import requests
from bs4 import BeautifulSoup
import bs4
def getHTNLText(url):
try:
r=requests.get(url,timeout=30)
r.raise_for_status()
r.encoding=r.apparent_encoding
return r.text
except:
return ' '
def univList(infoList,html):
demo=BeautifulSoup(html,"html.parser")
for tr in demo.find('tbody').children:
if isinstance (tr,bs4.element.Tag):
tds=tr('td')
infoList.append([tds[0].string,tds[1].string,tds[3].string])
def printList(ulist,num):
tplt="{0:^10}\t{1:{3}^10}\t\t{2:^10}"
print(tplt.format("排名","学校名称","总分",chr(12288))) #这一部分的format用法再去查查
for i in range(num):
u=ulist[i]
print(tplt.format(u[0],u[1],u[2],chr(12288)))
def main():
unifo=[]
url='http://zuihaodaxue.com/shengyuanzhiliangpaiming2017.html'
html=getHTNLText(url)
univList(unifo,html)
printList(unifo,10)
main()
from bs4 import BeautifulSoup
import bs4
def getHTNLText(url):
try:
r=requests.get(url,timeout=30)
r.raise_for_status()
r.encoding=r.apparent_encoding
return r.text
except:
return ' '
def univList(infoList,html):
demo=BeautifulSoup(html,"html.parser")
for tr in demo.find('tbody').children:
if isinstance (tr,bs4.element.Tag):
tds=tr('td')
infoList.append([tds[0].string,tds[1].string,tds[3].string])
def printList(ulist,num):
tplt="{0:^10}\t{1:{3}^10}\t\t{2:^10}"
print(tplt.format("排名","学校名称","总分",chr(12288))) #这一部分的format用法再去查查
for i in range(num):
u=ulist[i]
print(tplt.format(u[0],u[1],u[2],chr(12288)))
def main():
unifo=[]
url='http://zuihaodaxue.com/shengyuanzhiliangpaiming2017.html'
html=getHTNLText(url)
univList(unifo,html)
printList(unifo,10)
main()