python爬新闻并保存到csv_python入门 访问网站并将爬回来的数据保存为csv文件

1 import requests2 import csv3 import os4 import codecs5 frombs4 import BeautifulSoup6 allUniv =[]7 def getHTMLText(url):8 try:9 r = requests.get(url, timeout=30)10 r.raise_for_status()11 r.encoding = 'utf-8'

12 returnr.text13 except:14 return ""

15 def fillUnivList(soup):16 data = soup.find_all('tr')17 for tr indata:18 ltd = tr.find_all('td')19 if len(ltd)==0:20 continue

21 singleUniv =[]22 for td inltd:23 singleUniv.append(td.string)24 allUniv.append(singleUniv)25 def printUnivList(num):26 print("{:^4}{:^10}{:^5}{:^8}{:^10}".format("排名","学校名称","省市","总分","培养规模"))27 for i inrange(num):28 u=allUniv[i]29 print("{:^4}{:^10}{:^5}{:^8}{:^10}".format(u[0],u[1],u[2],u[3],u[6]))30

31 def writercsv(save_road,num,title):32 ifos.path.isfile(save_road):33 with open(save_road,'a',newline='')asf:34 csv_write=csv.writer(f,dialect='excel')35 for i inrange(num):36 u=allUniv[i]37 csv_write.writerow(u)38 else:39 with open(save_road,'w',newline='')asf:40 csv_write=csv.writer(f,dialect='excel')41 csv_write.writerow(title)42 for i inrange(num):43 u=allUniv[i]44 csv_write.writerow(u)45

46 title=["排名","学校名称","省市","总分","生源质量","培养结果","科研规模","科研质量","顶尖成果","顶尖人才","科技服务","产学研究合作","成果转化"]47 save_road="F:\\python\csvData.csv"

48 def main():49 url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html'

50 html =getHTMLText(url)51 soup = BeautifulSoup(html, "html.parser")52 fillUnivList(soup)53 printUnivList(10)54 writercsv('F:\\python\csvData.csv',10,title)55 main()