各编程语言做个简单爬虫-526互联

编程语言有很多种，想要全部学会简直天方夜谭，而且每个细分领域有很多要学习的知识，所以对于新手来说一定要专注一个领域学透学扎实了。下面几种语言做的一些简单爬虫，大家可以参考下。

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("net/http")
    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))
}

C语言简单爬虫

#include<stdio.h>
void main()
{
	int a[10],i,j,t;
	for(i=0;i<=9;i++)
	scanf("%d",&a[i]);
	for(i=0;i<9;i++)
		for(j=0;j<9-i;j++)
			if(a[j]>a[j+1])
			{
				t=a[j];
				a[j]=a[j+1];
				a[j+1]=t;
			}
	for(i=0;i<=9;i++)
	printf("%d\t",a[i]);

}

java语言爬虫

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://jshk.com.cn"
         xmlns:xsi="http://jshk.com.cn/mb/reg.asp?kefu=xjy"
         xsi:schemaLocation="http://jshk.com.cn</modelVersion>

    <groupId>org.example</groupId>
    <artifactId>BeCarefulInPrison</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.10.2</version>
        </dependency>
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.51</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.2</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>