{"id":415,"date":"2025-10-22T11:33:26","date_gmt":"2025-10-22T03:33:26","guid":{"rendered":"https:\/\/www.idcyz.com\/blog\/?p=415"},"modified":"2025-10-22T11:33:26","modified_gmt":"2025-10-22T03:33:26","slug":"%e9%aa%8c%e8%af%81%e7%a0%81%e8%87%aa%e5%8a%a8%e5%a1%ab%e5%86%99%e8%a7%a3%e5%86%b3%e6%96%b9%e6%a1%88%ef%bc%9a%e6%8f%90%e5%8d%87%e7%94%a8%e6%88%b7%e4%bd%93%e9%aa%8c%e7%9a%84%e6%8a%80%e5%b7%a7","status":"publish","type":"post","link":"https:\/\/www.idcyz.com\/blog\/415.html","title":{"rendered":"\u9a8c\u8bc1\u7801\u81ea\u52a8\u586b\u5199\u89e3\u51b3\u65b9\u6848\uff1a\u63d0\u5347\u7528\u6237\u4f53\u9a8c\u7684\u6280\u5de7"},"content":{"rendered":"<p><h2>\u9a8c\u8bc1\u7801\u81ea\u52a8\u586b\u5199\u6280\u672f\u6982\u8ff0<\/h2>\n<\/p>\n<p style=\"text-align:center\"><img decoding=\"async\" src=\"https:\/\/www.idcyz.com\/blog\/wp-content\/uploads\/2025\/07\/N91K6WH.jpg\" alt=\"\u9a8c\u8bc1\u7801\u81ea\u52a8\u586b\u5199\u89e3\u51b3\u65b9\u6848\uff1a\u63d0\u5347\u7528\u6237\u4f53\u9a8c\u7684\u6280\u5de7\" title=\"\u9a8c\u8bc1\u7801\u81ea\u52a8\u586b\u5199\u89e3\u51b3\u65b9\u6848\uff1a\u63d0\u5347\u7528\u6237\u4f53\u9a8c\u7684\u6280\u5de7\"><\/p>\n<p><p>\u9a8c\u8bc1\u7801\u662f\u9632\u6b62\u7f51\u7edc\u722c\u866b\u548c\u6076\u610f\u653b\u51fb\u7684\u91cd\u8981\u624b\u6bb5\u3002\u4e3a\u4e86\u63d0\u9ad8\u7528\u6237\u4f53\u9a8c\uff0c\u9a8c\u8bc1\u7801\u7684\u81ea\u52a8\u586b\u5199\u6280\u672f\u5e94\u8fd0\u800c\u751f\u3002\u8be5\u6280\u672f\u901a\u8fc7\u8bc6\u522b\u9a8c\u8bc1\u7801\u5185\u5bb9\uff0c\u5e76\u5c06\u5176\u5feb\u901f\u586b\u5199\u5230\u76f8\u5e94\u7684\u8f93\u5165\u6846\u4e2d\uff0c\u8282\u7701\u4e86\u7528\u6237\u7684\u64cd\u4f5c\u65f6\u95f4\u3002\u672c\u6587\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u5b9e\u73b0\u9a8c\u8bc1\u7801\u7684\u81ea\u52a8\u586b\u5199\uff0c\u5305\u62ec\u6240\u9700\u7684\u5e93\u3001\u8be6\u7ec6\u7684\u64cd\u4f5c\u6b65\u9aa4\u53ca\u6ce8\u610f\u4e8b\u9879\u3002<\/p>\n<\/p>\n<p><h2>\u6240\u9700\u5de5\u5177\u4e0e\u51c6\u5907<\/h2>\n<\/p>\n<ul>\n<li><strong>Python\u7f16\u7a0b\u8bed\u8a00\uff1a<\/strong> \u786e\u4fdd\u8ba1\u7b97\u673a\u4e0a\u5df2\u5b89\u88c5Python\u73af\u5883\uff0c\u63a8\u8350\u4f7f\u75283.6\u53ca\u4ee5\u4e0a\u7248\u672c\u3002<\/li>\n<li><strong>\u7b2c\u4e09\u65b9\u5e93\uff1a<\/strong> \u4f7f\u7528\u4ee5\u4e0b\u5e93\u8fdb\u884c\u9a8c\u8bc1\u7801\u8bc6\u522b\u548c\u81ea\u52a8\u586b\u5199\u3002<\/li>\n<ul>\n<li>pytesseract\uff1a\u7528\u4e8eOCR\u56fe\u50cf\u8bc6\u522b\u3002<\/li>\n<li>