|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
在把一个网站多个子网站写进一个列表里一直报错
- import requests
- import re
- def gethtml(url):
- k = {'user-agent':'Mozilla/5.0'}
- r = requests.get(url,headers = k)
- r.status_code
- r.encoding = r.apparent_encoding
- html = r.text
- return html
- def findip(html):
- p = r'(?:(?:[0,1]?\d?\d|2[0-4]\d|25[0-5])\.){3}(?:[0,1]?\d?\d|2[0-4]\d|25[0-5])'
- iplist = re.findall(p,html)
- for each in iplist:
- print(each)
- def main():
- url = []
- for i in range(1,20):
- u = 'http://www.66ip.cn/' + str(i) +'.html'
- url.append(u)
-
- for each in url:
- findip(gethtml(each))
- print('爬取完毕!')
- main()
- input()
复制代码
代码正确缩进啊。。
- import requests
- import re
- def gethtml(url):
- k = {'user-agent':'Mozilla/5.0'}
- r = requests.get(url,headers = k)
- r.status_code
- r.encoding = r.apparent_encoding
- html = r.text
- return html
- def findip(html):
- p = r'(?:(?:[0,1]?\d?\d|2[0-4]\d|25[0-5])\.){3}(?:[0,1]?\d?\d|2[0-4]\d|25[0-5])'
- iplist = re.findall(p,html)
- for each in iplist:
- print(each)
- def main():
- url = []
- for i in range(1,20):
- u = 'http://www.66ip.cn/' + str(i) +'.html'
- url.append(u)
-
- for each in url:
- findip(gethtml(each))
- print('爬取完毕!')
- main()
- input()
复制代码
|
|