# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
(?: # 采用非捕获括号进行分组（非必要不使用捕获型括号）
```[\s\S]*?``` # 采用非贪婪匹配（必须），匹配0到n次空白或非空白字符（任意字符）
) # 结束第一个分支
| # 或符号
(?: # 同上，采用非捕获型括号
~~~[\s\S]*?~~~ # 同上，非贪婪匹配来匹配0到n次空白或非空白字符
) # 结束第二个分支
"""
test_str = ("// 1. 匹配四个空格导出的代码块\n\n"
" functino(asfd)\n"
" safdsadf\n"
" safsadf\n"
" safdsdaf\n\n\n\n"
"// 2. 匹配三个反引号所引出的代码块\n"
"```\n"
" func function(){\n"
" }\n"
"```\n\n"
"这里是一些文本\n"
"……\n"
"………………\n\n"
"``` python\n"
" print(\"hello\")\n"
"```\n\n"
"// 3.如果四个空格之前的一行不是回车独占一行，则不会导出代码块（符合Markdown约定）\n"
" functino(asfd)\n"
" safdsadf\n"
" safsadf\n"
" safdsdaf\n"
"safd\n\n"
"// 4. 匹配三个波浪号导出的代码块\n\n"
"~~~\n"
" fmt.println(123)\n"
"~~~\n\n"
"// 5. 匹配前后四个及以上反引号导出的代码块\n"
"````\n"
"aaa\n"
"```\n"
"````\n\n"
"这里是一些文本……\n\n"
"`````\n"
" print(\"this is a code block\")\n"
"`````\n\n"
"// 6. 匹配前后四个及以上波浪号导出的代码块\n"
"~~~~\n"
"aaa\n"
"~~~\n"
"~~~~\n\n"
"这里是一些文本……\n\n"
"~~~~~~\n"
" print(\"this is a code block\")\n"
"~~~~~~\n")
subst = ""
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.MULTILINE | re.VERBOSE)
if result:
print (result)
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html