Pillow\uff1a\u7528\u4e8e\u56fe\u50cf\u5904\u7406\u3002<\/li>\n<li>requests\uff1a\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u3002<\/li>\n<li>selenium\uff1a\u7528\u4e8e\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u64cd\u4f5c\u3002<\/li>\n<li>BeautifulSoup\uff1a\u7528\u4e8eHTML\u89e3\u6790\u3002<\/li>\n<\/ul>\n<\/ul>\n<p><h2>\u5b89\u88c5\u5fc5\u8981\u5e93<\/h2>\n<\/p>\n<p><p>\u53ef\u4ee5\u4f7f\u7528pip\u5de5\u5177\u6765\u5b89\u88c5\u4e0a\u8ff0\u5e93\u3002\u5728\u547d\u4ee4\u884c\u4e2d\u8f93\u5165\u4ee5\u4e0b\u547d\u4ee4\uff1a<\/p>\n<\/p>\n<p><pre><code>pip install pytesseract Pillow requests selenium beautifulsoup4<\/code><\/pre>\n<\/p>\n<p><p>\u6ce8\u610f\uff1a\u5982\u679c\u4f7f\u7528Tesseract OCR\u5de5\u5177\uff0c\u9700\u8981\u989d\u5916\u5b89\u88c5Tesseract\uff0c\u5e76\u5c06\u5176\u8def\u5f84\u6dfb\u52a0\u81f3\u7cfb\u7edf\u73af\u5883\u53d8\u91cf\u3002<\/p>\n<\/p>\n<p><h2>\u9a8c\u8bc1\u7801\u81ea\u52a8\u586b\u5199\u7684\u5b9e\u73b0\u6b65\u9aa4<\/h2>\n<\/p>\n<p><h3>\u6b65\u9aa41\uff1a\u83b7\u53d6\u9a8c\u8bc1\u7801\u56fe\u50cf<\/h3>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u9700\u8981\u83b7\u53d6\u9700\u8981\u586b\u5199\u7684\u9a8c\u8bc1\u7801\u56fe\u50cf\u3002\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\uff0c\u7136\u540e\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875\u5185\u5bb9\uff0c\u63d0\u53d6\u9a8c\u8bc1\u7801\u7684URL\u5730\u5740\u3002<\/p>\n<\/p>\n<p><pre><code>import requests<\/p>\r\n<p>from bs4 import BeautifulSoup<\/p>\r\n\r\n<p>url = \"http:\/\/example.com\/login\"  # \u6307\u5b9a\u767b\u5f55\u9875\u9762\u7684URL<\/p>\r\n<p>response = requests.get(url)<\/p>\r\n<p>soup = BeautifulSoup(response.text, 'html.parser')<\/p>\r\n\r\n<p># \u63d0\u53d6\u9a8c\u8bc1\u7801\u56fe\u50cf\u7684URL\uff0c\u5047\u8bbe\u5176\u5728\u67d0\u4e2a<img>\u6807\u7b7e\u4e2d<\/p>\r\n<p>captcha_url = soup.find('img', {'id': 'captcha'})['src']<\/p>\r\n<p># \u5b8c\u6574\u7684\u9a8c\u8bc1\u7801URL<\/p>\r\n<p>captcha_url = url.rsplit('\/', 1)[0] + '\/' + captcha_url<\/p>\r\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u6b65\u9aa42\uff1a\u4e0b\u8f7d\u9a8c\u8bc1\u7801\u56fe\u50cf<\/h3>\n<\/p>\n<p><p>\u5c06\u9a8c\u8bc1\u7801\u56fe\u50cf\u4e0b\u8f7d\u5e76\u4fdd\u5b58\u5230\u672c\u5730\uff0c\u4ee5\u4fbf\u540e\u7eed\u5904\u7406\u3002<\/p>\n<\/p>\n<p><pre><code>captcha_response = requests.get(captcha_url)<\/p>\r\n<p>with open('captcha.png', 'wb') as f:<\/p>\r\n<p>    