爬中国大学排名网站内容

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.com/zuihaodaxuepaiming2018.html'
    html=getHTMLText(url)
    soup=BeautifulSoup(html,"html.parser")
    fillUnivList(soup)
    printUnivList(num)
    #saveUnivData(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)', '学生国际化(留学生比例)']
    name2 = ['a', 'b', 'c']
    test = pd.DataFrame(columns=name, data=list)
    test.to_csv('D:/我的文件/Python作业/CrawUniv.csv', encoding='gbk')

posted @ 2020-05-13 16:32  哦噢  阅读(155)  评论(0编辑  收藏  举报