Python利用正则提取字符串中数字的方法

1

2

3

4

5

6

7

8

9

10

11

12

import re

text = 'cn_000858'

# 提取所有数字

numbers = re.findall(r'\d+', text)

print(numbers)  # ['000858']

# 如果只需要第一个匹配结果

if numbers:

    result = numbers[0]

    print(result)  # '000858'

1

2

3

4

5

6

7

8

9

import re

text = 'cn_000858'

# 搜索第一个数字序列

match = re.search(r'\d+', text)

if match:

    result = match.group()

    print(result)  # '000858'

1

2

3

4

5

6

7

8

9

import re

text = 'cn_000858'

# 匹配'cn_'后面的数字

match = re.search(r'cn_(\d+)', text)

if match:

    result = match.group(1)  # group(1)获取第一个捕获组

    print(result)  # '000858'

1

2

3

4

5

6

7

8

9

10

11

12

13

14

import re

# 如果字符串中有多个数字

text = 'cn_000858_stock_123'

# 提取所有数字

numbers = re.findall(r'\d+', text)

print(numbers)  # ['000858', '123']

# 提取特定位置的数字

match = re.search(r'cn_(\d+)', text)

if match:

    stock_code = match.group(1)

    print(f"股票代码: {stock_code}")  # '000858'

1

2

3

4

5

6

7

8

9

10

11

12

import re

text = 'cn_000858'

# 使用下划线分割，取最后一部分

parts = text.split('_')

result = parts[-1]

print(result)  # '000858'

# 或者用正则split

result = re.split(r'[^\d]+', text)[-1]

print(result)  # '000858'

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

import re

text = 'cn_000858'

# 提取数字并转换为整数（会去掉前导零）

match = re.search(r'\d+', text)

if match:

    number_str = match.group()

    number_int = int(number_str)

    print(f"字符串: {number_str}, 整数: {number_int}")

    # 输出: 字符串: 000858, 整数: 858

# 如果需要保留前导零，保持字符串形式

result = match.group()

print(f"保留前导零: {result}")  # '000858'

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

import re

def extract_stock_code(text):

    """

    从各种格式中提取股票代码

    """

    # 匹配多种模式: cn_000858, sh600000, sz000001, 000858等

    patterns = [

        r'cn_(\d+)',           # cn_000858

        r'(?:sh|sz)(\d+)',     # sh600000, sz000001

        r'^(\d{6})$',          # 纯数字6位

        r'_(\d{6})',           # 下划线后6位数字

    ]

    for pattern in patterns:

        match = re.search(pattern, text, re.IGNORECASE)

        if match:

            return match.group(1)

    return None

# 测试

test_cases = [

    'cn_000858',

    'sh600000',

    'sz000001',

    '000858',

    'stock_cn_000858_data',

]

for text in test_cases:

    code = extract_stock_code(text)

    print(f"{text:20} -> [code]")

1

2

3

4

5

6

7

8

9

10

11

12

import re

text = 'cn_000858'

# 使用命名捕获组

match = re.search(r'cn_(?P<code>\d+)', text)

if match:

    code = match.group('code')

    print(f"股票代码: [code]")  # '000858'

    # 也可以用groupdict()

    print(match.groupdict())  # {'code': '000858'}

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

import re

# 批量处理多个字符串

texts = [

    'cn_000858',

    'cn_000001',

    'sh600000',

    'sz000002',

]

# 使用列表推导式

codes = [re.search(r'\d+', text).group() for text in texts if re.search(r'\d+', text)]

print(codes)  # ['000858', '000001', '600000', '000002']

# 更安全的方式（处理可能没有数字的情况）

codes = []

for text in texts:

    match = re.search(r'\d+', text)

    if match:

        codes.append(match.group())

print(codes)

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

import re

from typing import Optional, List

class StockCodeExtractor:

    """股票代码提取器"""

    @staticmethod

    def extract(text: str) -> Optional[str]:

