一、正則表示式庫的引用

在python中，你要使用正則表示式，需要引用程式庫re。

import re

二、正則表示式函式說明：

match =》嘗試在字串的開頭運用模式，返回一個match物件，如果沒有匹配則返回None fullmatch =》嘗試對整個字串運用模式，返回一個match物件，如果沒有匹配或部分匹配則返回None search =》 掃描整個字串來匹配模式，返回一個match物件，如果沒有找到匹配則返回None sub =》 找到模式匹配的字串並替換掉。返回替換了的字串 subn =》找到模式匹配的字串並替換掉。 返回替換了的字串和匹配的次數 split =》根據模式匹配來分割字串，返回子字串列表，列表中可能包含空的字串。 findall =》 查詢所有非重疊的匹配，返回的是一個組列表

三、簡單模式的使用

if m is not None: #food of the sea裡面開頭匹配foo： foo print("food of the sea裡面開頭匹配foo：",m.group())
print("") print("匹配多個字串符號|") pattern = "bet|bat|bit" str = "bat" m = re.match(pattern, str) if m is not None: #bat裡面開頭匹配bet|bat|bit = bat print("%s裡面開頭匹配%s = %s"%(str, pattern, m.group()))
m = re.match(pattern, "blt") if m is None: #bat裡面匹配bet|bat|bit = None print("%s裡面開頭匹配%s = %s" % (str, pattern, "None"))
print("") print(".匹配任何單個的字元，除了\\n") pattern = ".end" str = "tend" m = re.match(pattern, "tend") if m is not None: #tend裡面開頭匹配.end = tend print("%s裡面開頭匹配%s = %s"%(str, pattern, m.group()))
str = "end" m = re.match(pattern, str) if m is None: #end裡面開頭匹配.end = None print("%s裡面開頭匹配%s = %s" % (str, pattern, "None"))
str = "\nend" m = re.match(pattern, str) if m is None: #\nend裡面開頭匹配.end = None print("%s裡面開頭匹配%s = %s" % (str, pattern, "None")) print(".不能匹配\\n")
print("") print("建立字串類，[]") pattern = "[cr][23][dp][t2]" str = "c3pt" m = re.match(pattern, str) if m is not None: #c3pt裡面開頭匹配[cr][23][dp][t2] = c3pt print("%s裡面開頭匹配%s = %s" % (str, pattern, m.group()))
str = "c2d2" m = re.match(pattern, str) if m is not None: #c2d2裡面開頭匹配[cr][23][dp][t2] = c2d2 print("%s裡面開頭匹配%s = %s" % (str, pattern, m.group()))
str = "c2dd" m = re.match(pattern, str) if m is None: #c2dd裡面開頭匹配[cr][23][dp][t2] = None print("%s裡面開頭匹配%s = %s" % (str, pattern, "None"))
print("") print("匹配特殊字元") pattern = "\[email protected](\w+\.)?\w+\.com" str = "[email protected]" m = re.match(pattern, str) if m is not None: #[email protected]裡面開頭匹配\[email protected](\w+\.)?\w+\.com = [email protected] print("%s裡面開頭匹配%s = %s" % (str, pattern, m.group())) str = "[email protected]" m = re.match(pattern, str) if m is not None: #[email protected]裡面開頭匹配\[email protected](\w+\.)?\w+\.com = [email protected] print("%s裡面開頭匹配%s = %s" % (str, pattern, m.group())) str = "[email protected]" m = re.match(pattern, str) if m is None: #[email protected]裡面匹配\[email protected](\w+\.)?\w+\.com = None print("%s裡面開頭匹配%s = %s" % (str, pattern, "None"))

四、正則表示式函式的使用

print("") print("re模式匹配函式測試") print("測試fullmatch方法") pattern = ".end" str = "this is the end of film" m = re.fullmatch(pattern, str) if m is None: #this is the end of film裡面整體匹配.end = None print("%s裡面整體匹配%s = %s"%(str, pattern, "None")) str = "tend" m = re.fullmatch(pattern, str) if m is not None: #tend裡面整體匹配.end = tend print("%s裡面整體匹配%s = %s" % (str, pattern, m.group()))
print("") print("測試search方法") str = "this is the dend of film" m = re.search(pattern, str) if m is not None: #this is the dend of film裡面搜尋匹配.end = dend print("%s裡面搜尋匹配%s = %s" % (str, pattern, m.group()))
str = "this is the nd of film" m = re.search(pattern, str) if m is None: #this is the nd of film裡面搜尋匹配.end = None print("%s裡面搜尋匹配%s = %s" % (str, pattern, "None"))
print("") print("測試sub方法") pattern = "[aoe]" str = "mark the amoment" m = re.sub(pattern, "o", str) #mark the amoment被模式[aoe]替換後的字串mork tho omomont print("%s被模式%s替換後的字串%s"%(str, pattern, m)) str = "pip pip pug" m = re.sub(pattern, "o", str) #pip pip pug被模式[aoe]替換後的字串pip pip pug print("%s被模式%s替換後的字串%s"%(str, pattern, m))
print("") print("測試subn方法") pattern = "[aoe]" str = "mark the amoment" m = re.subn(pattern, "o", str) #mark the amoment被模式[aoe]替換後的字串('mork tho omomont', 5) print("%s被模式%s替換後的字串%s"%(str, pattern, m)) str = "pip pip pug" m = re.subn(pattern, "o", str) #pip pip pug被模式[aoe]替換後的字串('pip pip pug', 0) print("%s被模式%s替換後的字串%s"%(str, pattern, m))
print("") print("測試split方法") pattern = "of|the" str = "the book of the school, the nineth." m = re.split(pattern, str) #the book of the school, the nineth.被模式of|the分割後的列表['', ' book ', ' ', ' school, ', ' nineth.'] print("%s被模式%s分割後的列表%s"%(str, pattern, m))
print("") print("測試findall方法") pattern = "of|the" str = "the book of the school, the nineth." m = re.findall(pattern, str) #the book of the school, the nineth.被模式of|the分割後的列表['the', 'of', 'the', 'the'] print("%s被模式%s找到的字串列表%s"%(str, pattern, m))