f.write(captcha_response.content)<\/p>\r\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u6b65\u9aa43\uff1a\u4f7f\u7528OCR\u8bc6\u522b\u9a8c\u8bc1\u7801<\/h3>\n<\/p>\n<p><p>\u5229\u7528pytesseract\u5c06\u4e0b\u8f7d\u7684\u9a8c\u8bc1\u7801\u56fe\u50cf\u8f6c\u5316\u4e3a\u6587\u672c\u5b57\u7b26\u4e32\u3002<\/p>\n<\/p>\n<p><pre><code>from PIL import Image<\/p>\r\n<p>import pytesseract<\/p>\r\n\r\n<p># \u52a0\u8f7d\u9a8c\u8bc1\u7801\u56fe\u50cf<\/p>\r\n<p>image = Image.open('captcha.png')<\/p>\r\n\r\n<p># \u4f7f\u7528pytesseract\u8bc6\u522b\u56fe\u50cf\u4e2d\u7684\u6587\u672c<\/p>\r\n<p>captcha_text = pytesseract.image_to_string(image).strip()<\/p>\r\n<p>print(f'\u8bc6\u522b\u51fa\u7684\u9a8c\u8bc1\u7801\u4e3a: {captcha_text}')<\/p>\r\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u6b65\u9aa44\uff1a\u4f7f\u7528Selenium\u81ea\u52a8\u586b\u5199\u8868\u5355<\/h3>\n<\/p>\n<p><p>\u5b89\u88c5\u5e76\u914d\u7f6e\u597d\u6d4f\u89c8\u5668\u9a71\u52a8\uff0c\u4f7f\u7528Selenium\u63a7\u5236\u6d4f\u89c8\u5668\u6253\u5f00\u767b\u5f55\u9875\u9762\uff0c\u5e76\u81ea\u52a8\u586b\u5165\u7528\u6237\u540d\u3001\u5bc6\u7801\u53ca\u8bc6\u522b\u51fa\u7684\u9a8c\u8bc1\u7801\u3002<\/p>\n<\/p>\n<p><pre><code>from selenium import webdriver<\/p>\r\n<p>from selenium.webdriver.common.by import By<\/p>\r\n<p>import time<\/p>\r\n\r\n<p>driver = webdriver.Chrome()  # \u8c03\u7528Chrome\u6d4f\u89c8\u5668<\/p>\r\n\r\n<p># \u6253\u5f00\u767b\u5f55\u9875\u9762<\/p>\r\n<p>driver.get(url)<\/p>\r\n\r\n<p># \u586b\u5199\u7528\u6237\u540d\u548c\u5bc6\u7801<\/p>\r\n<p>driver.find_element(By.NAME, 'username').send_keys('your_username')<\/p>\r\n<p>driver.find_element(By.NAME, 'password').send_keys('your_password')<\/p>\r\n\r\n<p># \u586b\u5199\u9a8c\u8bc1\u7801<\/p>\r\n<p>driver.find_element(By.NAME, 'captcha').send_keys(captcha_text)<\/p>\r\n\r\n<p># \u63d0\u4ea4\u8868\u5355<\/p>\r\n<p>driver.find_element(By.NAME, 'submit').click()<\/p>\r\n\r\n<p># \u7b49\u5f85\u4e00\u6bb5\u65f6\u95f4\uff0c\u9632\u6b62\u9875\u9762\u52a0\u8f7d\u8fc7\u5feb<\/p>\r\n<p>time.sleep(3)<\/p>\r\n\r\n<p># \u5173\u95ed\u6d4f\u89c8\u5668<\/p>\r\n<p>driver.quit()<\/p>\r\n<p><\/code><\/pre>\n<\/p>\n<p><h2>\u6ce8\u610f\u4e8b\u9879<\/h2>\n<\/p>\n<ul>\n<li>\u786e\u4fdd\u9a8c\u8bc1\u7801\u56fe\u7247\u6e05\u6670\uff0c\u6a21\u7cca\u6216\u626d\u66f2\u7684\u56fe\u7247\u53ef\u80fd\u5f71\u54cd\u8bc6\u522b\u51c6\u786e\u7387\u3002<\/li>\n<li>\u4e0d\u540c\u7f51\u7ad9\u7684\u9a8c\u8bc1\u7801\u7ed3\u6784\u53ef\u80fd\u4e0d\u540c\uff0c\u53ef\u80fd\u9700\