[已解决]为啥这个正则表达式搜索不到东西？？

a1296715528 · 发表于 2018-4-29 20:03:03

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

本帖最后由 a1296715528 于 2018-4-29 22:13 编辑

求大佬解释

import urllib.request as u
import re
import chardet
import os

def openurl(url):
req = u.Request(url)
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 Edge/16.16299')

response = u.urlopen(req)
html = response.read()

return html

def trans(html):
code = chardet.detect(html)['encoding']

if code == 'GB2313' or code == 'gb2313':
      code = 'GBK'

html = html.decode(code)

return html

'''def findname_dict(html):
aim = r'alt="(\w+)"'
aimlist = delrep(re.findall(aim, html))

for each in aimlist:
      print(each)'''

def delrep(list1):
for each in list1[:]:
      if list1.count(each) == 2:
         list1.remove(each)

return list1

def findimg(html):
aim = r' src="([^"]+\.jpg)"'

aimlist = delrep(re.findall(aim, html))
print(len(aimlist))
'''for each in aimlist:
      filename = each.split("/")[-1]
      try:
         a =  u.urlretrieve(each, filename)
      except ValueError:
         pass'''

def main():
url = 'http://www.imomoe.com/'
html = trans(openurl(url))

# findname_dict(html)
findimg(html)

if __name__ == '__main__':
'''os.mkdir('ooxx')
os.chdir('ooxx')'''

main()