最近在学go,以前都是用python爬虫,这次试一下用go写。相比较比较火的java,php,javascript,python等语言,go的优势在于天生的异步能力。能够通过极为简洁优雅的方式实现多线程的编程。而go对于变量的种种限制,简直就是某些强迫症患者的福音。所以我们新手小白也可以尝试用这个语言写爬虫。
今天就用它写了一个简单的爬虫以做练习。首先呢要采集的网站就是今日头条
package main
import (
"net/url"
"net/http"
"bytes"
"fmt"
"io/ioutil"
)
// 代理服务器(产品官网 www.16yun.cn)
const ProxyServer = "t.16yun.cn:31111"
type ProxyAuth struct {
Username string
Password string
}
func (p ProxyAuth) ProxyClient() http.Client {
var proxyURL *url.URL
if p.Username != ""&& p.Password!="" {
proxyURL, _ = url.Parse("http://" + p.Username + ":" + p.Password + "@" + ProxyServer)
}else{
proxyURL, _ = url.Parse("http://" + ProxyServer)
}
return http.Client{Transport: &http.Transport{Proxy:http.ProxyURL(proxyURL)}}
}
func main() {
targetURI := "https:www.toutiao.com/"
// 初始化 proxy http client
client := ProxyAuth{"username", "password"}.ProxyClient()
request, _ := http.NewRequest("GET", targetURI, bytes.NewBuffer([] byte(``)))
// 设置Proxy-Tunnel
// rand.Seed(time.Now().UnixNano())
// tunnel := rand.Intn(10000)
// request.Header.Set("Proxy-Tunnel", strconv.Itoa(tunnel) )
response, err := client.Do(request)
if err != nil {
panic("failed to connect: " + err.Error())
} else {
bodyByte, err := ioutil.ReadAll(response.Body)
if err != nil {
fmt.Println("读取 Body 时出错", err)
return
}
response.Body.Close()
body := string(bodyByte)
fmt.Println("Response Status:", response.Status)
fmt.Println("Response Header:", response.Header)
fmt.Println("Response Body:\n", body)
}
}