爬虫中国大学排名 

from pip._vendor import requests

print('访问谷歌网站 获取Response对象')
r = requests.get("http://www.google.cn")
x = 1
while x <= 20:
    print('第' + str(x) + '次的返回状态打印：' + str(r.status_code))
    print('第' + str(x) + '次的text()打印：' + str(r.text))
    print('第' + str(x) + '次的text()属性长度打印：' + str(len(r.text)))
    print('第' + str(x) + '次的content属性长度打印：' +str(len(r.content)))
    x += 1

　　

（3）html页面

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>菜鸟教程(runoob.com)</title>
</head>
<body>
<h1>作业1</h1>
<p id="first">作业2</p>

</body>
<table border="1">
    <tr>
        <td>完成！</td>
        <td>赞！</td>
    </tr>
</table>
</html>

　（4）爬中国大学排名网站内容

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 = 'https://www.gpnu.edu.cn/Guangdong polytechnic normal university2020.html'
    html = getHTMLText(url)
    soup = BeautifulSoup(html, "html.parser")
    fillUnivList(soup)
    printUnivList(10)
main()

　　

posted @ 2020-12-14 18:56  陈欢欢  阅读(63)  评论(0)    收藏  举报