Python 正则表达式：从特定起始文本行高效提取数字范围数据

Active Stages - U: 1-18, L: 1-23
Passive Stages - U: 19-23
Attachments provided for stages - U: 1, 14; L: 1
Another Passive Stages - L: 1-5, U: 6-10

import re

# 示例文本数据
sample_text = """Active Stages - U: 1-18, L: 1-23
Passive Stages - U: 19-23
Attachments provided for stages - U: 1, 14; L: 1
Another Passive Stages - L: 1-5, U: 6-10"""

# 编译正则表达式，用于匹配 'U:' 或 'L:' 后跟数字或数字范围
# \b: 单词边界
# ([UL]): 捕获 'U' 或 'L'
# :\s*: 匹配冒号和零或多个空格
# (\d+(?:-\d+)*): 捕获数字或数字范围 (如 '1', '1-18')
data_pattern = re.compile(r"\b([UL]):\s*(\d+(?:-\d+)*)")

# 目标行起始文本
target_prefix_1 = "Passive Stages"
target_prefix_2 = "Attachments provided for stages"

print(f"--- 从以 '{target_prefix_1}' 开头的行中提取数据 ---")
extracted_data_list_1 = []

# 逐行处理文本
for line in sample_text.splitlines(False):
    # 检查行是否以目标前缀开始
    if line.startswith(target_prefix_1):
        print(f"\n匹配到行: {line}")
        # 在当前行中查找所有匹配项
        matches = data_pattern.findall(line)
        if matches:
            # 将匹配结果组织成字典，其值是列表，以处理同一行中多个相同类型（如多个U:）的情况
            line_parsed_data = {}
            for data_type, data_value in matches:
                line_parsed_data.setdefault(data_type, []).append(data_value)
            extracted_data_list_1.append(line_parsed_data)
            print(f"提取数据: {line_parsed_data}")
        else:
            print("未找到匹配数据。")

print("\n所有从 'Passive Stages' 行中提取的数据集合:")
for data_item in extracted_data_list_1:
    print(data_item)

print(f"\n--- 从以 '{target_prefix_2}' 开头的行中提取数据 ---")
extracted_data_list_2 = []

for line in sample_text.splitlines(False):
    if line.startswith(target_prefix_2):
        print(f"\n匹配到行: {line}")
        matches = data_pattern.findall(line)
        if matches:
            line_parsed_data = {}
            for data_type, data_value in matches:
                line_parsed_data.setdefault(data_type, []).append(data_value)
            extracted_data_list_2.append(line_parsed_data)
            print(f"提取数据: {line_parsed_data}")
        else:
            print("未找到匹配数据。")

print("\n所有从 'Attachments provided for stages' 行中提取的数据集合:")
for data_item in extracted_data_list_2:
    print(data_item)

--- 从以 'Passive Stages' 开头的行中提取数据 ---

匹配到行: Passive Stages - U: 19-23
提取数据: {'U': ['19-23']}

匹配到行: Another Passive Stages - L: 1-5, U: 6-10
提取数据: {'L': ['1-5'], 'U': ['6-10']}

所有从 'Passive Stages' 行中提取的数据集合:
{'U': ['19-23']}
{'L': ['1-5'], 'U': ['6-10']}

--- 从以 'Attachments provided for stages' 开头的行中提取数据 ---

匹配到行: Attachments provided for stages - U: 1, 14; L: 1
提取数据: {'U': ['1', '14'], 'L': ['1']}

所有从 'Attachments provided for stages' 行中提取的数据集合:
{'U': ['1', '14'], 'L': ['1']}