1、从网络上获得大学排名内容页面
def getHTMLText(url):
try:
r = requests.get(url,timeout = 20)
r.raise_for_status
r.encoding = r.apparent_encoding
return r.text
except:
return ""
2、将页面中信息提取为合适结构:
def fillUnivList(ulist,html):
soup = BeautifulSoup(html,"html.parser")
for tr in soup.find('tbody').children:
if isinstance(tr,bs4.element.Tag): #判断tr是不是bs4.element.Tag
tds = tr('td')
ulist.append([tds[0].string,tds[1].string,tds[3].string])
def printUnivList(ulist,num):
tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}" #{3}用于填充的单个字符,^居中显示,10槽的宽度
print(tplt.format("排名","学校名称","总分",chr(12288))) #chr(12288)用中文填充
for i in range(num):
u = ulist[i]
print(tplt.format(u[0],u[1],u[2],chr(12288)))
然在主函数中调用这三个函数:
def main():
uinfo = []
url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
html = getHTMLText(url)
fillUnivList(uinfo,html)
printUnivList(uinfo,10)
最后记得调用主函数main()哦