各语言简单爬虫

Python 简单爬虫

import requests, re

if __name__ == "__main__":
    r = requests.get('http://docs.python-requests.org/zh_CN/latest/user/quickstart.html')
    r.encoding = "UTF-8"
    print(r.text)  # 用于打印页面内容

    # 正则搜索 .表示任意字符*表示任意个数，group(第一个括号)
    search = re.search('href="#">(.*)</a><ul>', r.text)
    print(search.group(1))

golang简单爬虫

package main

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

func main() {
    resp, _ := http.Get("https://studygolang.com/static/pkgdoc/pkg/net_http.htm")
    defer resp.Body.Close()
    bytes, _ := ioutil.ReadAll(resp.Body)

    re := regexp.MustCompile(`<meta name="private:description" content="(.*)">`)
    b := re.FindSubmatch(bytes)[1]
    fmt.Println(string(b))
}