爬取中国大学排名
import requestsfrom bs4 import BeautifulSoup
import bs4
def getHTMLText(url):
try:
r = requests.get(url,timeout = 30)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return ''
def fillUnivList(ulist,html):
soup = BeautifulSoup(html,'html.parser')
for tr in soup.find('tbody').children:
if isinstance(tr,bs4.element.Tag):#确定tbody的儿子都是标签，无字符串
tds = tr('td')
ulist.append(.string,tds.string,tds.string])
def printUnivlist(ulist,num):
print('{:^10}\t{:^6}\t{:^10}'.format ('排名','学校','分数'))
for i in range(num):
u = ulist
print('{:^10}\t{:^6}\t{:^10}'.format (u,u,u))
def main():
uinfo = []
url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html'
html = getHTMLText(url)
fillUnivList(uinfo,html)
printUnivlist(uinfo,10)
main()
运行一直显示错误，IndexError: list index out of range，请大佬帮忙看一下~ 就是超出索引访问了
页:
[1]