{"id":1117713,"date":"2025-01-08T18:28:31","date_gmt":"2025-01-08T10:28:31","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1117713.html"},"modified":"2025-01-08T18:28:33","modified_gmt":"2025-01-08T10:28:33","slug":"%e5%a6%82%e4%bd%95%e6%8f%90%e5%8f%96%e9%82%ae%e7%ae%b1%e5%9c%b0%e5%9d%80%e5%ad%97%e7%ac%a6%e4%b8%b2python","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1117713.html","title":{"rendered":"\u5982\u4f55\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\u5b57\u7b26\u4e32python"},"content":{"rendered":"

\"\u5982\u4f55\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\u5b57\u7b26\u4e32python\"<\/p>\n

\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\u5b57\u7b26\u4e32\u7684Python\u65b9\u6cd5\u6709\u6b63\u5219\u8868\u8fbe\u5f0f\u3001\u5185\u7f6e\u5b57\u7b26\u4e32\u64cd\u4f5c\u3001\u5229\u7528\u7b2c\u4e09\u65b9\u5e93\u7b49<\/strong>\uff0c\u5176\u4e2d\uff0c\u6b63\u5219\u8868\u8fbe\u5f0f<\/strong>\u662f\u6700\u5e38\u7528\u548c\u6709\u6548\u7684\u65b9\u6cd5\u3002\u901a\u8fc7\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u5e93re<\/code>\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u4ece\u6587\u672c\u4e2d\u63d0\u53d6\u51fa\u90ae\u7bb1\u5730\u5740\u3002\u4e0b\u9762\u662f\u8be6\u7ec6\u63cf\u8ff0\u5982\u4f55\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u5b9e\u73b0\u8fd9\u4e00\u4efb\u52a1\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u90ae\u7bb1\u5730\u5740<\/p>\n<\/p>\n

\u6b63\u5219\u8868\u8fbe\u5f0f\uff08Regex\uff09\u662f\u4e00\u79cd\u5f3a\u5927\u7684\u5de5\u5177\uff0c\u7528\u4e8e\u6a21\u5f0f\u5339\u914d\u548c\u5b57\u7b26\u4e32\u64cd\u4f5c\u3002Python\u7684re<\/code>\u5e93\u63d0\u4f9b\u4e86\u5bf9\u6b63\u5219\u8868\u8fbe\u5f0f\u7684\u652f\u6301\uff0c\u4f7f\u5f97\u6211\u4eec\u80fd\u591f\u8f7b\u677e\u5730\u4ece\u6587\u672c\u4e2d\u63d0\u53d6\u51fa\u7b26\u5408\u7279\u5b9a\u6a21\u5f0f\u7684\u5b57\u7b26\u4e32\uff0c\u5982\u90ae\u7bb1\u5730\u5740\u3002<\/p>\n<\/p>\n

\u5bfc\u5165\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5757<\/h3>\n<\/p>\n

\u9996\u5148\uff0c\u5bfc\u5165Python\u7684re<\/code>\u6a21\u5757\uff1a<\/p>\n<\/p>\n

import re<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5b9a\u4e49\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f<\/h3>\n<\/p>\n
\u5b9a\u4e49\u4e00\u4e2a\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f\u6765\u5339\u914d\u90ae\u7bb1\u5730\u5740\u3002\u901a\u5e38\u60c5\u51b5\u4e0b\uff0c\u90ae\u7bb1\u5730\u5740\u7684\u683c\u5f0f\u4e3ausername@domAI<\/a>n.com<\/code>\uff0c\u5176\u4e2dusername<\/code>\u53ef\u4ee5\u5305\u542b\u5b57\u6bcd\u3001\u6570\u5b57\u3001\u70b9\u3001\u4e0b\u5212\u7ebf\u548c\u7834\u6298\u53f7\uff0cdomain<\/code>\u53ef\u4ee5\u5305\u542b\u5b57\u6bcd\u3001\u6570\u5b57\u548c\u70b9\u3002<\/p>\n<\/p>\n
email_pattern = r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}'<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u7f16\u5199\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\u7684\u51fd\u6570<\/h3>\n<\/p>\n
\u7f16\u5199\u4e00\u4e2a\u51fd\u6570\uff0c\u5229\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u4ece\u6587\u672c\u4e2d\u63d0\u53d6\u6240\u6709\u7684\u90ae\u7bb1\u5730\u5740\u3002<\/p>\n<\/p>\n
def extract_emails(text):<\/p>\n
    return re.findall(email_pattern, text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u793a\u4f8b\u7528\u6cd5<\/h3>\n<\/p>\n
