标签:span ISE ret 技术 cep col 排名 form 科研
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 printUnivList(num): a="广东" print("{1:^2}{2:{0}^10}{3:{0}^6}{4:{0}^4}{5:{0}^10}".format(chr(12288),"排名","学校名称","省市","总分","科研质量")) for i in range(num): u=allUniv[i] #print(u[1]) if a in u: print("{1:^2}{2:{0}^10}{3:{0}^6}{4:{0}^8.1f}{5:{0}^10}".format(chr(12288),i+1,u[1],u[2],eval(u[3]),u[7])) def main(): url=‘http://www.zuihaodaxue.cn/zuihaodaxuepaiming2018.html‘ html = getHTMLText(url) soup = BeautifulSoup(html,"html.parser") fillUnivList(soup) num=len(allUniv) printUnivList(num) main()
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 printUnivList(num): a="广东技术师范学院" print("{1:^2}{2:{0}^10}{3:{0}^6}{4:{0}^4}{5:{0}^10}".format(chr(12288),"排名","学校名称","省市","总分","科研质量")) for i in range(num): u=allUniv[i] #print(u[1]) if a in u: print("{1:^2}{2:{0}^10}{3:{0}^6}{4:{0}^8.1f}{5:{0}^10}".format(chr(12288),i+1,u[1],u[2],eval(u[3]),u[7])) def main(): url=‘http://www.zuihaodaxue.cn/zuihaodaxuepaiming2018.html‘ html = getHTMLText(url) soup = BeautifulSoup(html,"html.parser") fillUnivList(soup) num=len(allUniv) printUnivList(num) main()
标签:span ISE ret 技术 cep col 排名 form 科研
原文地址:https://www.cnblogs.com/hyocheong/p/12927208.html