正則表達式使用

時間 2019-11-20

原文原文鏈接

import re

#  匹配- match從頭匹配 (第一個參數就是正則表達式， 數據) 若是開始不能匹配就匹配失敗
# 正則表達式都是以r字符開始的 -- 牆裂建議
# 返回值就是匹配結果的對象 若是須要獲取對象中的結果就須要.group()
res = re.match(r'ello','ello meizi hello')

# 若是成功匹配 則返回對象 若是沒有匹配結果則返回值爲空
if res:
    print(res.group())
else:
    print("沒有匹配結果")

# 搜索 查找 --- 若是開始不能匹配 則繼續日後搜索 嘗試看可否匹配
res = re.search(r'hello','ello meizi hello')

# 若是成功匹配 則返回對象 若是沒有匹配結果則返回值爲空
if res:
    print(res.group())
else:
    print("沒有匹配結果")
    """match函數和search函數的功能 區別和聯繫"""

In [1]: import re
In [2]: re.match(r"hello","hello").group()
# ----------1. .匹配一個任意字符(除去\n)-----------------------------------------
In [3]: re.match(r".ello","hello").group()
In [4]: re.match(r".ello","Hello").group()
In [5]: re.match(r".ello","1ello").group()
In [6]: re.match(r".ello","&ello").group()
In [7]: re.match(r".ello","\nello").group()  # 出錯
In [14]: re.match(r".ello",".ello").group()
In [15]: re.match(r"\.ello",".ello").group()

------------2. []匹配集合中任意一個字符----------------------------------------
In [8]: re.match(r"[Hh]ello","Hello").group()
In [9]: re.match(r"[Hh]ello","hello").group()
In [10]: re.match(r"[Hh]ello","1ello").group() # 出錯

In [11]: re.match(r"[0123456789]ello","1ello").group()
In [12]: re.match(r"[0123456789]ello","9ello").group()
In [13]: re.match(r"[0123456789]ello","Hello").group()  # 出錯

In [16]: re.match(r"[0123456789]ello","Hello").group()  # 出錯
In [17]: re.match(r"[0123456789]ello","1ello").group()

------------3. [-]匹配範圍內部的任意一個字符-----------------
In [18]: re.match(r"[0-9]ello","1ello").group()
In [19]: re.match(r"[0-35-9]ello","1ello").group()
In [20]: re.match(r"[0-35-9]ello","9ello").group()
In [21]: re.match(r"[0-35-9]ello","4ello").group()  #  出錯
In [22]: re.match(r"[0-9a-zA-Z]ello","4ello").group()
In [23]: re.match(r"[0-9a-zA-Z]ello","aello").group()
In [24]: re.match(r"[0-9a-zA-Z]ello","Hello").group()
In [25]: re.match(r"[0-35-9]ello","9ello").group()
In [26]: re.match(r"[0-35-9]ello","4ello").group()  # 出錯

------------4. [^] 禁止匹配 範圍內部的任意一個字符-----------------

In [27]: re.match(r"[^4]ello","4ello").group()
In [28]: re.match(r"[^4]ello","0ello").group()
In [29]: re.match(r"[^4]ello","9ello").group()

------------5. '\d'匹配一個任意數字字符  '\D'匹配任意個非數字字符 -----------------

In [30]: re.match(r"\dello","9ello").group()
In [31]: re.match(r"\dello","0ello").group()
In [32]: re.match(r"\dello","@ello").group()

In [33]: re.match(r"\Dello","0ello").group()
In [34]: re.match(r"\Dello","@ello").group()
In [35]: re.match(r"\Dello","?ello").group()

------------6. '\s'匹配一個任意空白字符  '\S'匹配一個任意 非空白字符串-------------------------------
In [36]: re.match(r"\Dello"," ello").group()

In [37]: re.match(r"[\t\r\n\v\f ]ello"," ello").group()
In [38]: re.match(r"\sello"," ello").group()
In [39]: re.match(r"\Sello"," ello").group()
In [40]: re.match(r"\Sello","1ello").group()

-----------7. '\w'匹配一個任意單詞字符 '\W'匹配一個任務 非單詞字符-----------------------------
In [41]: re.match(r"\wello","1ello").group()
In [42]: re.match(r"\wello","hello").group()
In [43]: re.match(r"\wello","Hello").group()
In [44]: re.match(r"\wello","_ello").group()
In [45]: re.match(r"\Wello","_ello").group()
In [46]: re.match(r"\Wello","?ello").group()

