{"id":1089836,"date":"2025-01-08T13:57:04","date_gmt":"2025-01-08T05:57:04","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1089836.html"},"modified":"2025-01-08T13:57:08","modified_gmt":"2025-01-08T05:57:08","slug":"python%e5%a6%82%e4%bd%95%e6%8a%93%e5%8f%96%e6%89%8b%e6%9c%ba%e5%8f%b7%e7%a0%81-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1089836.html","title":{"rendered":"python\u5982\u4f55\u6293\u53d6\u624b\u673a\u53f7\u7801"},"content":{"rendered":"

\"python\u5982\u4f55\u6293\u53d6\u624b\u673a\u53f7\u7801\"<\/p>\n

\u5728Python\u4e2d\u6293\u53d6\u624b\u673a\u53f7\u7801\uff0c\u53ef\u4ee5\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u3001BeautifulSoup\u3001Scrapy\u7b49\u5de5\u5177\u3002\u6b63\u5219\u8868\u8fbe\u5f0f\u3001BeautifulSoup\u3001Scrapy\u7b49\u5de5\u5177\u90fd\u53ef\u4ee5\u7528\u6765\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u624b\u673a\u53f7\u7801\u3002<\/strong>\u5728\u672c\u6587\u4e2d\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u6bcf\u79cd\u65b9\u6cd5\u7684\u4f7f\u7528\u53ca\u5176\u4f18\u7f3a\u70b9\uff0c\u5e76\u901a\u8fc7\u793a\u4f8b\u4ee3\u7801\u5e2e\u52a9\u4f60\u66f4\u597d\u5730\u7406\u89e3\u548c\u5e94\u7528\u8fd9\u4e9b\u65b9\u6cd5\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u6b63\u5219\u8868\u8fbe\u5f0f<\/h3>\n<\/p>\n

\u6b63\u5219\u8868\u8fbe\u5f0f\u662f\u4e00\u79cd\u5f3a\u5927\u7684\u6587\u672c\u5339\u914d\u5de5\u5177\uff0c\u53ef\u4ee5\u7528\u6765\u5339\u914d\u7279\u5b9a\u683c\u5f0f\u7684\u5b57\u7b26\u4e32\u3002\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528re\u6a21\u5757\u6765\u5904\u7406\u6b63\u5219\u8868\u8fbe\u5f0f\u3002<\/p>\n<\/p>\n

1\u3001\u5b89\u88c5re\u6a21\u5757<\/h4>\n<\/p>\n

re\u6a21\u5757\u662fPython\u7684\u6807\u51c6\u5e93\uff0c\u65e0\u9700\u989d\u5916\u5b89\u88c5\uff0c\u76f4\u63a5\u5bfc\u5165\u5373\u53ef\u4f7f\u7528\u3002<\/p>\n<\/p>\n

