UDP/爬虫/HTML


#接受端代码（更改IP地址即可，其余无须修改）
import socket
#使用IPV4协议，使用UDP协议传输数据
s=socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
#绑定端口和端口号，空字符串表示本机任何可用IP地址
s.bind(('100.100.100.100', 5000)) #更改IP地址即可
while True:
    data, addr=s.recvfrom(1024)
     #显示接收到的内容
    print('received message:{0} from PORT {1} on {2}'.format(data.decode(),addr[1], addr[0]))
    if data.decode().lower() == 'bye':
        break
s.close( )

#接受端代码（更改IP地址即可）
import socket
import sys
s=socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
s.sendto(sys.argv[1].encode() , ("100.100.100.100" ,5000))
#假设100.100.100.100是接收端机器的IP地址
s.close( )

将两段代码制作成PY文件放在桌面

然后就按图中操作即可

——————————————————————————分界线————————————————————————

用requests库的get函数访问360浏览器20遍，打印返回状态，text（）内容，计算text（）属性和content（）属性所返回网页内容的长度

代码

import requests
from bs4 import BeautifulSoup
def getHTMLText(url):
    try:
        r=requests.get(url,timeout=30)
        soup=BeautifulSoup(r.text)
        r.raise_for_status()
        r.encoding='utf-8'
        return r.text,r.status_code,len(r.text),r.encoding,len(soup.text)
    except:
        return ""
    
url="https://www.baidu.com"  #这是一个网页链接，自行更改即可
for i in range(20):
    print(i)
    print(getHTMLText(url))

爬大学排名网页内容

import requests
from bs4 import BeautifulSoup
import csv
import pandas as pd

allUniv=[]

def getHTMLText(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding='utf-8'
        return r.text
    except:
        return ""
    
def fillUnivList(soup):
    data=soup.find_all('tr')
    for tr in data:
        ltd=tr.find_all('td')
        if len(ltd)==0:
            continue
        singleUniv=[]
        for td in ltd:
            singleUniv.append(td.string)
        allUniv.append(singleUniv)
        
def printUnivList(num):
    print("{:^4}{:^10}{:^5}{:^8}{:^10}".format("排名","学校名称","省市","总分","年费"))
    for i in range(num):
        u=allUniv[i]
        print("{:^4}{:^10}{:^5}{:^8}{:^10}".format(u[0],u[1],u[2],u[3],u[6]))
    return u

def main(num):
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2018.html'
    html = getHTMLText(url)
    soup = BeautifulSoup(html, "html.parser")
    fillUnivList(soup)
    printUnivList(num)
    print("结果如上所示")

main(100)

import requests
from bs4 import BeautifulSoup
import csv
allUniv=[]
def getHTMLText (url):
    try:
        r = requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding = 'utf-8'
        return r.text
    except:
        return ""
def fillUnivList (soup):
    data = soup.find_all('tr')
    for tr in data:
        ltd = tr.find_all('td')
        if len(ltd)==0:
            continue
        singleUniv=[]
        for td in ltd:
            singleUniv.append(td.string)
        allUniv.append(singleUniv)
    write_csv(allUniv)
def printUnivList (num):
    print("{:^4}{:^10}{:^5}{:^8}{:^10}". format("排名",\
          "学校名称", "省市","总分","培养规模"))
    for i in range (num):
        u=allUniv[i]
        print("{:^4}{:^10}{:^5}{:^8}{:^10}".format(u[0],\
              u[1],u[2],u[3],u[6]))
    return u
def write_csv(list):
    name = ['排名', '学校名称', '省份', '总分', '生源质量（新生高考成绩得分）', '培养结果（毕业生就业率）', '社会声誉（社会捐赠收入·千元）', '科研规模（论文数量·篇）',\
'科研质量（论文质量·FWCI）', '顶尖成果（高被引论文·篇）', '顶尖人才（高被引学者·人）', '科技服务（企业科研经费·千元）', '成果转化（技术转让收入·千元）']
    with open('C:/Users/86188/Desktop/新建文件夹/最好大学排名.csv', 'w') as f:
        writer = csv.writer(f)
        writer.writerow(name)
        for row in list:
            writer.writerow(row)
def main (num) :
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText (url)
    soup = BeautifulSoup(html, "html.parser")
    fillUnivList(soup)
    printUnivList(num)
    print("排名情况如上所示")
main(100)

结果如下

——————————————————————————分界线————————————————————————

HTML之初学习

<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>lalalalalala(lalalalala.com)</title>
</head>
<body>

<h1>HTML初尝试</h1>
<p>3132 啦啦啦啦啦。</p>

</body>
</html>

posted on 2020-05-13 11:27 动物园天下第一阅读(328) 评论(0) 编辑收藏举报