------------'\w'語義拓展
In [2]: re.match(r"\wBC","ABC")
In [3]: re.match(r"\wBC","ABC").group()
In [4]: re.match(r"\wBC","呵BC").group()
In [5]: re.match(r"\wBC","呵BC",re.ASCII).group()
In [6]: re.match(r"\wBC","呵BC",re.UNICODE).group()
In [7]: re.match(r"\wBC","呵BC").group()


-----------二 量詞  匹配多個字符---------------------------
In [47]: re.match(r"嫦娥號\d升空了","嫦娥1號升空了").group()
In [48]: re.match(r"嫦娥\d號升空了","嫦娥1號升空了").group()
In [49]: re.match(r"嫦娥\d號升空了","嫦娥9號升空了").group()
In [50]: re.match(r"嫦娥\d號升空了","嫦娥10號升空了").group()
In [51]: re.match(r"嫦娥\d\d號升空了","嫦娥10號升空了").group()
In [52]: re.match(r"嫦娥\d\d號升空了","嫦娥99號升空了").group()
In [53]: re.match(r"嫦娥\d\d號升空了","嫦娥100號升空了").group()
In [54]: re.match(r"嫦娥\d\d\d號升空了","嫦娥100號升空了").group()
In [55]: re.match(r"嫦娥\d\d\d\d\d號升空了","嫦娥10000號升空了").group()

In [56]: re.match(r"嫦娥\d{5}號升空了","嫦娥10000號升空了").group()
In [57]: re.match(r"嫦娥\d{3}號升空了","嫦娥10000號升空了").group()
In [58]: re.match(r"嫦娥\d{3}號升空了","嫦娥100號升空了").group()

In [59]: re.match(r"嫦娥\d{1,3}號升空了","嫦娥100號升空了").group()
In [60]: re.match(r"嫦娥\d{1,3}號升空了","嫦娥1號升空了").group()
In [61]: re.match(r"嫦娥\d{1,3}號升空了","嫦娥10號升空了").group()
In [62]: re.match(r"嫦娥\d{1,1}號升空了","嫦娥10號升空了").group()
In [64]: re.match(r"嫦娥\d{0,3}號升空了","嫦娥號升空了").group()

In [65]: re.match(r"嫦娥\d{0,}號升空了","嫦娥號升空了").group()
In [66]: re.match(r"嫦娥\d*號升空了","嫦娥號升空了").group()

In [67]: re.match(r"嫦娥\d{1,}號升空了","嫦娥1號升空了").group()
In [68]: re.match(r"嫦娥\d{1,}號升空了","嫦娥號升空了").group()
In [69]: re.match(r"嫦娥\d{1,}號升空了","嫦娥1000號升空了").group()
In [70]: re.match(r"嫦娥\d+號升空了","嫦娥1000號升空了").group()

In [8]: re.match(r"\w?BC","ABC").group()
In [9]: re.match(r"\w?BC","BC").group()


---------------三 匹配開始^ 和結束位置$--------------------------

In [71]: re.match(r"\w{4,20}@163.com","hello@163.com").group()
In [72]: re.match(r"\w{4,20}@163.com","hello@163Acom").group()
In [73]: re.match(r"\w{4,20}@163\.com","hello@163Acom").group()
In [74]: re.match(r"\w{4,20}@163\.com","hello@163.com").group()
In [75]: re.match(r"\w{4,20}@163\.com","hello@163.com.cn").group()
In [76]: re.match(r"\w{4,20}@163\.com","cc.hello@163.com").group()
In [77]: re.search(r"\w{4,20}@163\.com","cc.hello@163.com").group()
In [78]: re.search(r"\w{4,20}@163\.com","cc.hello@163.com.cn").group()

In [79]: re.search(r"^\w{4,20}@163\.com","cc.hello@163.com.cn").group()
In [80]: re.search(r"^\w{4,20}@163\.com","hello@163.com.cn").group()

In [81]: re.search(r"^\w{4,20}@163\.com$","hello@163.com.cn").group()
In [82]: re.search(r"^\w{4,20}@163\.com$","hello@163.com").group()
In [83]: re.match(r"^\w{4,20}@163\.com","hello@163.com.cn").group()
In [84]: re.match(r"^\w{4,20}@163\.com$","hello@163.com.cn").group()
In [85]: re.match(r"^\w{4,20}@163\.com$","hello@163.com").group()


-------------四 匹配分組 ()將感興趣的數據進行提取------
In [86]: re.match(r"嫦娥(\d+)號升空了","嫦娥1000號升空了").group()
In [87]: re.match(r"嫦娥(\d+)號升空了","嫦娥1000號升空了").group(0)
In [88]: re.match(r"嫦娥(\d+)號升空了","嫦娥1000號升空了").group(1)
In [89]: re.match(r"^(\w{4,20})@(163)\.com$","hello@163.com").group()
In [90]: re.match(r"^(\w{4,20})@(163)\.com$","hello@163.com").group(1)
In [91]: re.match(r"^(\w{4,20})@(163)\.com$","hello@163.com").group(2)

