re匹配

import re

1# # findall:  匹配字符串中所有的符合正则的内容
# lst = re.findall(r"\d+", "我的电话号是:10086, 我女朋友的电话是:10010")
# print(lst)
#
2# # finditer: 匹配字符串中所有的内容[返回的是迭代器], 从迭代器中拿到内容需要.group()
# it = re.finditer(r"\d+", "我的电话号是:10086, 我女朋友的电话是:10010")
# for i in it:
#     # print(i) #<re.Match object; span=(7, 12), match='10086'>
#     print(i.group())

3# # search, 找到一个结果就返回, 返回的结果是match对象. 拿数据需要.group()
# s = re.search(r"\d+", "我的电话号是:10086, 我女朋友的电话是:10010")
# print(s.group())


4# # match是从头开始匹配
# s = re.match(r"\d+", "10086, 我女朋友的电话是:10010")
# print(s.group())

5# # 预加载正则表达式
# obj = re.compile(r"\d+")
#
# ret = obj.finditer("我的电话号是:10086, 我女朋友的电话是:10010")
# for it in ret:
#     print(it.group())
#
# ret = obj.findall("呵呵哒, 我就不信你不换我1000000000")
# print(ret)


6 #re.sub (替换)

import re
a ="https://video.pearvideo.com/mp4/adshort/20210708/1625804543078-15713872_adpkg-ad_hd.mp4"
c =re.sub(r"\d{13}", "你好我是替换的数据", a)
# download_url = re.sub(r"\d{13}", f"cont-{page}", download_url)
print(c) # https://video.pearvideo.com/mp4/adshort/20210708/你好我是替换的数据-15713872_adpkg-ad_hd.mp4

#示例：

s = """
<div class='jay'><span id='1'>郭麒麟</span></div>
<div class='jj'><span id='2'>宋铁</span></div>
<div class='jolin'><span id='3'>大聪明</span></div>
<div class='sylar'><span id='4'>范思哲</span></div>
<div class='tory'><span id='5'>胡说八道</span></div>
"""

# (?P<分组名字>正则) 可以单独从正则匹配的内容中进一步提取内容
obj = re.compile(r"<div class='.*?'><span id='(?P<id>\d+)'>(?P<wahaha>.*?)</span></div>", re.S)  # re.S: 让.能匹配换行符

result = obj.finditer(s)
for it in result:
    print(it.group("wahaha"))
    print(it.group("id"))

 

2 示例二：删除字符串中的符号

#删除字符串中的标点符号 -- re.sub的使用; str.maketrans

import re
import string

data = "Stuning even for the non-gamer: This sound track was beautiful!\
It paints the senery in your mind so well I would recomend\
it even to people who hate vid. game music! I have played the game Chrono \
Cross but out of all of the games I have ever played it has the best music! \
It backs away from crude keyboarding and takes a fresher step with grate\
guitars and soulful orchestras.\
It would impress anyone who cares to listen!"

# Methood 1 : Regex
# Remove the special charaters from the read string.
no_specials_string = re.sub('[!#?,.:";]', '', data)
print(no_specials_string)

# Methood 2 : translate()
# Rake translator object
translator = str.maketrans('', '', string.punctuation)
data = data.translate(translator)
print(data)