{"id":206,"date":"2023-02-22T22:22:58","date_gmt":"2023-02-22T14:22:58","guid":{"rendered":"https:\/\/www.appblog.cn\/?p=206"},"modified":"2023-04-30T15:28:59","modified_gmt":"2023-04-30T07:28:59","slug":"python-pattern-matching-and-regular-expressions","status":"publish","type":"post","link":"https:\/\/www.appblog.cn\/index.php\/2023\/02\/22\/python-pattern-matching-and-regular-expressions\/","title":{"rendered":"Python\u6a21\u5f0f\u5339\u914d\u4e0e\u6b63\u5219\u8868\u8fbe\u5f0f"},"content":{"rendered":"

\u6a21\u5f0f\u5339\u914d\u6d41\u7a0b<\/h3>\n
    \n
  1. \u7528import re \u5c06\u6b63\u5219\u6a21\u5757\u5bfc\u5165<\/li>\n
  2. \u7528re.complie() \u51fd\u6570\u521b\u5efa\u4e00\u4e2aRegex\u5bf9\u8c61\uff08\u8bb0\u5f97\u662f\u4f7f\u7528\u539f\u59cb\u5b57\u7b26\u4e32\uff09<\/li>\n
  3. \u5411Regex\u5bf9\u8c61\u7684serach()\uff0c\u65b9\u6cd5\u4f20\u5165\u60f3\u67e5\u627e\u7684\u5b57\u7b26\u4e32<\/li>\n
  4. \u8c03\u7528Match\u5bf9\u8c61\u7684group()\uff0c\u8fd4\u56de\u5b9e\u9645\u5339\u914d\u6587\u672c\u7684\u5b57\u7b26\u4e32<\/li>\n<\/ol>\n

    <\/p>\n

    \u521b\u5efa\u6b63\u5219\u8868\u8fbe\u5bf9\u8c61<\/h3>\n

    \u67e5\u627e\u6bb5\u843d\u4e2d\u7684\u7535\u8bdd\u53f7\u7801 \u2018xxx-xxx-xxxx\u2019<\/p>\n

    >>> import re\n>>> phoneNumRegex = re.compile(r'\\d{3}-\\d{3}-\\d{4}')  #\\d \u8868\u793a\u4e00\u4e2a\u6570\u5b57\u5b57\u7b26\n>>> mo = phoneNumRegex.search('My number is 123-456-7890')  #\u5339\u914dRegex\u5bf9\u8c61\n>>> mo.group()\n'123-456-7890'\n>>> print(mo)\n<re.Match object; span=(13, 25), match='123-456-7890'><\/code><\/pre>\n
    re.compile(r'\\d{3}-\\d{3}-\\d{4}').search('My number is 123-456-7890').group()<\/code><\/pre>\n
    \u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u5339\u914d\u66f4\u591a\u6a21\u5f0f<\/h3>\n
    \u5229\u7528\u62ec\u53f7\u5206\u7ec4<\/h4>\n
    >>> phoneNumRegex = re.compile(r'(\\d{3})-(\\d{3}-\\d{4})')\n>>> mo = phoneNumRegex.search('My number is 123-456-7890')\n>>> mo.group()\n'123-456-7890'\n>>> mo.group(1)\n'123'\n>>> mo.group(2)\n'456-7890'\n>>> mo.group(0)\n'123-456-7890'\n>>> mo.groups()\n('123', '456-7890')<\/code><\/pre>\n
    \u5f53\u4f7f\u7528\u62ec\u53f7\u7684\u65f6\u5019( \u548c) \u6765\u8868\u793a<\/p>\n
    >>> phoneNumRegex = re.compile(r'(\\(\\d{3}\\)) (\\d{3}-\\d{4})')\n>>> mo = phoneNumRegex.search('My number is (123) 456-7890')\n>>> mo\n<re.Match object; span=(13, 27), match='(123) 456-7890'>\n>>> mo.group()\n'(123) 456-7890'\n>>> mo.groups()\n('(123)', '456-7890')<\/code><\/pre>\n
    \u5229\u7528\u7ba1\u9053\u6280\u672f\u5206\u7ec4<\/h4>\n
    >>> heroRegex = re.compile(r'Tom|Job')\n>>> mo1 = heroRegex.search('Tom is better Job')\n>>> mo2 = heroRegex.search('Job is better Tom')\n>>> mo1\n<re.Match object; span=(0, 3), match='Tom'>\n>>> mo1.group()\n'Tom'\n>>> mo2.group()\n'Job'<\/code><\/pre>\n