-------(|)匹配其中任何一個表達式而且放入分組中----

In [92]: re.match(r"^(\w{4,20})@(163|qq)\.com$","hello@263.com").group(2)
In [93]: re.match(r"^(\w{4,20})@(163|qq)\.com$","hello@qq.com").group(2)
In [94]: re.match(r"^(\w*)hello(\w*)$","hellohello@qq.com").group(1)


---------------------'\分組編號' 使用某個分組的數據在後面某個位置繼續匹配 ----

In [11]: re.match(r"^\w{4,20}@163.com$|^\w{4,20}@qq.com$","hello@163.com").group()
In [12]: re.match(r"^\w{4,20}@163.com$|^\w{4,20}@qq.com$","hello@qq.com").group()
In [13]: re.match(r"^\w{4,20}@(163|qq).com$","hello@qq.com").group()
In [14]: re.match(r"^\w{4,20}@(163|qq).com$","hello@163.com").group()

In [15]: re.match(r"(\d{3,4})-(\d{6,8})","0755-12345678").group()
In [16]: re.match(r"(\d{3,4})-(\d{6,8})","0755-12345678").group(1)
In [17]: re.match(r"(\d{3,4})-(\d{6,8})","0755-12345678").group(2)

In [18]: re.match(r"(\d{3,4})-(\d{6,8}) \1-\2","0755-12345678 0755-1234567").group(2)
In [19]: re.match(r"(\d{3,4})-(\d{6,8}) \1-\2","0755-12345678 0755-12345678").group()
In [20]: re.match(r"(\d{3,4})-(\d{6,8}) \1-\2","0755-12345678 0755-1234567").group()
In [21]: re.match(r"<(\w+)>","<html>aaa</html>").group(1)
In [22]: re.match(r"<(\w+)>(.*)</\1>","<html>aaa</html>").group(1)
In [23]: re.match(r"<(\w+)>(.*)</\1>","<html>aaa</html2>").group(1)

匹配多個標籤中的數據 
<html><body>hello</body></html>
"""思考問題  如何建立有名分組  如何引用有名分組"""

In [24]: re.match(r"<(\w+)><(\w+)>(.+)</\2></\1>","<html><body>hello</body></html>").group()
In [25]: re.match(r"<(\w+)><(\w+)>(.+)</\2></\1>","<html><body>hello</body></html>").group(1)
In [26]: re.match(r"<(\w+)><(\w+)>(.+)</\2></\1>","<html><body>hello</body></html>").group(2)
In [27]: re.match(r"<(\w+)><(\w+)>(.+)</\2></\1>","<html><body>hello</body></html1>").group(2)
In [28]: re.match(r"<(\w+)><(\w+)>(.+)</\2></\1>","<html><body>hello</body></html1>").group()

In [29]: re.match(r"((\d{3,4})-(\d{6,8}))","0755-12345678").group()
In [30]: re.match(r"((\d{3,4})-(\d{6,8}))","0755-12345678").group(1)
In [31]: re.match(r"((\d{3,4})-(\d{6,8}))","0755-12345678").group(2)
In [32]: re.match(r"((\d{3,4})-(\d{6,8}))","0755-12345678").group(3)

In [34]: re.match(r"((\d{3,4})-(\d{6,8})) \2-\3","0755-12345678 0755-12345678").group()

In [35]: re.match(r"(?P<quhao>\d{3,4})-(?P<zuoji>\d{6,8})","0755-12345678").group()
In [36]: re.match(r"(?P<quhao>\d{3,4})-(?P<zuoji>\d{6,8})","0755-12345678").group(1)
In [37]: re.match(r"(?P<quhao>\d{3,4})-(?P<zuoji>\d{6,8})","0755-12345678").group(2)
In [38]: re.match(r"(?P<quhao>\d{3,4})-(?P<zuoji>\d{6,8})","0755-12345678").group('quhao')
In [39]: re.match(r"(?P<quhao>\d{3,4})-(?P<zuoji>\d{6,8})","0755-12345678").group('zuoji')
In [40]: re.match(r"(?P<quhao>\d{3,4})-(?P<zuoji>\d{6,8}) (?P=quhao)-(?P=zuoji)","0755-12345678 07
    ...: 55-12345678").group()

