{"id":202158,"date":"2025-05-10T15:02:34","date_gmt":"2025-05-10T07:02:34","guid":{"rendered":"https:\/\/server.hk\/cnblog\/202158\/"},"modified":"2025-05-10T15:02:34","modified_gmt":"2025-05-10T07:02:34","slug":"%e4%bd%bf%e7%94%a8python%e5%92%8credis%e6%9e%84%e5%bb%ba%e7%bd%91%e7%bb%9c%e7%88%ac%e8%99%ab%ef%bc%9a%e5%a6%82%e4%bd%95%e5%a4%84%e7%90%86%e5%8f%8d%e7%88%ac%e8%99%ab%e7%ad%96%e7%95%a5","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/202158\/","title":{"rendered":"\u4f7f\u7528Python\u548cRedis\u6784\u5efa\u7f51\u7edc\u722c\u866b\uff1a\u5982\u4f55\u5904\u7406\u53cd\u722c\u866b\u7b56\u7565"},"content":{"rendered":"<p><b><\/b> <\/p>\n<h1>\u4f7f\u7528Python\u548cRedis\u6784\u5efa\u7f51\u7edc\u722c\u866b\uff1a\u5982\u4f55\u5904\u7406\u53cd\u722c\u866b\u7b56\u7565<\/h1>\n<p>\u6700\u8fd1\u53d1\u73b0\u4e0d\u5c11\u5c0f\u4f19\u4f34\u90fd\u5bf9<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u6570\u636e\u5e93<\/span>\u5f88\u611f\u5174\u8da3\uff0c\u6240\u4ee5\u4eca\u5929\u7ee7\u7eed\u7ed9\u5927\u5bb6\u4ecb\u7ecd<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u6570\u636e\u5e93<\/span>\u76f8\u5173\u7684\u77e5\u8bc6\uff0c\u672c\u6587<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u300a\u4f7f\u7528Python\u548cRedis\u6784\u5efa\u7f51\u7edc\u722c\u866b\uff1a\u5982\u4f55\u5904\u7406\u53cd\u722c\u866b\u7b56\u7565\u300b<\/span>\u4e3b\u8981\u5185\u5bb9\u6d89\u53ca\u5230<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\"><\/span>\u7b49\u7b49\u77e5\u8bc6\u70b9\uff0c\u5e0c\u671b\u80fd\u5e2e\u5230\u4f60\uff01\u5f53\u7136\u5982\u679c\u9605\u8bfb\u672c\u6587\u65f6\u5b58\u5728\u4e0d\u540c\u60f3\u6cd5\uff0c\u53ef\u4ee5\u5728\u8bc4\u8bba\u4e2d\u8868\u8fbe\uff0c\u4f46\u662f\u8bf7\u52ff\u4f7f\u7528\u8fc7\u6fc0\u7684\u63aa\u8f9e~<\/p>\n<p>\u4f7f\u7528Python\u548cRedis\u6784\u5efa\u7f51\u7edc\u722c\u866b\uff1a\u5982\u4f55\u5904\u7406\u53cd\u722c\u866b\u7b56\u7565<\/p>\n<p>\u5f15\u8a00\uff1a<br \/>\u8fd1\u5e74\u6765\uff0c\u968f\u7740\u4e92\u8054\u7f51\u7684\u5feb\u901f\u53d1\u5c55\uff0c\u7f51\u7edc\u722c\u866b\u5df2\u6210\u4e3a\u83b7\u53d6\u4fe1\u606f\u548c\u6570\u636e\u7684\u91cd\u8981\u624b\u6bb5\u4e4b\u4e00\u3002\u7136\u800c\uff0c\u8bb8\u591a\u7f51\u7ad9\u4e3a\u4e86\u4fdd\u62a4\u81ea\u5df1\u7684\u6570\u636e\uff0c\u91c7\u53d6\u4e86\u5404\u79cd\u53cd\u722c\u866b\u7b56\u7565\uff0c\u5bf9\u722c\u866b\u9020\u6210\u4e86\u56f0\u6270\u3002\u672c\u6587\u5c06\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528Python\u548cRedis\u6765\u6784\u5efa\u4e00\u4e2a\u5f3a\u5927\u7684\u7f51\u7edc\u722c\u866b\uff0c\u5e76\u89e3\u51b3\u5e38\u89c1\u7684\u53cd\u722c\u866b\u7b56\u7565\u3002<\/p>\n<ol>\n<li>\u722c\u866b\u57fa\u672c\u8bbe\u7f6e<br \/>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5\u76f8\u5173\u5e93\uff0c\u4f8b\u5982requests\u3001beautifulsoup\u548credis-py\u3002\u4e0b\u9762\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u4ee3\u7801\u793a\u4f8b\uff0c\u7528\u4e8e\u8bbe\u7f6e\u722c\u866b\u7684\u57fa\u672c\u53c2\u6570\u548c\u521d\u59cb\u5316Redis\u8fde\u63a5\uff1a<\/li>\n<\/ol>\n<pre>import requests\nfrom bs4 import BeautifulSoup\nimport redis\n\n# \u8bbe\u7f6e\u722c\u866b\u7684\u57fa\u672c\u53c2\u6570\nbase_url = \"https:\/\/example.com\"  # \u5f85\u722c\u53d6\u7684\u7f51\u7ad9\nuser_agent = \"Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/89.0.4389.82 Safari\/537.36\"  # \u8bbe\u7f6eUser-Agent\n\n# \u521d\u59cb\u5316Redis\u8fde\u63a5\nredis_host = \"localhost\"  # Redis\u4e3b\u673a\u5730\u5740\nredis_port = 6379  # Redis\u7aef\u53e3\u53f7\nr = redis.StrictRedis(host=redis_host, port=redis_port, db=0)<\/pre>\n<ol>\n<li>\u5904\u7406\u8bf7\u6c42\u5934\u4fe1\u606f<br \/>\u53cd\u722c\u866b\u7b56\u7565\u4e4b\u4e00\u5c31\u662f\u68c0\u6d4b\u8bf7\u6c42\u5934\u4e2d\u7684User-Agent\uff0c\u5224\u65ad\u8bf7\u6c42\u662f\u5426\u6765\u81ea\u771f\u5b9e\u7684\u6d4f\u89c8\u5668\u3002\u6211\u4eec\u53ef\u4ee5\u5728\u4ee3\u7801\u4e2d\u8bbe\u7f6e\u5408\u9002\u7684User-Agent\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u8bf7\u6c42\uff0c\u5982\u4e0a\u9762\u4ee3\u7801\u4e2d\u7684user_agent\u3002<\/li>\n<\/ol>\n<pre>headers = {\n    \"User-Agent\": user_agent\n}<\/pre>\n<ol>\n<li>\u5904\u7406IP\u4ee3\u7406<br \/>\u8bb8\u591a\u7f51\u7ad9\u4f1a\u9650\u5236\u76f8\u540cIP\u5730\u5740\u7684\u8bf7\u6c42\u9891\u7387\u6216\u8bbe\u7f6e\u8bbf\u95ee\u767d\u540d\u5355\u3002\u4e3a\u4e86\u7ed5\u8fc7\u8fd9\u4e2a\u9650\u5236\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u4ee3\u7406IP\u6c60\u3002\u8fd9\u91cc\u4f7f\u7528Redis\u5b58\u50a8\u4ee3\u7406IP\uff0c\u7136\u540e\u5728\u6bcf\u4e2a\u8bf7\u6c42\u4e2d\u968f\u673a\u9009\u62e9\u4e00\u4e2aIP\u3002<\/li>\n<\/ol>\n<pre># \u4eceRedis\u4e2d\u83b7\u53d6\u4ee3\u7406IP\nproxy_ip = r.srandmember(\"proxy_ip_pool\")\n\nproxies = {\n    \"http\": \"http:\/\/\" + proxy_ip,\n    \"https\": \"https:\/\/\" + proxy_ip\n}<\/pre>\n<ol>\n<li>\u5904\u7406\u9a8c\u8bc1\u7801<br \/>\u6709\u4e9b\u7f51\u7ad9\u4e3a\u4e86\u9632\u6b62\u81ea\u52a8\u5316\u722c\u53d6\uff0c\u4f1a\u8bbe\u7f6e\u9a8c\u8bc1\u7801\u6765\u9a8c\u8bc1\u7528\u6237\u7684\u771f\u5b9e\u6027\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u7b2c\u4e09\u65b9\u5e93\uff08\u5982Pillow\uff09\u6765\u5904\u7406\u9a8c\u8bc1\u7801\uff0c\u6216\u8005\u4f7f\u7528\u5f00\u6e90\u5de5\u5177\uff08\u5982Tesseract\uff09\u8fdb\u884c\u56fe\u50cf\u8bc6\u522b\u3002<\/li>\n<\/ol>\n<pre># \u5904\u7406\u9a8c\u8bc1\u7801\uff0c\u6b64\u5904\u4ee5Pillow\u5e93\u4e3a\u4f8b\nfrom