    \u7528 ?<\/code> \u5b9e\u73b0\u53ef\u9009\u5206\u914d<\/h4>\n
    (wo)? \u8868\u793a\u5339\u914d\u65f6\u51fa\u73b0\u96f6\u6b21\u6216\u8005\u4e00\u6b21<\/p>\n
    >>> batRegex = re.compile(r'Bar(wo)?man')\n>>> temp1 = batRegex.search('Barman')\n>>> temp2 = batRegex.search('Barwoman')\n>>> temp1.group()\n'Barman'\n>>> temp2.group()\n'Barwoman'\n>>> temp1\n<re.Match object; span=(0, 6), match='Barman'>\n>>> temp2\n<re.Match object; span=(0, 8), match='Barwoman'><\/code><\/pre>\n
    \u7528 *<\/code> \u5339\u914d\u96f6\u6b21\u6216\u8005\u591a\u6b21<\/h4>\n
    >>> batRegex = re.compile(r'Bar(wo)*man')\n>>> temp1 = batRegex.search('Barman')\n>>> temp2 = batRegex.search('Barwoman')\n>>> temp3 = batRegex.search('Barwowowowoman')\n>>> print(temp1,temp2,temp3)\n<re.Match object; span=(0, 6), match='Barman'>\n<re.Match object; span=(0, 8), match='Barwoman'> \n<re.Match object; span=(0, 14), match='Barwowowowoman'>\n>>> print(temp1.group(),temp2.group(),temp3.group())\nBarman Barwoman Barwowowowoman<\/code><\/pre>\n
    \u7528 +<\/code> \u8868\u793a\u4e00\u6b21\u6216\u8005\u591a\u6b21<\/h4>\n
    >>> batRegex = re.compile(r'Bar(wo)+man')\n>>> temp1 = batRegex.search('Barman')\n>>> temp2 = batRegex.search('Barwoman')\n>>> temp3 = batRegex.search('Barwowowowoman')\n>>> print(temp1,temp2,temp3)\nNone  \n#\u56e0\u4e3atemp1\u4e2d\u5bf9\u5e94\u5b57\u7b26\u4e32\u4e2d\u6ca1\u6709\u5339\u914d\u9879\uff0c\u6240\u4ee5\u4e3a None\n<re.Match object; span=(0, 8), match='Barwoman'> \n<re.Match object; span=(0, 14), match='Barwowowowoman'>\n>>> print(temp2.group(),temp3.group())\nBarwoman Barwowowowoman<\/code><\/pre>\n
    \u4f7f\u7528 { }<\/code> \u5339\u914d\u7279\u5b9a\u6b21\u6570<\/h4>\n
    #(Ha){3} <=> #(Ha)(Ha)(Ha)\n(Ha){3,5} <=> ((Ha)(Ha)(Ha))|(Ha)(Ha)(Ha)(Ha)|(Ha)(Ha)(Ha)(Ha)(Ha)<\/code><\/pre>\n
    >>> haRegex = re.compile(r'(ha){3}')\n>>> mo = haRegex.search('hahaha')\n>>> mo.group()\n'hahaha'\n>>> mo.group(0)\n'hahaha'\n>>> mo.group(1)\n'ha'<\/code><\/pre>\n
    \u8d2a\u5fc3\u548c\u975e\u8d2a\u5fc3\u5339\u914d<\/h3>\n
    >>> import re\n>>> greedyHaRegex = re.compile(r'(Ha){3,5}')\n>>> mo1 = greedyHaRegex.search('HaHaHaHaHa')\n>>> mo1.group()\n'HaHaHaHaHa'\n>>> greedyHaRegex = re.compile(r'(Ha){3,5}?')\n>>> mo2 = greedyHaRegex.search('HaHaHaHaHa')\n>>> mo2.group()\n'HaHaHa'<\/code><\/pre>\n
    findall()<\/code> \u65b9\u6cd5<\/h3>\n
    \u67e5\u627e\u5168\u90e8\u7b26\u5408\u9879<\/p>\n
    >>> phoneNumRegex = re.compile(r'\\d{3}-\\d{3}-\\d{4}')\n>>> mo = phoneNumRegex.findall('Cell:415-555-9999 work: 212-555-1000')\n>>> mo\n['415-555-9999', '212-555-1000']\n>>> phoneNumRegex = re.compile(r'(\\d{3})-(\\d{3})-(\\d{4})')\n>>> mo = phoneNumRegex.findall('Cell:415-555-9999 work: 212-555-1000')\n>>> mo\n[('415', '555', '9999'), ('212', '555', '1000')]<\/code><\/pre>\n