In [41]: re.match(r"((?P<quhao>\d{3,4})-(?P<zuoji>\d{6,8})) (?P=quhao)-(?P=zuoji)","0755-12345678 
    ...: 0755-12345678").group()


---------------------------re模塊高級函數--------------------------
In [42]: ret = re.search(r"\d+", "閱讀次數爲 9999").group()

In [43]: re.search(r"\d+", "閱讀次數爲 9999").group()
Out[43]: '9999'

In [46]: re.findall(r"\d+", "python = 9999, c = 7890, c++ = 12345")
Out[46]: ['9999', '7890', '12345']

In [47]: re.sub(r"\d+","998","python=997")
Out[47]: 'python=998'

In [48]: re.sub(r"\d+","998","python=997 c=988")
Out[48]: 'python=998 c=998'

In [49]: re.sub(r"\d+","998","python=997 c=988",1)
Out[49]: 'python=998 c=988'

In [52]: def func(matchobj):
    ...:     data = matchobj.group()
    ...:     str_data = str( int(data) + 1)
    ...:     return str_data
    ...: 

In [53]: re.sub(r"\d+",func, "age=17")
Out[53]: 'age=18'

In [54]: data = """
    ...: <div>
    ...:         <p>崗位職責：</p>
    ...: <p>完成推薦算法、數據統計、接口、後臺等服務器端相關工做</p>
    ...: <p><br></p>
    ...: <p>必備要求：</p>
    ...: <p>良好的自我驅動力和職業素養，工做積極主動、結果導向</p>
    ...: <p>&nbsp;<br></p>
    ...: <p>技術要求：</p>
    ...: <p>一、一年以上 Python 開發經驗，掌握面向對象分析和設計，瞭解設計模式</p>
    ...: <p>二、掌握HTTP協議，熟悉MVC、MVVM等概念以及相關WEB開發框架</p>
    ...: <p>三、掌握關係數據庫開發設計，掌握 SQL，熟練使用 MySQL/PostgreSQL 中的一種<br></p>
    ...: <p>四、掌握NoSQL、MQ，熟練使用對應技術解決方案</p>
    ...: <p>五、熟悉 Javascript/CSS/HTML5，JQuery、React、Vue.js</p>
    ...: <p>&nbsp;<br></p>
    ...: <p>加分項：</p>
    ...: <p>大數據，數理統計，機器學習，sklearn，高性能，大併發。</p>
    ...: 
    ...:         </div>"""

In [55]: re.sub(r"<.*>","",data)
Out[55]: '\n\n        \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n        '

In [56]: re.sub(r"<\w+>","",data)
Out[56]: '\n\n        崗位職責：</p>\n完成推薦算法、數據統計、接口、後臺等服務器端相關工做</p>\n</p>\n必備要求：</p>\n良好的自我驅動力和職業素養，工做積極主動、結果導向</p>\n&nbsp;</p>\n技術要求：</p>\n一、一年以上 Python 開發經驗，掌握面向對象分析和設計，瞭解設計模式</p>\n二、掌握HTTP協議，熟悉MVC、MVVM等概念以及相關WEB開發框架</p>\n三、掌握關係數據庫開發設計，掌握 SQL，熟練使用 MySQL/PostgreSQL 中的一種</p>\n四、掌握NoSQL、MQ，熟練使用對應技術解決方案</p>\n五、熟悉 Javascript/CSS/HTML5，JQuery、React、Vue.js</p>\n&nbsp;</p>\n加分項：</p>\n大數據，數理統計，機器學習，sklearn，高性能，大併發。</p>\n\n        </div>'

In [57]: re.sub(r"</?\w+>","",data)
Out[57]: '\n\n        崗位職責：\n完成推薦算法、數據統計、接口、後臺等服務器端相關工做\n\n必備要求：\n良好的自我驅動力和職業素養，工做積極主動、結果導向\n&nbsp;\n技術要求：\n一、一年以上 Python 開發經驗，掌握面向對象分析和設計，瞭解設計模式\n二、掌握HTTP協議，熟悉MVC、MVVM等概念以及相關WEB開發框架\n三、掌握關係數據庫開發設計，掌握 SQL，熟練使用 MySQL/PostgreSQL 中的一種\n四、掌握NoSQL、MQ，熟練使用對應技術解決方案\n五、熟悉 Javascript/CSS/HTML5，JQuery、React、Vue.js\n&nbsp;\n加分項：\n大數據，數理統計，機器學習，sklearn，高性能，大併發。\n\n        '

