源码
import requests
import bs4
from bs4 import BeautifulSoup
def getHTMLText(url):
try:
r = requests.get(url,timeout = 30)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
print(chucuo)
def fillUnivList(ulist,html):
soup = BeautifulSoup(html,"html.parser")
for tr in soup.find('tbody').children:
if isinstance(tr,bs4.element.Tag): #需bs4库,如果参数不是一个给定类型的对象，返回假
tds = tr('td')
ulist.append([tds[0].sting,tds[1].sting,tds[3].sting])
def printUnivList(ulist,num):
print("{:^10}\t{:^6}\t{:^10}".format("排名","学校","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()可能原因分析：
soup.find(‘tbody’).children: ‘tbody’内容出错，尝试输出 tbody
def fillUnivList(ulist,html):
soup = BeautifulSoup(html,"html.parser")
print(1)
print(soup.find('tbody'))
print(3)输出为
1
None
3
即未搜索到 tbody 结果
确认 r.text 内容
def getHTMLText(url):
try:
r = requests.get(url,timeout = 30)
r.raise_for_status()
r.encoding = r.apparent_encoding
print(1)
print(r.text)
print(3)
return r.text输出
1
Your browse does not support frame!
3
即 r.text出错
有信息输出，表示网页已成功连接上，
>>> import requests
>>> r = requests.get("http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html")
>>> r.status_code
200
>>> r.encoding
'ISO-8859-1'
>>> r.encoding = r.apparent_encoding
>>> r.encoding
'ascii'
>>> r.text
'<html><frameset> <frame id=\'top\' src="http://192.168.0.29/disable/disable.htm"><noframes> <body>Your browse does not support frame!</body> </noframes> </frameset> </html>'
>>> 1、网址更改为百度 返回正常；2、网址在浏览器打开正常；3、网站没有robot协议，不存在爬虫受限情况；4、浏览器打开”http://www.zuihaodaxue.cn/“, 发现被管理员禁止了，公司禁网了，就是不知道为什么它的下阶网站不禁；
1327
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