    \u5b57\u7b26\u4e32\u5206\u7c7b<\/h3>\n\n\n\n\n\n\n\n\n\n\n
    \u7f29\u5199\u5b57\u7b26\u7c7b\u578b<\/th>\n\u8868\u793a<\/th>\n<\/tr>\n<\/thead>\n
    \\d<\/td>\n[0-9]<\/td>\n<\/tr>\n
    \\D<\/td>\n[^0-9]<\/td>\n<\/tr>\n
    \\w<\/td>\n\u4efb\u4f55\u5b57\u6bcd\u6570\u5b57\u6216\u8005\u4e0b\u5212\u7ebf<\/td>\n<\/tr>\n
    \\W<\/td>\n\u9664\u5b57\u6bcd\u6570\u5b57\u6216\u8005\u4e0b\u5212\u7ebf\u7684\u4efb\u4f55\u5b57\u7b26<\/td>\n<\/tr>\n
    \\s<\/td>\n\u7a7a\u683c\u3001\u5236\u8868\u7b26\u3001\u6362\u884c\u7b26<\/td>\n<\/tr>\n
    \\S<\/td>\n\u9664\u7a7a\u683c\u3001\u5236\u8868\u7b26\u3001\u6362\u884c\u7b26\u7684\u4efb\u4f55\u5b57\u7b26<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
    >>> xmasRegex = re.compile(r'\\d+\\s\\w+')\n>>> mo = xmasRegex.findall('12 dru, 11 pip, 10 lords, 5 rings')\n>>> mo\n['12 dru', '11 pip', '10 lords', '5 rings']<\/code><\/pre>\n
    \u5efa\u7acb\u81ea\u5df1\u7684\u5b57\u7b26\u5206\u7c7b<\/h3>\n
    >>> vowelRegex = re.compile(r'[123abcefg]')\n>>> mo = vowelRegex.findall('Hello Word 2018!')\n>>> mo\n['e', '2', '1']\n>>> vowelRegex = re.compile(r'[1-5.]')\n>>> mo = vowelRegex.findall('Hello Word 2018.')\n>>> mo\n['2', '1', '.']<\/code><\/pre>\n
    \u5728 []<\/code> \u7684\u524d\u7aef\u52a0\u4e0a ^<\/code>\uff0c\u4ee3\u8868\u53d6\u53cd\uff0c\u9664 []<\/code> \u5185\u5b57\u7b26\u90fd\u53ef\u4ee5\u5339\u914d<\/p>\n
    >>> vowelRegex = re.compile(r'[^123abcefg]')\n>>> mo = vowelRegex.findall('Hello Word 2018.')\n>>> mo\n['H', 'l', 'l', 'o', ' ', 'W', 'o', 'r', 'd', ' ', '0', '8', '.']<\/code><\/pre>\n
    \u63d2\u5165\u5b57\u7b26\u548c\u7f8e\u5143\u5b57\u7b26<\/h3>\n
    \u4e0e\u53d6\u53cd\u4e0d\u540c\uff0c\u8fd9\u91cc\u7684 (r'^xxxx')<\/code> \u662f\u4ee3\u8868\u5339\u914d\u7684\u5b57\u7b26\u4e32\u9700\u8981\u4ee5\u7279\u5b9a\u7684\u5b57\u7b26\u4e32\u5f00\u5934<\/p>\n
    >>> begRegex = re.compile(r'^hello')\n>>> mo = begRegex.search('hello world')\n>>> mo\n<re.Match object; span=(0, 5), match='hello'>\n>>> mo.group()\n'hello'<\/code><\/pre>\n
    \u5982\u679c\u6ca1\u6709\u5339\u914d\u6210\u529f\u7684\u8bdd\uff0c\u8fd4\u56de\u7684\u662f None<\/code><\/p>\n
    >>> begRegex = re.compile(r'^hello')\n>>> mo = begRegex.search('hi world')\n>>> mo == None\nTrue<\/code><\/pre>\n
    \u5f53\u5339\u914d\u4e3a (r'world$')<\/code> \u662f\u4ee3\u8868\u5339\u914d\u7684\u5b57\u7b26\u4e32\u9700\u8981\u4ee5\u7279\u5b9a\u7684\u5b57\u7b26\u4e32\u7ed3\u5c3e<\/p>\n
    >>> begRegex = re.compile(r'world$')\n>>> mo = begRegex.search('hello world')\n>>> mo.group()\n'world'<\/code><\/pre>\n