In [58]: re.sub(r"</?\w+>|\n","",data)
Out[58]: '        崗位職責：完成推薦算法、數據統計、接口、後臺等服務器端相關工做必備要求：良好的自我驅動力和職業素養，工做積極主動、結果導向&nbsp;技術要求：一、一年以上 Python 開發經驗，掌握面向對象分析和設計，瞭解設計模式二、掌握HTTP協議，熟悉MVC、MVVM等概念以及相關WEB開發框架三、掌握關係數據庫開發設計，掌握 SQL，熟練使用 MySQL/PostgreSQL 中的一種四、掌握NoSQL、MQ，熟練使用對應技術解決方案五、熟悉 Javascript/CSS/HTML5，JQuery、React、Vue.js&nbsp;加分項：大數據，數理統計，機器學習，sklearn，高性能，大併發。        '

In [59]: re.sub(r"</?\w+>|\n|&nbsp","",data)
Out[59]: '        崗位職責：完成推薦算法、數據統計、接口、後臺等服務器端相關工做必備要求：良好的自我驅動力和職業素養，工做積極主動、結果導向;技術要求：一、一年以上 Python 開發經驗，掌握面向對象分析和設計，瞭解設計模式二、掌握HTTP協議，熟悉MVC、MVVM等概念以及相關WEB開發框架三、掌握關係數據庫開發設計，掌握 SQL，熟練使用 MySQL/PostgreSQL 中的一種四、掌握NoSQL、MQ，熟練使用對應技術解決方案五、熟悉 Javascript/CSS/HTML5，JQuery、React、Vue.js;加分項：大數據，數理統計，機器學習，sklearn，高性能，大併發。        '

In [60]: re.split(r" ","age=18 name=tom")
Out[60]: ['age=18', 'name=tom']

In [61]: re.split(r" |=","age=18 name=tom")
Out[61]: ['age', '18', 'name', 'tom']

----------------------?號將正則轉化爲非貪婪模式(懶惰模式)-------------------------------

In [62]: re.match(r"(\d+)(\d?)","12345678").group()
Out[62]: '12345678'

In [63]: re.match(r"(\d+)(\d?)","12345678").group(1)
Out[63]: '12345678'

In [64]: re.match(r"(\d+)(\d?)","12345678").group(2)
Out[64]: ''

In [65]: re.match(r"(\d+?)(\d?)","12345678").group(2)
Out[65]: '2'

In [66]: re.match(r"(\d+?)(\d+)","12345678").group(2)
Out[66]: '2345678'

In [67]: re.match(r"(\d+?)(\d+)","12345678").group(1)
Out[67]: '1'

In [68]: re.match(r"(\d+)(\d+)","12345678").group(1)
Out[68]: '1234567'

In [69]: re.match(r"(\d+)(\d+)","12345678").group(2)
Out[69]: '8'
In [70]: url = """<img alt="丁叮c的直播" data-original="https://rpic.douyucdn.cn/live-cover/appCov
    ...: ers/2017/12/27/462253_20171227014914_big.jpg" src="https://rpic.douyucdn.cn/live-cover/ap
    ...: pCovers/2017/12/27/462253_20171227014914_big.jpg" width="283" height="163" style="display
    ...: : block;">"""

In [72]: re.search(r"http.*jpg",url).group()
Out[72]: 'https://rpic.douyucdn.cn/live-cover/appCovers/2017/12/27/462253_20171227014914_big.jpg" src="https://rpic.douyucdn.cn/live-cover/appCovers/2017/12/27/462253_20171227014914_big.jpg'

In [73]: re.search(r"http.*?jpg",url).group()
Out[73]: 'https://rpic.douyucdn.cn/live-cover/appCovers/2017/12/27/462253_20171227014914_big.jpg'



----------------r原生字符串 能夠自動將其中的反斜線 進行轉義----------------------
In [74]: path = "c:\\a\\b"

In [75]: print(path)
c:\a\b

In [76]: path = "c:\a\b\n"

In [77]: print(path)
c:


In [78]: re.match("c:\\a","c:\\a\\b\\c").group()
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-78-c8bbf045c2be> in <module>()
----> 1 re.match("c:\\a","c:\\a\\b\\c").group()

AttributeError: 'NoneType' object has no attribute 'group'

In [79]: re.match("c:\\\\a","c:\\a\\b\\c").group()
Out[79]: 'c:\\a'

In [80]: re.match("c:\\\\a\\\\b\\\\c","c:\\a\\b\\c").group()
Out[80]: 'c:\\a\\b\\c'

In [81]: re.match(r"c:\\a\\b\\c","c:\\a\\b\\c").group()
Out[81]: 'c:\\a\\b\\c'

In [82]: r"c:\\a\\b\\c"
Out[82]: 'c:\\\\a\\\\b\\\\c'