import requests
import bs4
def getHtmlText(url):
try:
r=requests.get(url)
r.raise_for_status()#失败会抛出异常 进入except
r.encoding=r.apparent_encoding
return r.text
except:
return "1"
def fillUnivList(ulist,html):
soup=bs4.BeautifulSoup(html,"html.parser")
for tr in soup.find("tbody").children:#遍历tbody的子节点
if isinstance(tr,bs4.element.Tag):#判断是否为标签 只找标签tr
tds=tr('td') # 将td保存到tds 列表中
ulist.append([tds[0].string,tds[1].string,tds[2].string,tds[3].string])#ulist表 填入元素
def printUnivList(ulist,num):
tplt="{0:^10}\t{1:{3}^8}\t{2:^10}"
print(tplt.format("排名","学校","总分",chr(12288)))#chr(12288) 中文填充 解决中英文填充对齐问题
for i in range(num):
u=ulist[i]
print(tplt.format(u[0],u[1],u[3],chr(12288)))
def main():
uinfo=[]
url="http://www.zuihaodaxue.com/zuihaodaxuepaiming2016.html"
html=getHtmlText(url)
fillUnivList(uinfo,html)
printUnivList(uinfo,20)
main()
来源于MOOC中国大学的Python课程的练习