go语音之进阶篇爬百度贴吧单线程版本？

一、爬什么？

1、明确目标 ： 知道你准备在那个范围或者网站去搜索

2、爬： 将所有的网站的内容全部爬下来

3、取：去掉对我们没用处的数据

4、处理数据：按照我们想要的方式存储或使用

二、百度贴吧小爬虫

需求：百度贴吧，每50页就翻页

https://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=0

https://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=50

示例： 单线程版本

package main

import (
        "fmt"
        "net/http"
        "os"
        "strconv"
)

//爬取网页内容
func HttpGet(url string) (result string, err error) {
        resp, err1 := http.Get(url)
        if err1 != nil {
                err = err1
                return
        }

        defer resp.Body.Close()

        //读取网页body内容
        buf := make([]byte, 1024*4)
        for {
                n, _ := resp.Body.Read(buf)
                if n == 0 { //读取结束，或者，出问题
                        //fmt.Println("resp.Body.Read err = ", err)
                        break
                }

                result += string(buf[:n])
        }

        return
}

func DoWork(start, end int) {
        fmt.Printf("正在爬取 %d 到 %d 的页面\n", start, end)

        //明确目标 (要知道你准备在哪个范围或者网站去搜索)
        for i := start; i <= end; i++ {
                url := "http://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=" + strconv.Itoa((i-1)*50)
                fmt.Println("url = ", url)

                //2) 爬 (将所有的网站的内容全部爬下来)
                result, err := HttpGet(url)
                if err != nil {
                        fmt.Println("HttpGet err = ", err)
                        continue
                }

                //把内容写入到文件
                fileName := strconv.Itoa(i) + ".html"
                f, err1 := os.Create(fileName)
                if err1 != nil {
                        fmt.Println("os.Create err1 = ", err1)
                        continue
                }

                f.WriteString(result) //写内容

                f.Close() //关闭文件
        }

}

func main() {
        var start, end int
        fmt.Printf("请输入起始页( >= 1) :")
        fmt.Scan(&start)
        fmt.Printf("请输入终止页( >= 起始页) :")
        fmt.Scan(&end)

        DoWork(start, end)
}

执行结果：

请输入起始页( >= 1) :1   //输入起始页
请输入终止页( >= 起始页) :10  //输入终止页
正在爬取 1 到 10 的页面
url =  http://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=0
url =  http://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=50
url =  http://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=100
url =  http://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=150
url =  http://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=200
url =  http://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=250
url =  http://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=300
url =  http://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=350
url =  http://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=400
url =  http://tieba.baidu.com/f?kw=%E7%BB%9D%E5%9C%B0%E6%B1%82%E7%94%9F&ie=utf-8&pn=450