u8981\u8c03\u6574\u56fe\u50cf\u5904\u7406\u6216OCR\u53c2\u6570\uff0c\u4ee5\u63d0\u9ad8\u8bc6\u522b\u7cbe\u5ea6\u3002<\/li>\n<li>\u6709\u4e9b\u7f51\u7ad9\u53ef\u80fd\u91c7\u7528\u66f4\u590d\u6742\u7684\u9a8c\u8bc1\u7801\u6280\u672f\uff08\u5982\u56fe\u5f62\u9a8c\u8bc1\u7801\u3001\u52a8\u6001\u9a8c\u8bc1\u7801\uff09\uff0c\u9700\u8981\u66f4\u4e3a\u590d\u6742\u7684\u7b97\u6cd5\u6765\u8bc6\u522b\u3002<\/li>\n<li>\u9891\u7e41\u81ea\u52a8\u5316\u64cd\u4f5c\u53ef\u80fd\u89e6\u53d1\u7f51\u7ad9\u7684\u5b89\u5168\u673a\u5236\uff0c\u5efa\u8bae\u9002\u5ea6\u4f7f\u7528\u3002<\/li>\n<\/ul>\n<p><h2>\u5b9e\u7528\u6280\u5de7<\/h2>\n<\/p>\n<ul>\n<li>\u5728\u4f7f\u7528pytesseract\u65f6\uff0c\u5c1d\u8bd5\u4e0d\u540c\u7684\u56fe\u50cf\u9884\u5904\u7406\u65b9\u6cd5\uff0c\u5982\u4e8c\u503c\u5316\u3001\u65cb\u8f6c\u7b49\uff0c\u4ee5\u63d0\u9ad8\u8bc6\u522b\u7387\u3002<\/li>\n<li>\u53ef\u4ee5\u5728webdriver\u4e2d\u901a\u8fc7\u8bbe\u7f6e\u9690\u5f0f\u7b49\u5f85\u65f6\u95f4\uff0c\u786e\u4fdd\u9875\u9762\u7684\u6240\u6709\u5143\u7d20\u90fd\u5df2\u52a0\u8f7d\u5b8c\u6210\u3002<\/li>\n<li>\u4f7f\u7528try-except\u7ed3\u6784\u6355\u83b7\u53ef\u80fd\u7684\u5f02\u5e38\uff0c\u786e\u4fdd\u7a0b\u5e8f\u7684\u5065\u58ee\u6027\u3002<\/li>\n<li>\u5728\u4f7f\u7528Tesseract\u65f6\uff0c\u53ef\u4ee5\u901a\u8fc7\u914d\u7f6e\u8bad\u7ec3\u6570\u636e\u6765\u63d0\u9ad8\u8bc6\u522b\u7279\u5b9a\u9a8c\u8bc1\u7801\u7684\u51c6\u786e\u6027\u3002<\/li>\n<\/ul>\n<p><h2>\u6269\u5c55\u4e0e\u4f18\u5316<\/h2>\n<\/p>\n<p><p>\u4e3a\u4e86\u8fdb\u4e00\u6b65\u63d0\u5347\u9a8c\u8bc1\u7801\u81ea\u52a8\u586b\u5199\u7684\u51c6\u786e\u6027\u548c\u6548\u7387\uff0c\u53ef\u4ee5\u8003\u8651\u4ee5\u4e0b\u6269\u5c55\u6280\u672f\uff1a<\/p>\n<\/p>\n<ul>\n<li>\u5b9e\u73b0\u56fe\u50cf\u589e\u5f3a\u5904\u7406\uff0c\u5982\u4f7f\u7528OpenCV\u5e93\u5904\u7406\u56fe\u50cf\u4f7f\u5176\u66f4\u6613\u4e8e\u8fa8\u8ba4\u3002<\/li>\n<li>\u4f7f\u7528\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u6765\u8bad\u7ec3\u5bf9\u7279\u5b9a\u7c7b\u578b\u9a8c\u8bc1\u7801\u7684\u8bc6\u522b\uff0c\u53ef\u80fd\u4f1a\u663e\u8457\u63d0\u9ad8\u8bc6\u522b\u7387\u3002<\/li>\n<li>\u63a2\u7d22\u201c\u4eba\u673a\u534f\u4f5c\u201d\u7684\u65b9\u5f0f\uff0c\u7ed3\u5408\u4eba\u5de5\u8f93\u5165\u548c\u81ea\u52a8\u8bc6\u522b\uff0c\u8fdb\u4e00\u6b65\u63d0\u9ad8\u6548\u7387\u3002<\/li>\n<\/ul>\n<p><p>\u4e0a\u8ff0\u6b65\u9aa4\u548c\u6280\u5de7\u63d0\u4f9b\u4e86\u4e00\u6761\u5b9e\u73b0\u9a8c\u8bc1\u7801\u81ea\u52a8\u586b\u5199\u7684\u5b8c\u6574\u8def\u