    \u5f53 (r'^\\d+$')<\/code> \u662f\u4ee3\u8868\u6574\u4e2a\u5b57\u7b26\u4e32\u90fd\u662f\u6570\u5b57<\/p>\n
    >>> begRegex = re.compile(r'^\\d+$')\n>>> mo = begRegex.search('123hello world')\n>>> mo\n>>> mo == None\nTrue<\/code><\/pre>\n
    \u901a\u914d\u5b57\u7b26<\/h3>\n
    \u4f7f\u7528 .(\u53e5\u70b9)<\/code> \u5339\u914d \u7a7a\u683c\u53ca\u6362\u884c<\/code> \u4e4b\u5916\u7684\u4efb\u4f55\u5b57\u7b26<\/h4>\n
    >>> atRegex = re.compile(r'.at')\n>>> atRegex.findall('The cat in the hat sat on the flat mat.')\n['cat', 'hat', 'sat', 'lat', 'mat']<\/code><\/pre>\n
    \u4f7f\u7528 .*<\/code> \u5339\u914d \u6362\u884c<\/code> \u4e4b\u5916\u7684\u4efb\u4f55\u5b57\u7b26<\/h4>\n
    >>> nameRegex = re.compile(r'First Name:(.*) Last Name:(.*)')\n>>> mo = nameRegex.search('First Name:AL Last Name:Sweigart')\n>>> mo.groups()\n('AL', 'Sweigart')\n>>> mo\n<re.Match object; span=(0, 32), match='First Name:AL Last Name:Sweigart'><\/code><\/pre>\n
    \u4f7f\u7528\u53e5\u70b9\u5b57\u7b26\u5339\u914d\u6362\u884c re.DOTALL<\/code><\/h4>\n
    >>> newLineREgex = re.compile(r'.*', re.DOTALL)\n>>> mo = newLineREgex.search("Hi:\\nYes,I can do It.\\nThank you.")\n>>> print(mo.group())\nHi:\nYes,I can do It.\nThank you.\n>>> newLineREgex = re.compile(r'.*')\n>>> mo = newLineREgex.search("Hi:\\nYes,I can do It.\\nThank you.")\n>>> print(mo.group())\nHi:<\/code><\/pre>\n
    \u4e0d\u533a\u5206\u5927\u5c0f\u5199\u7684\u5339\u914d re.I or re.IGNORECASE<\/code><\/h3>\n
    >>> robocop = re.compile(r'robocop', re.I)\n>>> mo = robocop.findall('RobocoproBOCOPRRROBOCOP')\n>>> print(mo)\n['Robocop', 'roBOCOP', 'ROBOCOP']<\/code><\/pre>\n
    \u4f7f\u7528 sub()<\/code> \u65b9\u6cd5\u66ff\u6362\u5b57\u7b26\u4e32<\/h3>\n
    >>> namesRegex = re.compile(r'Agent \\w+')\n>>> namesRegex.sub('CENSORED', 'Agent Alice gave the secret documents to Agent Bob')\n'CENSORED gave the secret documents to CENSORED'<\/code><\/pre>\n
    \u4fdd\u7559\u524d\u4e00\u4e2a\u5b57\u7b26<\/p>\n
    >>> namesRegex = re.compile(r'Agent (\\w)\\w+')\n>>> namesRegex.sub(r'\\1****', 'Agent Alice told Agent Carol that Agent ')\n'A**** told C**** that Agent '<\/code><\/pre>\n
    \u5982\u679c\u60f3\u4fdd\u7559\u4e09\u4e2a\u5b57\u7b26\uff0c\u53ef\u4ee5\u8fd9\u4e48\u505a<\/p>\n
    >>> namesRegex = re.compile(r'Agent (\\w{3})\\w+')\n>>> namesRegex.sub(r'\\1****', 'Agent Alice told Agent Carol that Agent ')\n'Ali**** told Car**** that Agent '<\/code><\/pre>\n
    >>> namesRegex = re.compile(r'(\\d{3})\\d{4}(\\d{4})')\n>>> namesRegex.findall(' tell:15735184252;call:13835213493')\n[('157', '4252'), ('138', '3493')]\n>>> namesRegex.sub(r'\\1****\\2', ' tell:15735184252;call:13835213493')\n' tell:157****4252;call:138****3493'<\/code><\/pre>\n