\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff0c\u5c55\u793a\u5982\u4f55\u4f7f\u7528\u4e0a\u8ff0\u51fd\u6570\u4ece\u6587\u672c\u4e2d\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\uff1a<\/p>\n<\/p>\n
text = """<\/p>\n
Hello, you can reach out to us at support@example.com for further assistance.<\/p>\n
Alternatively, contact john.doe123@example.co.uk or jane_doe123@sub.example.org for more information.<\/p>\n
"""<\/p>\n
emails = extract_emails(text)<\/p>\n
print(emails)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u4e2a\u793a\u4f8b\u5c06\u8f93\u51fa\uff1a<\/p>\n<\/p>\n
['support@example.com', 'john.doe123@example.co.uk', 'jane_doe123@sub.example.org']<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u5904\u7406\u590d\u6742\u7684\u6587\u672c<\/p>\n<\/p>\n
\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u6587\u672c\u53ef\u80fd\u4f1a\u66f4\u52a0\u590d\u6742\uff0c\u5305\u542b\u591a\u884c\u3001\u7279\u6b8a\u5b57\u7b26\u7b49\u60c5\u51b5\u3002\u6b63\u5219\u8868\u8fbe\u5f0f\u53ef\u4ee5\u901a\u8fc7\u6dfb\u52a0\u66f4\u591a\u7684\u6a21\u5f0f\u5339\u914d\u89c4\u5219\u6765\u5904\u7406\u8fd9\u4e9b\u590d\u6742\u60c5\u51b5\u3002<\/p>\n<\/p>\n
\u5904\u7406\u591a\u884c\u6587\u672c<\/h3>\n<\/p>\n
\u5982\u679c\u8f93\u5165\u7684\u6587\u672c\u5305\u542b\u591a\u884c\uff0c\u53ef\u4ee5\u4f7f\u7528re.DOTALL<\/code>\u6807\u5fd7\uff0c\u4f7f\u5f97\u70b9\u53f7\uff08.<\/code>\uff09\u53ef\u4ee5\u5339\u914d\u5305\u62ec\u6362\u884c\u7b26\u5728\u5185\u7684\u6240\u6709\u5b57\u7b26\uff1a<\/p>\n<\/p>\n
def extract_emails_multiline(text):<\/p>\n
    return re.findall(email_pattern, text, re.DOTALL)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5904\u7406\u7279\u6b8a\u5b57\u7b26<\/h3>\n<\/p>\n
\u6709\u65f6\uff0c\u90ae\u7bb1\u5730\u5740\u53ef\u80fd\u5305\u542b\u7279\u6b8a\u5b57\u7b26\u6216\u4f4d\u4e8eHTML\u6807\u7b7e\u5185\u3002\u53ef\u4ee5\u901a\u8fc7\u8c03\u6574\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f\u6765\u5904\u7406\u8fd9\u4e9b\u60c5\u51b5\u3002\u4f8b\u5982\uff0c\u5904\u7406HTML\u6807\u7b7e\u5185\u7684\u90ae\u7bb1\u5730\u5740\uff1a<\/p>\n<\/p>\n
email_pattern_html = r'[\\w\\.-]+@[\\w\\.-]+\\.\\w+'<\/p>\n
def extract_emails_from_html(text):<\/p>\n
    return re.findall(email_pattern_html, text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528\u7b2c\u4e09\u65b9\u5e93\u63d0\u53d6\u90ae\u7bb1\u5730\u5740<\/p>\n<\/p>\n
\u9664\u4e86\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\uff0c\u8fd8\u53ef\u4ee5\u5229\u7528\u7b2c\u4e09\u65b9\u5e93\u5982email.utils<\/code>\u548cBeautifulSoup<\/code>\u6765\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\u3002<\/p>\n<\/p>\n
\u4f7f\u7528email.utils<\/h3>\n<\/p>\n
email.utils<\/code>\u6a21\u5757\u63d0\u4f9b\u4e86\u5904\u7406\u7535\u5b50\u90ae\u4ef6\u5730\u5740\u7684\u5de5\u5177\u3002\u53ef\u4ee5\u4f7f\u7528email.utils<\/code>\u6765\u89e3\u6790\u548c\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\uff1a<\/p>\n<\/p>\n
from email.utils import getaddresses<\/p>\n
def extract_emails_with_utils(text):<\/p>\n
    return [addr for name, addr in getaddresses([text]) if '@' in addr]<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4f7f\u7528BeautifulSoup<\/h3>\n<\/p>\n
BeautifulSoup<\/code>\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u7684\u5e93\uff0c\u53ef\u4ee5\u7ed3\u5408\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u63d0\u53d6HTML\u6587\u6863\u4e2d\u7684\u90ae\u7bb1\u5730\u5740\uff1a<\/p>\n<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
def extract_emails_with_soup(html):<\/p>\n
