大学排名

import requests
import pandas as pd
import numpy as np
from bs4 import BeautifulSoup
import sqlite3
allUniv=[]
def getHTMLText(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding = 'utf-8'
        return r.text
    except:
        return "error"
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):
    with open(r'D:\mypython\大学排名30.CSV','w') as f:
        f.write("{1:^2}{2:{0}^10}{3:{0}^6}{4:{0}^4}{5:{0}^10}\n".format((chr(12288)),"排名","学校名称","省市","总分","科研服务"))
        for i in range(num):
            u=allUniv[i]
            f.write("{1:^2}{2:{0}^10}{3:{0}^6}{4:{0}^8.1f}{5:{0}^10}\n".format((chr(12288)),i+1,u[1],u[2],eval(u[3]),u[11]))
        f.close()
    if 1:
        print("successful")
    else:
        print("fail")

def main(num):
    url='http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html'
    html = getHTMLText(url)
    soup = BeautifulSoup(html,"html.parser")
    fillUnivList(soup)
    printUnivList(num)

main(500)

大学排名

上一篇:爬虫流程(前面发过的文章的合集)巩固


下一篇:爬取菜谱网站