go-爬图片

go语言爬取图片

注：动态加载出来的爬取不到，或怕取出来图片出错，代码中的网页是可以正常爬取的

package main

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

func saveimg(idx int, url string, page chan int) {
    path := "d:/gogogo/src/go-爬虫/图片爬取/main/images/" + strconv.itoa(idx+1) + ".jpg"
    f, err := os.create(path)
    //  resp, err1 := http.get(url)
    if err != nil {
        fmt.println("err:", err)
        return
    }

    defer f.close()
    resp, err := http.get(url)
    if err != nil {
        fmt.println("err:", err)
        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
        }
        f.write(buf[:n])

    }
    page <- idx
}

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 main() {
    url := "http://sc.chinaz.com/tupian/ribenmeinv.html"
    result, err := httpget(url)
    if err != nil {
        fmt.println("err:", err)
        return
    }
    //  (?s:(.*?))
    ret1 := regexp.mustcompile(`<img src2="(?s:(.*?))"`)

    alls := ret1.findallstringsubmatch(result, -1)

    page := make(chan int)
    n := len(alls)

    for idx, imgurl := range alls {
        //      fmt.println(imgurl[1])
        go saveimg(idx, imgurl[1], page)

    }
    for i := 0; i < n; i++ {
        fmt.printf("第%d下载完成\n", <-page)
    }

}