go-爬虫-百度贴吧(并发版)

2022-10-12,,

爬取百度贴吧的网页

并发

package main

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

func httpget(url string) (result string, err error) {
    //  var result string
    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)
        if n == 0 {
            fmt.println("读取网页完成")
            break
        }
        if err2 != nil && err2 != io.eof {
            err = err2
            return
        }
        result += string(buf[:n])
    }
    return
}

func working(start, end int) {
    fmt.printf("正在爬取第%d到第%d页", start, end)
    //爬取每一个网页
    for i := start; i <= end; i++ {
        url := "https://tieba.baidu.com/f?kw=vue&ie=utf-8&pn=" + strconv.itoa((i-1)*50)
        result, err := httpget(url)
        if err != nil {
            fmt.println("httpget err", err)
            continue
        }
        //      fmt.println("result", result)
        f, err := os.create("第" + strconv.itoa(i) + "页" + ".html")
        if err != nil {
            fmt.println("httpget err", err)
            continue
        }
        f.writestring(result)
        f.close()
    }
}

func main() {
    var start, end int
    fmt.print("请输入起始页。。。")
    fmt.scan(&start)
    fmt.print("请输入终止页。。。")
    fmt.scan(&end)

    working(start, end)
}

并发版

这个只是在上面的基础上加了管道和开了协程

package main

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

func httpget(url string) (result string, err error) {
    //  var result string
    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)
        if n == 0 {
            fmt.println("读取网页完成\n")
            break
        }
        if err2 != nil && err2 != io.eof {
            err = err2
            return
        }
        result += string(buf[:n])
    }
    return
}

func spiderpage(index int, page chan int) {
    fmt.printf("正在爬取第%d到页\n", index)
    //爬取每一个网页
    //  for i := start; i <= end; i++ {
    url := "https://tieba.baidu.com/f?kw=vue&ie=utf-8&pn=" + strconv.itoa((index-1)*50)
    result, err := httpget(url)
    if err != nil {
        fmt.println("httpget err", err)
        return
    }
    //      fmt.println("result", result)
    f, err := os.create("第" + strconv.itoa(index) + "页" + ".html")
    if err != nil {
        fmt.println("httpget err", err)
        return
    }
    f.writestring(result)
    f.close()
    //  }

    page <- index
}

func working2(start, end int) {
    fmt.printf("正在爬取第%d页到%d页\n", start, end)

    page := make(chan int)

    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\n", <-page)
    }
}

func main() {
    var start, end int
    fmt.print("请输入起始页。。。")
    fmt.scan(&start)
    fmt.print("请输入终止页。。。")
    fmt.scan(&end)

    working2(start, end)
}

《go-爬虫-百度贴吧(并发版).doc》

下载本文的Word格式文档,以方便收藏与打印。