追追比

导航

爬虫作业 

import requests
for i in range (20):
    print("第",i+1,"次访问")
    r=requests.get("https://www.google.cn/")
    r.encoding='utf-8'
    print("返回状态:",r.status_code)
    print(r.text)
    print("text属性长度：",len(r.text))
    print("content属性长度:",len(r.content))
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8"> 
<title>菜鸟教程(runoob.com)</title> 
</head>
<body>
    <h1>欢迎您的加入123</h1>
    <p>有你想不到的意外哦！</p>
</body>
        <table border="1">
    <tr>
        <td>班级</td>
        <td>19统计</td>
    </tr>
    <tr>
        <td>学号</td>
        <td>15</td>
    </tr>
</table>
</html>
import requests
from bs4 import BeautifulSoup
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("{1:^2}{2:{0}^10}{3:{0}^6}{4:{0}^4}{5:{0}^10}".format(chr(12288),"排名","学校名称","省市","总分","年费"))
    for i in range(num):
        u=allUniv[i]
        print("{1:^4}{2:{0}^10}{3:{0}^5}{4:{0}^8.1f}{5:{0}^11}".format(chr(12288),u[0],u[1],u[2],eval(u[3]),u[11]))
def main():
    url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2018.html'
    html = getHTMLText(url)
    soup = BeautifulSoup(html, "html.parser")
    fillUnivList(soup)
    printUnivList(10)
main()

 

posted on 2020-12-14 16:24  追追比  阅读(48)  评论(0)    收藏  举报