python爬取中国大学排名
在学习嵩天老师的爬虫课程中,有出现 ‘NoneType’ object has no attribute 'children’的错误。如果soup_find没有children属性,应该是url传给html中时出现了问题。在检查代码时,发现r.encoding=r.apparent.encoding时少些了一个a,导致html解析不了soup_find().children。
代码如下
import requests
from 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 "出现异常"
def fillUnivList(ulist,html):
soup=BeautifulSoup(html,"html.parser")
for tr in soup.find('tbody').children:
if isinstance(tr,bs4.element.Tag):
tds=tr('td')
ulist.append([tds[0].string,tds[1].string,tds[3].string])
def printUnivList(ulist,num):
print ("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
for i in range(num):
u=ulist[i]
print ("{:^10}\t{:^6}\t{:^10}".format(u[0],u[1],u[2]))
def main():
uinfo=[]
url='http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html'
html=getHTMLText(url)
fillUnivList(uinfo,html)
printUnivList(uinfo,20)
main()