https://github.com/r1chardj0n3s/parse

使用范例

  1. from parse import parse
  3. before_data = (
  4.     'cookie=0x9816da8e872d717d, duration=298506.364s, table=0, n_packets=480'
  5.             )   
  7. print(f"before_data: {before_data}")
  8. # before_data: cookie=0x9816da8e872d717d, duration=298506.364s, table=0, n_packets=480
  10. parse_result = parse('cookie={cookie}, duration={duration}, table={table}, n_packets={n_packets}', before_data)
  11. print(f"parse_result: {parse_result}")
  12. # parse_result: <Result () {'cookie': '0x9816da8e872d717d', 'duration': '298506.364s', 'table': '0', 'n_packets': '480'}>
  14. print(f'cookie: {parse_result["cookie"]}')  # cookie: 0x9816da8e872d717d

解析没有定义字段名字的情况

  1. from parse import parse
  4. # 解析没有定义字段名字的情况
  5. before_data_2 = 'I am zaygee, 26 years old' 
  6. parse_2_result = parse("i am {}, {} years old", before_data_2)
  7. print(f"parse_2_result: {parse_2_result}")  
  8. # parse_2_result: <Result ('zaygee', '26') {}>

解析类似字典的实例的情况

  1. from parse import parse
  4. # 解析类似字典的实例的情况
  5. parse_3_result = parse("i am {name}, {age} years old", before_data_2)
  6. print(f"parse_3_result: {parse_3_result}")  
  7. # parse_3_result: <Result () {'name': 'zaygee', 'age': '26'}>
  8. print(parse_3_result["name"])   # zaygee

支持pattern复用

  1. # 支持pattern复用
  2. from parse import compile
  4. pattern = compile("i am {name}, {age} years old")
  6. pattern_result = pattern.parse("I am hoan, 30 years old")
  7. print(f"pattern_result: {pattern_result}")  
  8. # pattern_result: <Result () {'name': 'hoan', 'age': '30'}>
  10. """实战小题： 
  11. user_infos = [
  12.     "username=john, mail=john@baidu.com",
  13.     "username=hoan, mail=hoan@baidu.com",
  14.     "username=zaygee, mail=zaygee@baidu.com",
  15.     "username=poppongj, mail=poppongj@baidu.com",
  16. ]
  17. 现在有一份测试数据 user_infos，需要将以上数据处理为字典输出
  18. 预期结果：
  19.     handle_results = [
  20.         {"username" : "john", "mail": "john@baidu.com"},
  21.         {"username" : "hoan", "mail": "hoan@baidu.com"},
  22.         ...
  23.     ]
  24. """
  25. from parse import compile
  26. import json
  28. user_infos = [
  29.     "username=john, mail=john@baidu.com",
  30.     "username=hoan, mail=hoan@baidu.com",
  31.     "username=zaygee, mail=zaygee@baidu.com",
  32.     "username=poppongj, mail=poppongj@baidu.com",
  33. ]
  34. # user_infos通用匹配规则
  35. user_info_pattern = compile("username={username}, mail={mail}")
  38. # 循环匹配user_infos，并且将匹配结果处理为预期格式添加到handle_results中
  39. handle_results = []
  40. for item in user_infos: 
  42.     pattern_result = user_info_pattern.parse(item)
  43.     print(f"user_info_pattern_result: {pattern_result}")
  45.     handle_results.append(
  46.         {
  47.             "username": pattern_result["username"],
  48.             "mail": pattern_result["mail"]
  49.         }
  50.     )
  51. # 输出预期结果
  52. print(f"handle_results:\n {json.dumps(handle_results, indent=4)}")
  54. # handle_results:
  55. #  [
  56. #     {
  57. #         "username": "john",
  58. #         "mail": "john@baidu.com"
  59. #     },
  60. #     {
  61. #         "username": "hoan",
  62. #         "mail": "hoan@baidu.com"
  63. #     },
  64. #     {
  65. #         "username": "zaygee",
  66. #         "mail": "zaygee@baidu.com"
  67. #     },
  68. #     {
  69. #         "username": "poppongj",
  70. #         "mail": "poppongj@baidu.com"
  71. #     }
  72. # ]

类型转换

更多类型转换见官方：https://github.com/r1chardj0n3s/parse

  1. """
  2. 解析时的类型转换：
  3.     {age:d} --> 将age的值转换为int类型
  4.     {date:tg} --> 将date的值转换为datatime e.g. 20/1/1972 10:21:36 AM +1:00
  5.     {numbers:f} --> 将numbers的值转换为float类型
  6. """
  7. from parse import parse
  10. str_data = "i am zaygee, 20 years old, now is  6/10/2022 11:00 PM, number is 1.444"
  11. str_data_result = parse(
  12.     "i am {name}, {age:d} years old, now is  {date:tg}, number is {num:f}", 
  13.     str_data)
  15. print(f"str_data_result: {str_data_result}")
  16. # str_data_result: <Result () {'name': 'zaygee', 'age': 20, 'date': datetime.datetime(2022, 10, 6, 23, 0), 'num': 1.444}>
  17. print(str_data_result["date"])  # 2022-10-06 23:00:00

