Examples of best ranking universities - reptiles diary

Examples of crawling

import  requests
from bs4 import  BeautifulSoup
import bs4

def getHTMLText(url): # 这个函数的作用是就是获取url的内容。
    try:
        r=requests.get(url,timeout =30)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except:
        return ''


def fillUnivList(ulist,html):  # 这个函数用来把全部文本中需要的内容提取出来
    soup=BeautifulSoup(html,'html.parser')
    print(soup)
    for tr in soup.find('tbody').children:
        if isinstance(tr,bs4.element.Tag):
            tds=tr('td')
            ulist.append([tds[0].string,tds[1].string,tds[3].string])


def printUnivList(ulist,num): # 用来把提取出来的数据展示出来
    print('{:^10}\t{:^6}\t{:^18}'.format('排名','学校名称','总分'))
    for i in range(num):
        u=ulist[i]
        print('{:^10}\t{:^6}\t{:^18}'.format(u[0],u[1],u[2]))



def main():  # 主函数,调用,用来传入参数,和调用其他函数
    uinfo =[]
    url='http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html'
    html=getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)
main()

Rank School Name Total
1 94.6 Tsinghua University
, Peking University 76.5
3 72.9 Zhejiang University
4 Shanghai Jiaotong University 72.1
5 65.6 Fudan University
6, University of Science and Technology of China 60.9
7 58.9 Huazhong University of Science and Technology
7, Nanjing University, 58.9
9 Sun Yat-sen 58.2
10 56.7 Harbin Institute of Technology
11 Beijing University of Aeronautics and Astronautics 56.3
12 56.2 Wuhan University
13 Tongji 55.7
14 55.0 Xi'an Jiaotong University
15 Sichuan University 54.4
16 Beijing Institute of Technology 54.0
17 53.6 Southeast University
18 Nankai 52.8
19 52.3 Tianjin University
20, South China University of Technology 52.0

Guess you like

Origin www.cnblogs.com/chanyuli/p/11408045.html