//參數(shù)正則字符串，返回值*Regexp
str := regexp.MustCompile(string) 
//參數(shù)要查找的數(shù)據(jù)，查找次數(shù)-1為全局，返回值二維數(shù)組，查找出的字符串+正則字符串
var result [][]string = str.FindAllStringSubmatch(data, -1)

package main

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

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

//http讀取網(wǎng)頁(yè)數(shù)據(jù)寫入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
}

//橫向縱向爬取文章標(biāo)題數(shù)據(jù)，并累計(jì)數(shù)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\">閱讀[(](?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\">評(píng)論[(](?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\">推薦[(](?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("正在從%d到%d爬取中...\n", start, end)

 //channel通知主線程是否所有g(shù)o都結(jié)束
 page := make(chan int)

 //多線程go程同時(shí)爬取
 for i := start; i <= end; i++ {
  go SpiderPageDB(i, page)
 }

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

//入口函數(shù)
func main() {
 //輸入爬取的起始頁(yè)
 var start, end int
 fmt.Print("startPos:")
 fmt.Scan(&start)
 fmt.Print("endPos:")
 fmt.Scan(&end)

 working(start, end)

 fmt.Println("閱讀:", readCount)
 fmt.Println("評(píng)論:", commentCount)
 fmt.Println("推薦:", diggCount)
}

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) + "頁(yè).txt")
	if err != nil {
		fmt.Println("os create err", err)
		return
	}
	defer f.Close()
	// 查出有多少條
	n := len(filmName)
	// 先寫抬頭 名稱     評(píng)分
	f.WriteString("電影名稱" + "\t\t\t" + "評(píng)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("請(qǐng)輸入要爬取的起始頁(yè)")
	fmt.Scan(&start)
	fmt.Print("請(qǐng)輸入要爬取的終止頁(yè)")
	fmt.Scan(&end)
	working(start, end)
}

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

// 爬取一個(gè)豆瓣頁(yè)面數(shù)據(jù)信息保存到文檔
func SpiderPage(index int) {
	// 獲取url
	url := "https://movie.douban.com/top250?start=" + strconv.Itoa((index-1)*25) + "&filter="

	// 爬取url對(duì)應(yīng)頁(yè)面
	result, err := HttpGet(url)
	if err != nil {
		fmt.Println("httpget err", err)
		return
	}
	//fmt.Println("result=", result)
	// 解析，編譯正則表達(dá)式  ---電影名稱
	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頁(yè)面，返回result
func HttpGet(url string) (result string, err error) {
	req, _ := http.NewRequest("GET", url, nil)
	// 設(shè)置頭部信息
	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)  //此方法已經(jīng)被豆瓣視為爬蟲，返回狀態(tài)嗎為418，所以必須偽裝頭部用上述辦法
	if err1 != nil {
		err = err1
		return
	}
	defer resp.Body.Close()

	buf := make([]byte, 4096)

	//循環(huán)爬取整頁(yè)數(shù)據(jù)
	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

}