高效解析多行键值对文本：Python正则表达式实战指南

Package: a4
Version: 1.44.0
Description: Umbrella package is available for the entire Automated
        Affymetrix Array Analysis suite of package.
Maintainer: Laure Cougnaud <<a class="__cf_email__" data-cfemail="ddb1bca8afb8f3beb2a8bab3bca8b99db2adb8b3bcb3bcb1a4a9b4beaef3b8a8" href="/cdn-cgi/l/email-protection">[email protected]</a>>

import requests

url = 'https://bioconductor.org/packages/release/bioc/VIEWS'
response = requests.get(url)
data_text = response.text

# 尝试按双换行符分割记录块
package_list = data_text.split('\n\n')

# 这种方法对于多行值会失败
# package_dict = {
#     package.split(':')[0]: package.split(':')[1] for package in package_list
# }
# 上述代码会因某些行没有冒号而报错，且无法处理多行值

import re
import requests

def parse_metadata_with_regex(url):
    """
    从指定URL获取文本数据，并使用正则表达式解析多行键值对。

    Args:
        url (str): 包含键值对数据的URL。

    Returns:
        list: 包含每个记录块解析结果字典的列表。
    """
    try:
        response = requests.get(url)
        response.raise_for_status()  # 检查HTTP请求是否成功
        data = response.text
    except requests.exceptions.RequestException as e:
        print(f"请求数据失败: {e}")
        return []

    # 编译正则表达式，提高效率并指定匹配模式
    # re.S (DOTALL): 使 '.' 匹配包括换行符在内的所有字符
    # re.M (MULTILINE): 使 '^' 和 '$' 匹配每行的开始和结束
    pat = re.compile(
        r"^([^\s][^:]*): (.+?)\s*(?=^[^\s][^:]*:|\Z)", flags=re.S | re.M
    )

    out = []
    # 首先按双换行符分割成独立的记录块
    for chunk in data.split("\n\n"):
        if chunk.strip():  # 确保块非空
            # 对每个记录块应用正则表达式查找所有键值对
            parsed_chunk = dict(pat.findall(chunk))
            if parsed_chunk: # 只有当成功解析出键值对时才添加
                out.append(parsed_chunk)
    return out

# 示例用法
example_url = "https://bioconductor.org/packages/release/bioc/VIEWS"
parsed_data = parse_metadata_with_regex(example_url)

# 打印前两个解析结果作为示例
if parsed_data:
    print(parsed_data[0])
    print(parsed_data[1])
else:
    print("未能解析任何数据。")

# 预期输出示例 (部分):
# {
#     "Package": "a4",
#     "Version": "1.44.0",
#     "Depends": "a4Base, a4Preproc, a4Classif, a4Core, a4Reporting",
#     "Suggests": "MLP, nlcv, ALL, Cairo, Rgraphviz, GOstats",
#     "License": "GPL-3",
#     "MD5sum": "cc696d3373a9f258d293f2d966da11d5",
#     "NeedsCompilation": "no",
#     "Title": "Automated Affymetrix Array Analysis Umbrella Package",
#     "Description": "Umbrella package is available for the entire Automated\n        Affymetrix Array Analysis suite of package.",
#     "biocViews": "Microarray",
#     "Author": "Willem Talloen [aut], Tobias Verbeke [aut], Laure Cougnaud\n        [cre]",
#     # ... 其他字段
# }