import re

# re.match() 從字符串的開始進行匹配,如果開始部分匹配成功就返回匹配對象,否則返回None
m = re.match('foo', 'food')  # 返回匹配對象
print(m)  # <_sre.SRE_Match object; span=(0, 3), match='foo'>

m = re.match('foo', 'fas')
print(m)  # None

# re.search() 掃描字符串,如果找到匹配就返回匹配對象,否則返回None
m = re.search('foo','hellofood')
print(m)

m = re.search('foo','hello')
print(m)

# re.findall() 查找所有匹配,返回所有匹配結果的列表
m = re.findall('ab','abcdabcdabcd')
print(m)

# re.finditer() 查找所有匹配,返回所有匹配結果的一個iterator
m = re.finditer('ab', 'abcdabcdabcd')
print(m)
for i in m:
    # print(i)
    print(i.group())

# re.sub() 用于替換匹配的字符串。將匹配到的字符串替換為另一個字符串
text = 'yeah, but no, but yeah, but no'
print(re.sub('but','AND',text))

re.match(pattern, string)

# .匹配任意一個字符 除了\n
ret = re.match('.','M')
print(ret.group())

ret = re.match('t.o', 'two')
print(ret.group())

ret = re.match('h', 'hellopython')
print(ret.group())

ret = re.match('H', 'Hellopython')
print(ret.group())

# 匹配[]中列舉的字符
ret = re.match('[hH]', 'hellopython')
print(ret.group())

ret = re.match("[hH]ello Python","Hello Python")
print(ret.group())

ret = re.match("[0123456789]Hello Python","6Hello Python")
print(ret.group())

ret = re.match("[0-9]Hello Python","6Hello Python")
print(ret.group())

# [a-z], [0-9],[a-zA-Z],[0-35-9]0到3和5到9
ret = re.match("[0-35-9]Hello Python","6Hello Python")
print(ret.group())

# 5[3-9] 匹配 53 到 59。
# 6[0-1] 匹配 60 到 61。
pattern = r'^(5[3-9]|6[0-1])Hello Python'
text = "57Hello Python"
ret = re.match(pattern, text)
print(ret.group() if ret else "No match")

# \d 匹配數字，即0-9
ret = re.match("python\d","python2停止維護了")
print(ret.group())

ret = re.match("python\d","python3發布了")
print(ret.group())

# \D 匹配非數字，即不是數字
ret = re.match('\D','f')
print(ret.group())

# \s 匹配空白，即空格 tab鍵
ret = re.match("hello\sworld", "hello world")
print(ret.group())

# ret = re.match('hello\sword','hello\tworld')  # 這句話會報錯 二者不匹配
ret = re.match("hello\sworld", "hello\tworld")
print(ret.group())
ret2 = re.match("hello\sworld", "hello\tworld")
if ret2:
    print("雙引號匹配成功:", ret2.group())  # 輸出: hello\tworld
else:
    print("雙引號匹配失敗")

# \S 匹配非空白
match_obj = re.match("hello\Sworld", "hello&world")
if match_obj:
    result = match_obj.group()
    print(result)
else:
    print("匹配失敗")

match_obj = re.match("hello\Sworld", "hello$world")
if match_obj:
  result = match_obj.group()
  print(result)
else:
    print("匹配失敗")

# \w 匹配非特殊字符，即a-z A-Z 0-9 _ 漢字
match_obj = re.match("\w", "A")
if match_obj:
  # 獲取匹配結果
  print(match_obj.group())
else:
  print("匹配失敗")

# \W 匹配特殊字符 即非字母 非數字 非漢字
match_obj = re.match("\W", "&")
if match_obj:
  # 獲取匹配結果
  print(match_obj.group())
else:
  print("匹配失敗")

# * 匹配前一個字符出現0次或者無限次
ret = re.match("[A-Z][a-z]*","M")
print(ret.group())

ret = re.match("[A-Z][a-z]*","MnnM")
print(ret.group())

ret = re.match("[A-Z][a-z]*","Aabcdef")
print(ret.group())

# + 匹配前一個字符出現1次或者無限次
match_obj = re.match("py.+n", "python")
if match_obj:
  print(match_obj.group())
else:
  print("匹配失敗")

# ？匹配前一個字符出現1次或者0次 要么有1次要么沒有
match_obj = re.match("https?", "http")
if match_obj:
  print(match_obj.group())
else:
  print("匹配失敗")

# {m}匹配前一個字符出現m次
ret = re.match("[a-zA-Z0-9_]{6}","12a3g45678")
print(ret.group())

# {m,n}匹配前一個字符出現從m到n次
ret = re.match("[a-zA-Z0-9_]{8,20}","1a2b3c4d5e6f7g8h9ijklmn")
print(ret.group())

info = "<div>1111</div><div>2222</div>"

# 貪婪模式
ret = re.match("<div>.*</div>", info)
print(ret.group())

# 非貪婪模式
ret = re.match("<div>.*?</div>", info)
print(ret.group())

# 匹配開頭結尾
# ^ 匹配字符串開頭  \d 以數字開頭復習： .代表任意 *代表多次
ret = re.match("^\d.*", "6hello")
print(ret.group())

# $匹配字符串結尾  \d以數字結尾
ret = re.match(".*\d$", "hello6")
print(ret.group())

ret = re.match("^\d.*\d$", "6hello6")
print(ret.group())

# [^指定字符] 表示除了指定字符都匹配
ret = re.match("[^aeiou]", 'ah')
print(ret.group() if ret else "匹配失敗")

# 或的使用
ret = re.match("mysql|flask","python")
print(ret.group() if ret else "匹配失敗")

# 分組的使用 (ab)    將括號中字符作為一個分組
# \w{4,10} 4-10個字符
ret = re.match("\w{4,10}@(163|126|qq|gmail)\.com","hello@qq.com")
# ret = re.match("\w{4,10}@(163|126|qq|gmail)\.com","llo@qq.com")
print(ret.group() if ret else "匹配失敗")

ret = re.match(".+:1\d{4,10}", "電話:10086")
print(ret.group() if ret else "匹配失敗")