爬虫作业

import csv
import os
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 writercsv(save_road,num,title):
    if os.path.isfile(save_road):
        with open(save_road,'a',newline='')as f:
            csv_write=csv.writer(f,dialect='excel')
            for i in range(num):
                u=AllUniv[i]
                csv_write.writerow(u)
    else:
        with open(save_road,'w',newline='')as f:
            csv_write=csv.writer(f,dialect='excel')
            csv_write.writerow(title)
            for i in range(num):
                u=AllUniv[i]
                csv_write.writerow(u)

title=["排名","学校名称","省市","类型","总分","生源质量","培养结果","科研规模（篇）",\
       "科研质量（FWCI）","顶尖成果（篇）","顶尖人才（人）","科技服务（千元）",\
       "产学研合作（篇）","成果转化（千元）"]
save_road="G:\\排名.csv"
url = 'https://www.shanghairanking.cn/rankings/bcur/202011'
html = getHTMLText(url)
soup = BeautifulSoup(html, "html.parser")
fillUnivList(soup)
writercsv(save_road,30,title)

　　

import requests print('访问百度网站 获取Response对象') r = requests.get("http://www.baidu.com") 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