同时爬取
 for i := start; i <= end; i++ {
  go SpiderPageDB(i, page)
 }

 for i := start; i <= end; i++ {
  fmt.Printf("拉取到%d页\n", <-page)
 }
}

//入口函数
func main() {
 //输入爬取的起始页
 var start, end int
 fmt.Print("startPos:")
 fmt.Scan(&start)
 fmt.Print("endPos:")
 fmt.Scan(&end)

 working(start, end)

 fmt.Println("阅读:", readCount)
 fmt.Println("评论:", commentCount)
 fmt.Println("推荐:", diggCount)
}

补充:正则表达式加golang爬虫爬取经典案例豆瓣top250

package main

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

func savToFile(index int, filmName, filmScore [][]string) {
	f, err := os.Create("第" + strconv.Itoa(index) + "页.txt")
	if err != nil {
		fmt.Println("os create err", err)
		return
	}
	defer f.Close()
	// 查出有多少条
	n := len(filmName)
	// 先写抬头 名称     评分
	f.WriteString("电影名称" + "\t\t\t" + "评分" + "\n")
	for i := 0; i < n; i++ {
		f.WriteString(filmName[i][1] + "\t\t\t" + filmScore[i][1] + "\n")
	}
}

func main() {
	var start, end int
	fmt.Print("请输入要爬取的起始页")
	fmt.Scan(&start)
	fmt.Print("请输入要爬取的终止页")
	fmt.Scan(&end)
	working(start, end)
}

func working(start int, end int) {
	fmt.Printf("正在爬取%d到%d页", start, end)
	for i := start; i <= end; i++ {
		SpiderPage(i)
	}
}

// 爬取一个豆瓣页面数据信息保存到文档
func SpiderPage(index int) {
	// 获取url
	url := "https://movie.douban.com/top250?start=" + strconv.Itoa((index-1)*25) + "&filter="

	// 爬取url对应页面
	result, err := HttpGet(url)
	if err != nil {
		fmt.Println("httpget err", err)
		return
	}
	//fmt.Println("result=", result)
	// 解析,编译正则表达式  ---电影名称
	ret := regexp.MustCompile(`<img width="100" alt="(?s:(.*?))"`)
	filmName := ret.FindAllStringSubmatch(result, -1)
	for _, name := range filmName {
		fmt.Println("name", name[1])
	}

	ret2 := regexp.MustCompile(`<span class="rating_num" property="v:average">(?s:(.*?))<`)
	filmScore := ret2.FindAllStringSubmatch(result, -1)
	for _, score := range filmScore {
		fmt.Println("score", score[1])
	}

	savToFile(index, filmName, filmScore)

}

// 爬取指定url页面,返回result
func HttpGet(url string) (result string, err error) {
	req, _ := http.NewRequest("GET", url, nil)
	// 设置头部信息
	req.Header.Set("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36 OPR/66.0.3515.115")
	resp, err1 := (&http.Client{}).Do(req)
	//resp, err1 := http.Get(url)  //此方法已经被豆瓣视为爬虫,返回状态吗为418,所以必须伪装头部用上述办法
	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

}

您可能感兴趣的文章:

相关文章