Go 언어 크롤러 개발을 위한 고급 기술: 심층 적용

package main

import (
    "fmt"
    "net/http"
)

func main() {
    urls := []string{
        "https:/www.example1.com",
        "https:/www.example2.com",
        "https:/www.example3.com",
    }

    // 创建一个无缓冲的channel
    ch := make(chan string)

    // 启动goroutine并发请求
    for _, url := range urls {
        go func(url string) {
            resp, err := http.Get(url)
            if err != nil {
                ch <- fmt.Sprintf("%s请求失败：%v", url, err)
            } else {
                ch <- fmt.Sprintf("%s请求成功，状态码：%d", url, resp.StatusCode)
            }
        }(url)
    }

    // 接收并打印请求结果
    for range urls {
        fmt.Println(<-ch)
    }
}

package main

import (
    "fmt"
    "net/http"
    "time"
)

func main() {
    url := "https:/www.example.com"

    // 创建一个定时器
    ticker := time.NewTicker(time.Hour) // 每小时执行一次任务

    for range ticker.C {
        fmt.Printf("开始抓取%s
", url)
        resp, err := http.Get(url)
        if err != nil {
            fmt.Printf("%s请求失败：%v
", url, err)
        } else {
            fmt.Printf("%s请求成功，状态码：%d
", url, resp.StatusCode)
            // TODO: 对网页进行解析和处理
        }
    }
}

package main

import (
    "fmt"
    "net/http"
    "net/url"
)

func main() {
    url := "https:/www.example.com"
    proxyUrl := "http://proxy.example.com:8080"

    proxy, err := url.Parse(proxyUrl)
    if err != nil {
        fmt.Printf("解析代理URL失败：%v
", err)
        return
    }

    client := &http.Client{
        Transport: &http.Transport{
            Proxy: http.ProxyURL(proxy),
        },
    }

    resp, err := client.Get(url)
    if err != nil {
        fmt.Printf("%s请求失败：%v
", url, err)
    } else {
        fmt.Printf("%s请求成功，状态码：%d
", url, resp.StatusCode)
    }
}