    soup = BeautifulSoup(html, 'html.parser')<\/p>\n
    text = soup.get_text()<\/p>\n
    return extract_emails(text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u793a\u4f8b\u7528\u6cd5<\/h3>\n<\/p>\n
html = """<\/p>\n
<html><\/p>\n
    <body><\/p>\n
        Contact us at <a href="mailto:support@example.com">support@example.com<\/a>.<\/p>\n
        Our team members: <a href="mailto:john.doe@example.com">john.doe@example.com<\/a>, <a href="mailto:jane_doe@example.com">jane_doe@example.com<\/a>.<\/p>\n
    <\/body><\/p>\n
<\/html><\/p>\n
"""<\/p>\n
emails = extract_emails_with_soup(html)<\/p>\n
print(emails)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u4e2a\u793a\u4f8b\u5c06\u8f93\u51fa\uff1a<\/p>\n<\/p>\n
['support@example.com', 'john.doe@example.com', 'jane_doe@example.com']<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u5904\u7406\u8fb9\u754c\u60c5\u51b5<\/p>\n<\/p>\n
\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u4e00\u4e9b\u8fb9\u754c\u60c5\u51b5\uff0c\u5982\u65e0\u6548\u7684\u90ae\u7bb1\u5730\u5740\u6216\u5305\u542b\u975eASCII\u5b57\u7b26\u7684\u90ae\u7bb1\u5730\u5740\u3002\u53ef\u4ee5\u5728\u6b63\u5219\u8868\u8fbe\u5f0f\u4e2d\u6dfb\u52a0\u989d\u5916\u7684\u89c4\u5219\u6765\u5904\u7406\u8fd9\u4e9b\u60c5\u51b5\u3002<\/p>\n<\/p>\n
\u65e0\u6548\u7684\u90ae\u7bb1\u5730\u5740<\/h3>\n<\/p>\n
\u4e3a\u4e86\u8fc7\u6ee4\u6389\u65e0\u6548\u7684\u90ae\u7bb1\u5730\u5740\uff0c\u53ef\u4ee5\u5728\u6b63\u5219\u8868\u8fbe\u5f0f\u4e2d\u6dfb\u52a0\u66f4\u591a\u7684\u7ea6\u675f\u6761\u4ef6\u3002\u4f8b\u5982\uff0c\u786e\u4fdd\u57df\u540d\u90e8\u5206\u5305\u542b\u81f3\u5c11\u4e00\u4e2a\u70b9\u53f7\uff1a<\/p>\n<\/p>\n
email_pattern_strict = r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}'<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u975eASCII\u5b57\u7b26\u7684\u90ae\u7bb1\u5730\u5740<\/h3>\n<\/p>\n
\u5982\u679c\u9700\u8981\u5904\u7406\u5305\u542b\u975eASCII\u5b57\u7b26\u7684\u90ae\u7bb1\u5730\u5740\uff0c\u53ef\u4ee5\u4f7f\u7528re.UNICODE<\/code>\u6807\u5fd7\u6765\u6269\u5c55\u6b63\u5219\u8868\u8fbe\u5f0f\u7684\u5339\u914d\u8303\u56f4\uff1a<\/p>\n<\/p>\n
email_pattern_unicode = r'[^\\s@]+@[^\\s@]+\\.[^\\s@]{2,}'<\/p>\n
def extract_emails_unicode(text):<\/p>\n
    return re.findall(email_pattern_unicode, text, re.UNICODE)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u793a\u4f8b\u7528\u6cd5<\/h3>\n<\/p>\n
text = """<\/p>\n
\u8bf7\u8054\u7cfb\u6211\u4eec\uff1a\u5ba2\u670d\u90ae\u7bb1: support@example.com<\/p>\n
\u56fd\u9645\u5ba2\u6237\u652f\u6301: \u56fd\u9645\u5ba2\u6237@example.\u4e2d\u56fd<\/p>\n
"""<\/p>\n
emails = extract_emails_unicode(text)<\/p>\n
print(emails)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u4e2a\u793a\u4f8b\u5c06\u8f93\u51fa\uff1a<\/p>\n<\/p>\n
['support@example.com', '\u56fd\u9645\u5ba2\u6237@example.\u4e2d\u56fd']<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u603b\u7ed3<\/p>\n<\/p>\n
\u901a\u8fc7\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u548cPython\u7684\u6807\u51c6\u5e93\u51fd\u6570\uff0c\u53ef\u4ee5\u9ad8\u6548\u5730\u4ece\u6587\u672c\u4e2d\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\u3002\u5c3d\u7ba1\u6b63\u5219\u8868\u8fbe\u5f0f\u662f\u6700\u5e38\u7528\u7684\u65b9\u6cd5\uff0c\u4f46\u5728\u5904\u7406\u590d\u6742\u6587\u672c\u6216\u7279\u5b9a\u683c\u5f0f\u7684\u90ae\u7bb1\u5730\u5740\u65f6\uff0c\u7ed3\u5408\u4f7f\u7528\u7b2c\u4e09\u65b9\u5e93\u53ef\u4ee5\u63d0\u4f9b\u66f4\u5f3a\u5927\u7684\u89