GO 爬虫链接

 

1. 正则爬取手机号

结果：

代码：

package main

import (
    "fmt"
    "io/ioutil"
    "net/http"
    "os"
    "regexp"
)

var (
    rePhone = `(1[3456789]d)(d{4})(d{4})`
)

func HandleError(err error, when string) {
    if err != nil {
        fmt.Println(when, err)
        os.Exit(1)
    }
}

func main() {
    //http get请求页面
    resp, err := http.Get("https://www.haomagujia.com/")

    //处理报错
    HandleError(err, "http.Get")

    //读取整体获取的页面内容
    bytes, _ := ioutil.ReadAll(resp.Body)
    html := string(bytes)
    //fmt.Println(html)

    //使用正则表达式对象在网页中过滤出手机号信息
    re := regexp.MustCompile(rePhone)
    //-1 代表匹配全部
    allString := re.FindAllStringSubmatch(html, -1)
    for _, x := range allString {
        fmt.Println(x)
    }

}

2. 正则爬邮箱

结果：

代码

package main

import (
    "fmt"
    "io/ioutil"
    "net/http"
    "os"
    "regexp"
)

var (
    reEmail = `[w.]+@w+.[a-z]{2,3}(.[a-z]{2,3})?`
)

func HandleError(err error, when string) {
    if err != nil {
        fmt.Println(when, err)
        os.Exit(1)
    }
}

func main() {

    html := GetHtml("https://www.douban.com/group/topic/41562980/")

    //模拟邮箱数据
    html += "xiaoming@163.com
"
    html += "aaa@126.com
"
    html += "22223@qq.com
"
    html += "x.badt@gmail.com
"

    re := regexp.MustCompile(reEmail)
    AallString := re.FindAllStringSubmatch(html, -1)
    for _, x := range AallString {
        fmt.Println(x)
    }

}

func GetHtml(url string) string {
    resp, err := http.Get(url)
    HandleError(err, "http.Get")
    bytes, _ := ioutil.ReadAll(resp.Body)
    html := string(bytes)
    return html
}

3. 正则爬超链接

代码：

package main

import (
    "fmt"
    "io/ioutil"
    "net/http"
    "os"
    "regexp"
)

var (
    reLink = `<a[sS]+?href="(http[sS+?])"` //需要根据实际情况书写规则
)

func HandleError(err error, when string) {
    if err != nil {
        fmt.Println(when, err)
        os.Exit(1)
    }
}

func main() {

    html := GetHtml("https://www.hao123.com")

    //爬取超链接
    re := regexp.MustCompile(reLink)
    AallString := re.FindAllStringSubmatch(html, -1)
    for _, x := range AallString {
        fmt.Println(x[0])
    }

}

func GetHtml(url string) string {
    resp, err := http.Get(url)
    HandleError(err, "http.Get")
    bytes, _ := ioutil.ReadAll(resp.Body)
    html := string(bytes)
    return html
}

3. 正则爬身份证号

代码:

package main

import (
    "fmt"
    "io/ioutil"
    "net/http"
    "os"
    "regexp"
)

var (
    //3-30625-1970-04-26-0474
    //reLink = `[1-6]d{5}-(19d{2})|(20(0d)|(1[0-8]))-(0[1-9])|(1[012])-((0[1-9])|([12]d)|(3[01]))-d{3}[dx]` //需要根据实际情况书写规则
    reLink = `[1-6]d{5}((19d{2})|(20((0d)|(1[0-8]))))(0[1-9])|(1[012])((0[1-9])|([12]d)|(3[01]))d{3}[dx]` //需要根据实际情况书写规则

)

func HandleError(err error, when string) {
    if err != nil {
        fmt.Println(when, err)
        os.Exit(1)
    }
}

func main() {

    html := GetHtml("http://www.shaoxing.com.cn/p/2771751.html")

    re := regexp.MustCompile(reLink)
    AallString := re.FindAllStringSubmatch(html, -1)
    for _, x := range AallString {
        fmt.Println(x[0])
    }

}

func GetHtml(url string) string {
    resp, err := http.Get(url)
    HandleError(err, "http.Get")
    bytes, _ := ioutil.ReadAll(resp.Body)
    html := string(bytes)
    return html
}

 完毕