import re
# re.match() 能够匹配出以xxx开头的字符串
ret = re.match(r"H", "Hello Python")
# print(ret.group())
# 分组
ret = re.match(r"([^-]*)-(\d+)", "010-12345678")
# print(ret.group(1))
# 通过引用分组中匹配到的数据即可，但是要注意是元字符串，即类似 r""这种格式
ret = re.match(r"<([a-zA-Z]*)>\w*</\1>", "<html>hh</html>")
# print(ret.group(0))
# 不仅匹配开头
ret = re.search(r"\d+", "阅读次数为 9999")
# print(ret.group())
# 匹配多个值，并返回一个列表
ret_list = re.findall(r"\d+", "python = 9999, c = 7890, c++ = 12345")
# print(ret_list)
# 匹配并替换多个值，并返回一个列表
ret_list = re.sub(r"\d+", ‘998‘, "python = 997 python = 997")
print(‘ret_list=====: %s‘ % ret_list)
# 匹配并切割
ret_list = re.split(r":| ", "info:xiaoZhang 33 shandong")
# print(ret_list)
# 非贪婪模式。在"*","?","+","{m,n}"后面加上？，使贪婪变成非贪婪。
s = "aa2343ddd"
r = re.match(r"aa(\d+?)", s)
# print(r.group(1))
print(‘111111111111111111‘)
# 匹配：‘http://www.freebuf.com‘,
# url = ‘http://www.freebuf.com‘
url = ‘https://freebuf.com/articles/es/123%e7%b1%b3%e9%9b%aa%e5%84%bf‘
url = ‘http://www.freebuf.com/author/%e7%b1%b3%e9%9b%aa%e5%84%bf‘
# url = ‘http://www.freebuf.com/157843sdf.html‘
# 匹配域名：https://www.freebuf.com
ret_list = re.search(r‘https?://(\w+?\.)+\w+\/?$‘, url)
print(ret_list.group()) if ret_list != None else print(‘ret_list = None‘)
# 匹配文件夹：https://www.freebuf.com/articles/es
ret_list = re.search(r‘https?://(\w+?\.)+\w+(\/\w+)*(\/\w+\/?)$‘, url)
if ret_list != None:
print(ret_list.group())
else:
print(‘ret_list = None‘)
# print(ret_list.group()) if ret_list != None else print(‘ret_list = None‘)
pass
# 匹配文件：http://www.freebuf.com/news/157843.html
ret_list = re.search(r‘https?://(\w+?\.)+\w+(\/\w+)*(\/\w+\.\w+)$‘, url)
print(ret_list.group()) if ret_list != None else print(‘ret_list = None‘)
先编译一次，后面就不编译了
import re str = ‘https://www.freebuf.com/page/357‘ pattern = re.compile(r‘(p|s)\:\/\/www\.(.+?\..+?)\/+?‘, re.DOTALL) match = pattern.findall(str) print(type(match)) print(match)
忽略大小写
在正则表达式前面加(?i)
import re
str1 = """
201.158.69.116 - - [03/Jan/2013:21:17:20 -0600] fwf[-] tip[-] 127.0.0.1:9000 0.007 0.007 MX pythontab.com GET /html/test.html http/1.1 "
200" 2426
"http://a.com" "es-ES,es;q=0.8" "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.97 Safari/537.11"
172.16.119.8 - admin [15/Aug/2011:18:17:50 +0800] "PROPFIND /svn/EAGLE HTtP/1.1" 201 649
172.16.119.8 - admin [15/Aug/2011:18:17:50 +0800] "PROPFIND /svn/EAGLE/!svn/vcc/default HTTP/1.1" 207 401
172.16.119.8 - admin [15/Aug/2011:18:17:50 +0800] "PROPFIND /svn/EAGLE/!svn/bln/31 HTTP/1.1" 207 454
172.16.119.8 - admin [15/Aug/2011:18:17:50 +0800] "PROPFIND /svn/EAGLE HTTP/1.1" 207 649
172.16.119.8 - admin [15/Aug/2011:18:17:50 +0800] "PROPFIND /svn/EAGLE/!svn/vcc/default HTTP/1.1" 207 454
"""
pattern = re.compile(r‘(?i)HTTP/.+?\b[^\d]+?([2345]\d{2})‘, re.DOTALL)
ret = pattern.findall(str1)
print(ret)
点号默认不匹配换行，要想匹配换行，需要设置re.DOTALL
pattern = re.compile(r‘(?i)HTTP/.+?\b[^\d]+?([2345]\d{2})‘, re.DOTALL)