导航

Go语言 爬虫1-网络请求

Posted on 2013-03-09 20:31  蝈蝈俊  阅读(4602)  评论(0编辑  收藏  举报

下面是找的几个例子:

 

例子1:获得百度首页的html源文件: 

package main
 
import(
    "fmt"
    "io/ioutil"
    "net/http"
)
 
func main(){
    response,_:=http.Get("http://www.baidu.com")
    defer response.Body.Close()
    body,_:=ioutil.ReadAll(response.Body)
    fmt.Println(string(body))
}

例子2,增加了一些错误验证

代码来自:https://gist.github.com/ijt/950790

package main
 
import(
    "fmt"
    "io/ioutil"
    "net/http"
    "os"
)
 
func main(){
    response,err:=http.Get("http://www.baidu.com/")
    if err!=nil{
        fmt.Printf("%s",err)
        os.Exit(1)
    }else{
        defer response.Body.Close()
        contents,err:=ioutil.ReadAll(response.Body)
        if err!=nil{
            fmt.Printf("%s",err)
            os.Exit(1)
        }
        fmt.Printf("%s\n",string(contents))
    }
}

http下有Get,Post,PostForm三个函数。这三个函数直接实现了简单的http客户端

下一个简单的例子增加了log, http://gameor.com/archives/178/golang%E5%8F%96%E9%93%BE%E6%8E%A5%E4%B8%8Ephp%E6%AF%94%E8%BE%83%E4%B8%8B/

package main
 
import(
    "fmt"
    "io/ioutil"
    "log"
    "net/http"
)
 
func main(){
    res,err:=http.Get("http://www.ghj1976.net/")
    if err!=nil{
        log.Fatal(err)
    }
    defer res.Body.Close()
    robots,err:=ioutil.ReadAll(res.Body)
    if err!=nil{
        log.Fatal(err)
    }
    fmt.Printf("%s",robots)
}

例子3:把百度的网页存在本地一个文件:

http://david-je.iteye.com/blog/1602774

package main
 
import(
    "fmt"
    "log"
    "net/http"
    "os"
)
 
func main(){
    resp,err:=http.Get("http://www.baidu.com")
    if err!=nil{
        //handleerror
        fmt.Println(err)
        log.Fatal(err)
    }
    defer resp.Body.Close()
    if resp.StatusCode==http.StatusOK{
        fmt.Println(resp.StatusCode)
    }
 
    buf:=make([]byte,1024)
    //createfile
    f,err1:=os.OpenFile("baidu.html",os.O_RDWR|os.O_CREATE|os.O_APPEND,os.ModePerm)
    if err1!=nil{
        panic(err1)
        return
    }
    defer f.Close()
 
    for{
        n,_:=resp.Body.Read(buf)
        if 0==n{
            break
        }
        f.WriteString(string(buf[:n]))
    }
 
}
 
 
其他可以借鉴的
 
golang 批量检查页面
http://www.simonzhang.net/?p=1346

 

除了使用Get、Post、PostForm 这三个函数来建立一个简单客户端,还可以使用:
http.Client和http.NewRequest来模拟请求

例子:指定公共头的请求百度页面

http://www.cnblogs.com/yjf512/archive/2012/06/18/2554066.html

package main
 
import(
    "fmt"
    "io/ioutil"
    "net/http"
)
 
func main(){
    client:=&http.Client{}
    reqest,_:=http.NewRequest("GET","http://www.baidu.com",nil)
 
    reqest.Header.Set("Accept","text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8")
    reqest.Header.Set("Accept-Charset","GBK,utf-8;q=0.7,*;q=0.3")
    reqest.Header.Set("Accept-Encoding","gzip,deflate,sdch")
    reqest.Header.Set("Accept-Language","zh-CN,zh;q=0.8")
    reqest.Header.Set("Cache-Control","max-age=0")
    reqest.Header.Set("Connection","keep-alive")
 
    response,_:=client.Do(reqest)
    if response.StatusCode==200{
        body,_:=ioutil.ReadAll(response.Body)
        bodystr:=string(body)
        fmt.Println(bodystr)
    }
}

 

 

参考资料:

用golang的正则regexp:去除HTML,CSS,SCRIPT代码,仅保留页面文字
http://bpbp.iteye.com/blog/1668869

 

Golang解析网页入门
http://mjason.github.com/blog/2013/01/29/golangjie-xi-wang-ye-ru-men/

golang做的webCrawl: gocrawl
http://hi.baidu.com/izouying/item/208551ec90a726f32a09a457

一个Go语言实现的web爬虫
http://www.sharejs.com/codes/go/4416