去除空格解析

去除两边空格：{name:^} 去除左边空格：{name:>} 去除右边空格：{name:<}

  2. """提取时去除空格"""
  3. space_data = "hello     world    , hello    python    "
  4. space_parse_data = parse("hello {world}, hello {python}", space_data)
  5. print(f"space_parse_data: {space_parse_data}")
  6. # space_parse_data: <Result () {'world': '    world    ', 'python': '   python    '}>
  8. # 提取时去除两边空格：{name:^}
  9. space_parse_data_2 = parse("hello {world:^}, hello {python:^}", space_data)
  10. print(f"space_parse_data_2: {space_parse_data_2}")
  11. # space_parse_data_2: <Result () {'world': 'world', 'python': 'python'}>
  13. # 提取时去除左边空格：{name:>}
  14. left_space_parse_data = parse("hello {world:>}, hello {python:>}", space_data)
  15. print(f"left_space_parse_data: {left_space_parse_data}")
  16. # left_space_parse_data: <Result () {'world': 'world    ', 'python': 'python    '}>
  18. # 提取时去除右边空格： {name: <}
  19. right_space_parse_data = parse("hello {world:<}, hello {python:<}", space_data)
  20. print(f"right_space_parse_data: {right_space_parse_data}")
  21. # right_space_parse_data: <Result () {'world': '    world', 'python': '   python'}>

设置是否大小写敏感

  1. """
  2. 设置大小写敏感
  3. """
  4. case_sensitive_data = "Zaygee, zaygee"
  5. case_parse_results = parse("zaygee, {}", case_sensitive_data)
  6. print(f"case_parse_results: {case_parse_results}")  
  7. # case_parse_results: <Result ('zaygee',) {}>
  9. # 设置大小写敏感
  10. case_parse_results_ = parse("zaygee, {}", case_sensitive_data, case_sensitive=True)
  11. print(f"case_parse_results_: {case_parse_results_}")
  12. # case_parse_results_: None

设置匹配字符数

精准匹配(最大匹配两个字符)：{name:.2}/{:.2}
模糊匹配(最少匹配两个字符)：{name:2}/{:2}

  1. """匹配字符数"""
  3. # 精确匹配：指定最大字符数 {name:.2}/ {:.2}
  4. accurate_match = parse("{name:.2}{age:.2}", "hello")
  5. print(f'accurate_match: {accurate_match}')
  6. # accurate_match: None
  8. accurate_match = parse("{name:.3}{age:.2}", "hello")
  9. print(f'accurate_match: {accurate_match}')
  10. # accurate_match: <Result () {'name': 'hel', 'age': 'lo'}>
  13. # 模糊匹配: 指定最小字符数 {name:2}/{:2}
  14. blurry_match = parse("{name:3}{age:2}", "hello")
  15. print(f"blurry_match: {blurry_match}")
  16. # blurry_match: <Result () {'name': 'hel', 'age': 'lo'}>
  18. # name最少匹配4个字符，age最少匹配2个字符
  19. blurry_match = parse("{name:4}{age:2}", "hello")
  20. print(f"blurry_match: {blurry_match}")
  21. # blurry_match: None
  23. # 精准/模糊匹配 + 类型转换
  24. # name 最少一个字符数，age最少2个字符数
  25. mix_change_type_match = parse("{name:1}, {age:2d}", "zaygee, 30")
  26. print(f"mix_change_type_match: {mix_change_type_match}")
  27. # mix_change_type_match: <Result () {'name': 'zaygee', 'age': 30}>

重要属性

  1. """
  2. 三个重要属性：fixed、named、spans
  4. fixed: 利用位置提取匿名字段的元组
  5. named: 存放有命名的字段的字典
  6. spans: 存放匹配到的字段的位置
  7. """
  9. profile = parse("i am {}, {age} years old", "i am zaygee, 27 years old")
  10. print(f"profile: {profile}")
  11. # profile: <Result ('zaygee',) {'age': '27'}>
  13. print(f"profile fixed: {profile.fixed}")
  14. # profile fixed: ('zaygee',)
  16. print(f'profile named : {profile.named}')
  17. # profile named : {'age': '27'}
  19. print(f'profile spans: {profile.spans}')
  20. # profile spans: {'age': (13, 15), 0: (5, 11)}

自定义类型转换

  1. """
  2. 自定义类型的转换
  4. """
  5. def change_dict(item):
  6.     """将匹配的字符串以字典的形式返回
  7.     params item: 匹配的字符串
  8.     type item: str eg: zaygee
  9.     """
  10.     return {item: item}
  13. customize_data = parse(
  14.     "i am {:change_d}, {:change_d} years old", 
  15.     "i am zaygee, 20 years old", 
  16.     dict(change_d=change_dict)
  17.     )
  18. print(f'customize_data: {customize_data}')
  19. # customize_data: <Result ({'zaygee': 'zaygee'}, {'20': '20'}) {}>