获取中国最好大学列表的解析器。我收到“NoneType”对象没有属性“children”的错误消息:
File "C:/Projects/Beijing Python/Week 2/Unit 06.py", line 22, in fillUnivList for tr in soup.find('tbody').children:
AttributeError: 'NoneType' object has no attribute 'children'
如果我手动检查,“soup.find('tbody').children”语句没问题。怎么了?
import requests
from bs4 import BeautifulSoup
import bs4
def getHTMLText(url):
try:
r = requests.get(url, timeout=30)
r.raise_for_stasus()
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):
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.cn/zuihaodaxuepaiming2016.html'
html = getHTMLText(url)
fillUnivList(uinfo, html)
printUnivList(uinfo, 20)
main()
请您参考如下方法:
我假设您的request 对象没有raise_for_stasus()。这是一个错字 - 它是 raise_for_status()。您也可以使用 status_code。
做
def getHTMLText(url):
try:
r = requests.get(url, timeout=30)
if r.status_code == 200:
r.encoding = r.apparent_encoding
return r.text
except Exception, e:
print (e)
return ""
并将您的find更改为for tr in soup.find('tbody', class_="hidden_zhpm").children:
似乎有效。