    \u7ba1\u7406\u590d\u6742\u7684\u6b63\u5219\u8868\u8fbe\u5f0f<\/h3>\n
    re.VERBOSE<\/code> \u8868\u793a\u53ef\u4ee5\u628a\u6b63\u5219\u8868\u8fbe\u5f0f\u5199\u6210\u591a\u884c\uff0c\u5e76\u4e14\u81ea\u52a8\u5ffd\u7565\u7a7a\u683c\u3002<\/p>\n
    >>> namesRegex = re.compile(r'''\n(\\d{3}|\\(\\d{3}\\))?       #area code\n(\\s|-|\\.)?               #separator\n\\d{4}                    #fist 4 digits\n(\\s|-|\\.)?               #separator\n\\d{4}                    #end 4 digits)''', re.VERBOSE)<\/code><\/pre>\n
    \u7ec4\u5408\u4f7f\u7528 re.DOTALL<\/code>\u3001re.VERBOSE<\/code>\u3001re.I<\/code><\/h3>\n
    \u5229\u7528\u7ba1\u9053\u6280\u672f\uff0c\u89e3\u51b3\u53ea\u6709\u4e00\u4e2a\u503c\u4f5c\u4e3a\u7b2c\u4e8c\u53c2\u6570<\/p>\n
    >>> someRegex = re.compile('foo', re.IGNORECASE|re.VERBOSE|re.DOTALL)<\/code><\/pre>\n
    \u5c0f\u9879\u76ee\u2014\u2014\u7535\u8bdd\u53f7\u7801\u548cEmail\u63d0\u53d6\u7a0b\u5e8f<\/h3>\n
    #! python3\nimport sys,pyperclip,re\n\nmailRegex = re.compile(r'''(\n    [a-zA-Z0-9_%+-]+   #username    \n    @                  #\n    [a-zA-Z0-9.-]+     #domain name\n    (\\.[a-zA-Z]{2,4})  #\n    )''', re.VERBOSE)\nphoneRegex = re.compile(r'''\n    \\(?(\\d{3})\\)?\n    (\\s|-|\\.)?\n    (\\d{3})\n    (\\s|-|\\.)\n    (\\d{4})''', re.VERBOSE)\n\ntext = str(pyperclip.paste())\nmatches = []\n#123-456-1234\nfor group in phoneRegex.findall(text):\n    phoneNum = '-'.join([group[0],group[2],group[4]])\n    matches.append(phoneNum)\nfor group in mailRegex.findall(text):\n    matches.append(group[0])\n\nif(len(matches) > 0):\n    pyperclip.copy('\\n'.join(matches))\n    print('Copied to clipboard:')\n    print('\\n'.join(matches))\nelse:\n    print("No found")<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"
    \u6a21\u5f0f\u5339\u914d\u6d41\u7a0b \u7528import re \u5c06\u6b63\u5219\u6a21\u5757\u5bfc\u5165 \u7528re.complie() \u51fd\u6570\u521b\u5efa\u4e00\u4e2aRegex\u5bf9\u8c61\uff08\u8bb0 […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[79],"tags":[],"class_list":["post-206","post","type-post","status-publish","format-standard","hentry","category-python"],"_links":{"self":[{"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/posts\/206","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/comments?post=206"}],"version-history":[{"count":0,"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/posts\/206\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/media?parent=206"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/categories?post=206"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.appblog.cn\/index.php\/wp-json\/wp\/v2\/tags?post=206"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}