5f84\u3002\u901a\u8fc7\u4e0d\u65ad\u5b9e\u8df5\u548c\u66f4\u65b0\u6280\u672f\u624b\u6bb5\uff0c\u53ef\u4ee5\u66f4\u6709\u6548\u5730\u5b8c\u6210\u81ea\u52a8\u5316\u64cd\u4f5c\u3002\u5e0c\u671b\u672c\u6587\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\u3002<\/p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u9a8c\u8bc1\u7801\u81ea\u52a8\u586b\u5199\u6280\u672f\u6982\u8ff0 \u9a8c\u8bc1\u7801\u662f\u9632\u6b62\u7f51\u7edc\u722c\u866b\u548c\u6076\u610f\u653b\u51fb\u7684\u91cd\u8981\u624b\u6bb5\u3002\u4e3a\u4e86\u63d0\u9ad8\u7528\u6237\u4f53\u9a8c\uff0c\u9a8c\u8bc1\u7801\u7684\u81ea\u52a8\u586b\u5199\u6280\u672f\u5e94\u8fd0\u800c\u751f\u3002\u8be5\u6280\u672f\u901a\u8fc7\u8bc6\u522b\u9a8c\u8bc1\u7801\u5185\u5bb9\uff0c\u5e76\u5c06\u5176\u5feb\u901f\u586b\u5199\u5230\u76f8\u5e94\u7684\u8f93\u5165\u6846\u4e2d\uff0c\u8282\u7701\u4e86\u7528\u6237\u7684\u64cd\u4f5c\u65f6\u95f4\u3002\u672c\u6587\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u5b9e\u73b0\u9a8c\u8bc1\u7801\u7684\u81ea\u52a8\u586b\u5199\uff0c\u5305\u62ec\u6240&#8230;<\/p>\n","protected":false},"author":1,"featured_media":416,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[226,227,225],"topic":[],"class_list":["post-415","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-jiushu","tag-226","tag-227","tag-225"],"_links":{"self":[{"href":"https:\/\/www.idcyz.com\/blog\/wp-json\/wp\/v2\/posts\/415","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.idcyz.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.idcyz.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.idcyz.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.idcyz.com\/blog\/wp-json\/wp\/v2\/comments?post=415"}],"version-history":[{"count":1,"href":"https:\/\/www.idcyz.com\/blog\/wp-json\/wp\/v2\/posts\/415\/revisions"}],"predecessor-version":[{"id":418,"href":"https:\/\/www.idcyz.com\/blog\/wp-json\/wp\/v2\/posts\/415\/revisions\/418"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.idcyz.com\/blog\/wp-json\/wp\/v2\/media\/416"}],"wp:attachment":[{"href":"https:\/\/www.idcyz.com\/blog\/wp-json\/wp\/v2\/media?parent=415"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.idcyz.com\/blog\/wp-json\/wp\/v2\/categories?post=415"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.idcyz.com\/blog\/wp-json\/wp\/v2\/tags?post=415"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.idcyz.com\/blog\/wp-json\/wp\/v2\/topic?post=415"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}