import re<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u5339\u914d\u624b\u673a\u53f7\u7801<\/h4>\n<\/p>\n
\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u5b9a\u4e49\u4e00\u4e2a\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u5339\u914d\u624b\u673a\u53f7\u7801\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u6b63\u5219\u8868\u8fbe\u5f0f\uff0c\u7528\u4e8e\u5339\u914d\u5e38\u89c1\u7684\u624b\u673a\u53f7\u7801\u683c\u5f0f\uff1a<\/p>\n<\/p>\n
phone_pattern = re.compile(r'\\b\\d{10}\\b')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u6bb5\u4ee3\u7801\u5b9a\u4e49\u4e86\u4e00\u4e2a\u6b63\u5219\u8868\u8fbe\u5f0f\uff0c\u5339\u914d10\u4f4d\u6570\u5b57\u7684\u5b57\u7b26\u4e32\u3002\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u53ef\u4ee5\u6839\u636e\u5177\u4f53\u9700\u6c42\u8c03\u6574\u6b63\u5219\u8868\u8fbe\u5f0f\uff0c\u4f8b\u5982\u5339\u914d\u7279\u5b9a\u7684\u56fd\u5bb6\u6216\u5730\u533a\u7684\u624b\u673a\u53f7\u7801\u683c\u5f0f\u3002<\/p>\n<\/p>\n
3\u3001\u4ece\u6587\u672c\u4e2d\u63d0\u53d6\u624b\u673a\u53f7\u7801<\/h4>\n<\/p>\n
\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\uff0c\u53ef\u4ee5\u4ece\u6587\u672c\u4e2d\u63d0\u53d6\u6240\u6709\u7b26\u5408\u6761\u4ef6\u7684\u624b\u673a\u53f7\u7801\uff1a<\/p>\n<\/p>\n
text = "Here are some phone numbers: 1234567890, 0987654321, 1122334455."<\/p>\n
phone_numbers = phone_pattern.findall(text)<\/p>\n
print(phone_numbers)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u6bb5\u4ee3\u7801\u5c06\u5728\u6587\u672c\u4e2d\u67e5\u627e\u6240\u6709\u7b26\u5408\u6b63\u5219\u8868\u8fbe\u5f0f\u7684\u624b\u673a\u53f7\u7801\uff0c\u5e76\u5c06\u5b83\u4eec\u5b58\u50a8\u5728\u4e00\u4e2a\u5217\u8868\u4e2d\u3002<\/p>\n<\/p>\n
\u4e8c\u3001BeautifulSoup<\/h3>\n<\/p>\n
BeautifulSoup\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u7684Python\u5e93\u3002\u5b83\u53ef\u4ee5\u7528\u6765\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u7279\u5b9a\u5185\u5bb9\uff0c\u4f8b\u5982\u624b\u673a\u53f7\u7801\u3002<\/p>\n<\/p>\n
1\u3001\u5b89\u88c5BeautifulSoup<\/h4>\n<\/p>\n
\u5728\u4f7f\u7528BeautifulSoup\u4e4b\u524d\uff0c\u9700\u8981\u5148\u5b89\u88c5\u5b83\u3002\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5\uff1a<\/p>\n<\/p>\n
pip install beautifulsoup4<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875<\/h4>\n<\/p>\n
\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff0c\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528BeautifulSoup\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u624b\u673a\u53f7\u7801\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
import re<\/p>\n
\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/strong><\/h2>\n
url = 'https:\/\/example.com'<\/p>\n
response = requests.get(url)<\/p>\n
web_content = response.text<\/p>\n
\u89e3\u6790\u7f51\u9875<\/strong><\/h2>\n
soup = BeautifulSoup(web_content, 'html.parser')<\/p>\n
\u63d0\u53d6\u624b\u673a\u53f7\u7801<\/strong><\/h2>\n
phone_pattern = re.compile(r'\\b\\d{10}\\b')<\/p>\n
phone_numbers = phone_pattern.findall(soup.get_text())<\/p>\n
print(phone_numbers)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u6bb5\u4ee3\u7801\u9996\u5148\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875\uff0c\u5e76\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u624b\u673a\u53f7\u7801\u3002<\/p>\n<\/p>\n
\u4e09\u3001Scrapy<\/h3>\n<\/p>\n
Scrapy\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u7528\u4e8e\u5927\u89c4\u6a21\u6570\u636e\u6293\u53d6\u4efb\u52a1\u3002\u4f7f\u7528Scrapy\u53ef\u4ee5\u8f7b\u677e\u5730\u4ece\u591a\u4e2a\u7f51\u9875\u4e2d\u63d0\u53d6\u624b\u673a\u53f7\u7801\u3002<\/p>\n<\/p>\n
1\u3001\u5b89\u88c5Scrapy<\/h4>\n<\/p>\n
\u5728\u4f7f\u7528Scrapy\u4e4b\u524d\uff0c\u9700\u8981\u5148\u5b89\u88c5\u5b83\u3002\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5\uff1a<\/p>\n<\/p>\n
pip install scrapy<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u4f7f\u7528Scrapy\u6293\u53d6\u624b\u673a\u53f7\u7801<\/h4>\n<\/p>\n
\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff0c\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528Scrapy\u6293\u53d6\u624b\u673a\u53f7\u7801\uff1a<\/p>\n<\/p>\n
import scrapy<\/p>\n
import re<\/p>\n
class PhoneSpider(scrapy.Spider):<\/p>\n
    name = "phone_spider"<\/p>\n
    start_urls = ['https:\/\/example.com']<\/p>\n
    def parse(self, response):<\/p>\n
        phone_pattern = re.compile(r'\\b\\d{10}\\b')<\/p>\n
        phone_numbers = phone_pattern.findall(response.text)<\/p>\n
        for phone_number in phone_numbers:<\/p>\n
            yield {'phone_number': phone_number}<\/p>\n
\u4fdd\u5b58\u722c\u53d6\u7ed3\u679c<\/strong><\/h2>\n
from scrapy.crawler import CrawlerProcess<\/p>\n
process = CrawlerProcess(settings={<\/p>\n
    "FEEDS": {<\/p>\n
        "phone_numbers.json": {"format": "json"},<\/p>\n
    },<\/p>\n
})<\/p>\n
process.crawl(PhoneSpider)<\/p>\n
process.start()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u6bb5\u4ee3\u7801\u5b9a\u4e49\u4e86\u4e00\u4e2aScrapy\u722c\u866b\uff0c\u4ece\u6307\u5b9a\u7684URL\u4e2d\u63d0\u53d6\u624b\u673a\u53f7\u7801\uff0c\u5e76\u5c06\u7ed3\u679c\u4fdd\u5b58\u5230JSON\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n
\u56db\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u5728\u672c\u6587\u4e2d\uff0c\u6211\u4eec\u4ecb\u7ecd\u4e86\u4e09\u79cd\u5728Python\u4e2d\u6293\u53d6\u624b\u673a\u53f7\u7801\u7684\u65b9\u6cd5\uff1a\u6b63\u5219\u8868\u8fbe\u5f0f\u3001BeautifulSoup\u548cScrapy\u3002\u6b63\u5219\u8868\u8fbe\u5f0f\u9002\u7528\u4e8e\u7b80\u5355\u7684\u6587\u672c\u5339\u914d\u4efb\u52a1<\/strong>\uff0cBeautifulSoup\u9002\u7528\u4e8e\u89e3\u6790\u548c\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u7279\u5b9a\u5185\u5bb9<\/strong>\uff0cScrapy\u9002\u7528\u4e8e\u5927\u89c4\u6a21\u6570\u636e\u6293\u53d6\u4efb\u52a1<\/strong>\u3002\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\uff0c\u53ef\u4ee5\u6709\u6548\u5730\u63d0\u9ad8\u6570\u636e\u6293\u53d6\u7684\u6548\u7387\u548c\u51c6\u786e\u6027\u3002<\/p>\n<\/p>\n
1\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u7684\u4f18\u7f3a\u70b9<\/h4>\n<\/p>\n
\u4f18\u70b9\uff1a<\/strong><\/p>\n<\/p>\n