e3\u51b3\u65b9\u6848\u3002\u65e0\u8bba\u662f\u54ea\u79cd\u65b9\u6cd5\uff0c\u7406\u89e3\u6587\u672c\u7684\u7ed3\u6784\u548c\u90ae\u7bb1\u5730\u5740\u7684\u683c\u5f0f\u662f\u6210\u529f\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\u7684\u5173\u952e\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5728Python\u4e2d\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u5229\u7528re<\/code>\u6a21\u5757\u53ef\u4ee5\u8f7b\u677e\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\u3002\u53ef\u4ee5\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u5339\u914d\u90ae\u7bb1\u7684\u5e38\u89c1\u683c\u5f0f\uff0c\u4f8b\u5982\uff1a[\\w\\.-]+@[\\w\\.-]+<\/code>\u3002\u901a\u8fc7\u7f16\u5199\u7b80\u5355\u7684\u4ee3\u7801\uff0c\u60a8\u53ef\u4ee5\u4ece\u6587\u672c\u5b57\u7b26\u4e32\u4e2d\u63d0\u53d6\u6240\u6709\u7b26\u5408\u683c\u5f0f\u7684\u90ae\u7bb1\u5730\u5740\u3002<\/p>\n
\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\u65f6\u6709\u4ec0\u4e48\u5e38\u89c1\u7684\u9519\u8bef\u9700\u8981\u907f\u514d\uff1f<\/strong>
\u5728\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\u65f6\uff0c\u5e38\u89c1\u9519\u8bef\u5305\u62ec\u4f7f\u7528\u4e0d\u51c6\u786e\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\uff0c\u672a\u8003\u8651\u90ae\u7bb1\u5730\u5740\u4e2d\u53ef\u80fd\u51fa\u73b0\u7684\u7279\u6b8a\u5b57\u7b26\uff08\u5982\u52a0\u53f7\u3001\u4e0b\u5212\u7ebf\u7b49\uff09\uff0c\u4ee5\u53ca\u5ffd\u7565\u6587\u672c\u4e2d\u7684\u5927\u5c0f\u5199\u95ee\u9898\u3002\u786e\u4fdd\u60a8\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\u8db3\u591f\u7075\u6d3b\uff0c\u80fd\u591f\u5339\u914d\u5927\u591a\u6570\u6709\u6548\u7684\u90ae\u7bb1\u683c\u5f0f\u3002<\/p>\n
\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\u540e\uff0c\u5982\u4f55\u5904\u7406\u548c\u5b58\u50a8\u8fd9\u4e9b\u5730\u5740\uff1f<\/strong>
\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\u540e\uff0c\u53ef\u4ee5\u5c06\u5176\u5b58\u50a8\u5728\u5217\u8868\u6216\u5b57\u5178\u4e2d\uff0c\u4ee5\u4fbf\u540e\u7eed\u4f7f\u7528\u3002\u5982\u679c\u9700\u8981\u4fdd\u5b58\u5230\u6587\u4ef6\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u7684csv<\/code>\u6a21\u5757\u6216json<\/code>\u6a21\u5757\u5c06\u90ae\u7bb1\u5730\u5740\u4ee5\u7ed3\u6784\u5316\u683c\u5f0f\u5199\u5165\u6587\u4ef6\u3002\u6b64\u5916\uff0c\u786e\u4fdd\u5728\u5b58\u50a8\u524d\u53bb\u91cd\uff0c\u4ee5\u907f\u514d\u91cd\u590d\u7684\u90ae\u7bb1\u5730\u5740\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u63d0\u53d6\u90ae\u7bb1\u5730\u5740\u5b57\u7b26\u4e32\u7684Python\u65b9\u6cd5\u6709\u6b63\u5219\u8868\u8fbe\u5f0f\u3001\u5185\u7f6e\u5b57\u7b26\u4e32\u64cd\u4f5c\u3001\u5229\u7528\u7b2c\u4e09\u65b9\u5e93\u7b49\uff0c\u5176\u4e2d\uff0c\u6b63\u5219\u8868\u8fbe\u5f0f\u662f\u6700\u5e38\u7528\u548c\u6709 […]","protected":false},"author":3,"featured_media":1117717,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1117713"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1117713"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1117713\/revisions"}],"predecessor-version":[{"id":1117718,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1117713\/revisions\/1117718"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1117717"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1117713"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1117713"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1117713"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}