go-爬段子

爬取搞笑的段子，横向爬取+纵向爬取

横向爬取爬页数，纵向爬取，爬每页的内容

package main

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

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)
        if n == 0 {
            break
        }
        if err2 != nil && err2 != io.eof {
            err = err2
            return
        }
        result += string(buf[:n])
    }
    return
}

func savejoke2file(idx int, filetitle, filecontent []string) {
    path := "第" + strconv.itoa(idx) + "页.txt"
    f, err := os.create(path)
    if err != nil {
        fmt.println("err:", err)
        return
    }
    defer f.close()
    n := len(filetitle)
    for i := 0; i < n; i++ {
        f.writestring(filetitle[i] + "\n" + filecontent[i] + "\n")
        f.writestring("-----------------------------\n")
    }
}

//抓取一个网页
func spiderpage(idx int, page chan int) {
    url := "https://m.pengfue.com/xiaohua_" + strconv.itoa(idx) + ".html"

    result, err := httpget(url)
    if err != nil {
        fmt.println("httpget err", err)
        return
    }

    ret := regexp.mustcompile(`<h1 class="f18"><a href="(?s:(.*?))"`)

    alls := ret.findallstringsubmatch(result, -1)

    filetitle := make([]string, 0)
    filecontent := make([]string, 0)

    for _, jokeurl := range alls {
        //      fmt.println("jokeurl", jokeurl[1])
        title, content, err := spiderjokepage(jokeurl[1])

        if err != nil {
            fmt.println("err:", err)
            continue
        }

        //      fmt.println("title:", title)
        //      fmt.println("content:", content)
        filetitle = append(filetitle, title)
        filecontent = append(filecontent, content)
    }
    savejoke2file(idx, filetitle, filecontent)

    page <- idx
}

func towork(start, end int) {
    fmt.printf("正在爬取%d到%d页。。。\n", start, end)

    page := make(chan int)

    for i := start; i <= end; i++ {
        //      title, content, err := spiderpage(i)
        go spiderpage(i, page)
        //      if err != nil {
        //          fmt.println("err:", err)
        //          continue
        //      }
        //      fmt.println("title:", title)
        //      fmt.println("content:", content)
    }
    for i := start; i <= end; i++ {
        fmt.printf("第%d个页面爬取完成\n", <-page)
    }
}

func spiderjokepage(url string) (title, content string, err error) {
    result, err1 := httpget(url)
    if err1 != nil {
        //      fmt.println("httpget err", err)
        err = err1
        return
    }
    ret1 := regexp.mustcompile(`<title>(?s:(.*?))</title>`)

    alls := ret1.findallstringsubmatch(result, 1) //两处，取一个
    for _, timtitle := range alls {
        title = timtitle[1]
        title = strings.replace(title, " ", "", -1)
        title = strings.replace(title, "\n", "", -1)
        break
    }

    ret2 := regexp.mustcompile(`<div class="con-txt">(?s:(.*?))</div>`)

    alls2 := ret2.findallstringsubmatch(result, 1) //两处，取一个
    for _, timtitle := range alls2 {
        content = timtitle[1]
        content = strings.replace(content, " ", "", -1)
        content = strings.replace(content, "\n", "", -1)
        content = strings.replace(content, "    ", "", -1)
        content = strings.replace(content, "&nbsp;", "", -1)
        break
    }
    return
}

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)

    towork(start, end)
}