        """

        从文本中提取股票代码

        支持格式: cn_000858, sh600000, sz000001, 000858等

        """

        if not text:

            return None

        # 模式列表（按优先级排序）

        patterns = [

            (r'cn_(\d{6})', 1),           # cn_000858

            (r'(?:sh|sz|hk)(\d{6})', 1),   # sh600000, sz000001, hk00700

            (r'^(\d{6})$', 1),             # 纯6位数字

            (r'_(\d{6})', 1),              # 下划线后6位数字

            (r'\b(\d{6})\b', 1),           # 单词边界的6位数字

            (r'\d+', 0),                    # 任意数字（最后备选）

        ]

        for pattern, group_idx in patterns:

            match = re.search(pattern, text, re.IGNORECASE)

            if match:

                code = match.group(group_idx)

                # 验证是否为6位数字（股票代码通常是6位）

                if len(code) == 6 and code.isdigit():

                    return code

                # 如果不是6位但也没有其他匹配，返回它

                elif group_idx == 0:  # 最后一个模式

                    return code

        return None

    @staticmethod

    def extract_all(text: str) -> List[str]:

        """

        提取文本中所有可能的股票代码

        """

        # 提取所有6位数字序列

        codes = re.findall(r'\b\d{6}\b', text)

        return codes

    @staticmethod

    def validate(code: str) -> bool:

        """

        验证股票代码格式

        """

        return bool(re.match(r'^\d{6}$', code))

# 使用示例

if __name__ == "__main__":

    extractor = StockCodeExtractor()

    test_cases = [

        'cn_000858',

        '深南电路 cn_000858',

        'sh600000',

        'sz000001',

        '000858',

        '股票代码: 000858',

        'hk00700',

    ]

    print("单个提取:")

    for text in test_cases:

        code = extractor.extract(text)

        is_valid = extractor.validate(code) if code else False

        print(f"{text:25} -> {code:10} (有效: {is_valid})")

    print("\n批量提取:")

    text = "关注股票: cn_000858, sh600000, sz000001"

    codes = extractor.extract_all(text)

    print(f"文本: {text}")

    print(f"提取的代码: {codes}")

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

import re

import json

def extract_stock_code_from_redis(data_str):

    """

    从Redis读取的数据中提取股票代码

    """

    try:

        # 先尝试解析JSON

        data = json.loads(data_str)

        # 如果是字典，查找包含代码的字段

        if isinstance(data, dict):

            # 尝试常见的字段名

            code_fields = ['code', 'stock_code', 'symbol', 'ts_code']

            for field in code_fields:

                if field in data:

                    code = data[field]

                    # 提取数字部分

                    match = re.search(r'\d+', str(code))

                    if match:

                        return match.group()

            # 如果没有找到，尝试从所有值中提取

            for value in data.values():

                match = re.search(r'\d+', str(value))

                if match and len(match.group()) == 6:

                    return match.group()

        # 如果是字符串，直接提取

        elif isinstance(data, str):

            match = re.search(r'\d{6}', data)

            if match:

                return match.group()

    except json.JSONDecodeError:

        # 如果不是JSON，直接从字符串提取

        match = re.search(r'\d{6}', data_str)

        if match:

            return match.group()

    return None

# 测试

test_data = [

    '{"name": "深南电路", "code": "cn_000858"}',

    '{"ts_code": "000858.SZ", "name": "深南电路"}',

    'cn_000858',

    '000858',

]

for data in test_data:

    code = extract_stock_code_from_redis(data)

    print(f"{data:40} -> 代码: [code]")

1

2

3

4

5

6

7

8

9

10

import re

# 从 'cn_000858' 提取数字

text = 'cn_000858'

result = re.search(r'\d+', text).group()

print(result)  # '000858'

# 或者一行代码

result = re.findall(r'\d+', 'cn_000858')[0]

print(result)  # '000858'