PIL import Image\nimport pytesseract\n\n# \u4e0b\u8f7d\u9a8c\u8bc1\u7801\u56fe\u7247\ncaptcha_url = base_url + \"\/captcha.jpg\"\nresponse = requests.get(captcha_url, headers=headers, proxies=proxies)\n# \u4fdd\u5b58\u9a8c\u8bc1\u7801\u56fe\u7247\nwith open(\"captcha.jpg\", \"wb\") as f:\n    f.write(response.content)\n# \u8bc6\u522b\u9a8c\u8bc1\u7801\ncaptcha_image = Image.open(\"captcha.jpg\")\ncaptcha_text = pytesseract.image_to_string(captcha_image)<\/pre>\n<ol>\n<li>\u5904\u7406\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9<br \/>\u8bb8\u591a\u7f51\u7ad9\u91c7\u7528\u52a8\u6001\u52a0\u8f7d\u6280\u672f\uff08\u5982AJAX\uff09\u6765\u52a0\u8f7d\u90e8\u5206\u6216\u5168\u90e8\u5185\u5bb9\u3002\u5bf9\u4e8e\u8fd9\u79cd\u60c5\u51b5\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u6a21\u62df\u6d4f\u89c8\u5668\u6267\u884cJavaScript\u4ee3\u7801\u7684\u5de5\u5177\uff0c\u5982Selenium\u6216Puppeteer\u3002<\/li>\n<\/ol>\n<pre>from selenium import webdriver\n\n# \u4f7f\u7528Selenium\u6a21\u62df\u6d4f\u89c8\u5668\u8bbf\u95ee\ndriver = webdriver.Chrome()\ndriver.get(base_url)\n# \u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6210\ntime.sleep(3)\n# \u83b7\u53d6\u9875\u9762\u6e90\u7801\npage_source = driver.page_source\n# \u4f7f\u7528BeautifulSoup\u89e3\u6790\u9875\u9762\nsoup = BeautifulSoup(page_source, \"html.parser\")<\/pre>\n<ol>\n<li>\u5904\u7406\u8d26\u53f7\u767b\u5f55<br \/>\u6709\u4e9b\u7f51\u7ad9\u8981\u6c42\u7528\u6237\u767b\u5f55\u540e\u624d\u80fd\u8bbf\u95ee\u5185\u5bb9\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Selenium\u81ea\u52a8\u586b\u5199\u767b\u5f55\u8868\u5355\u5e76\u63d0\u4ea4\u3002<\/li>\n<\/ol>\n<pre># \u586b\u5199\u767b\u5f55\u8868\u5355\ndriver.find_element_by_id(\"username\").send_keys(\"your_username\")\ndriver.find_element_by_id(\"password\").send_keys(\"your_password\")\n# \u63d0\u4ea4\u8868\u5355\ndriver.find_element_by_id(\"submit\").click()<\/pre>\n<p>\u7ed3\u8bed\uff1a<br \/>\u901a\u8fc7\u4f7f\u7528Python\u548cRedis\u6784\u5efa\u7f51\u7edc\u722c\u866b\uff0c\u6211\u4eec\u80fd\u591f\u6709\u6548\u5730\u5e94\u5bf9\u5e38\u89c1\u7684\u53cd\u722c\u866b\u7b56\u7565\uff0c\u5b9e\u73b0\u66f4\u7a33\u5b9a\u548c\u9ad8\u6548\u7684\u6570\u636e\u83b7\u53d6\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u8fd8\u9700\u8981\u6839\u636e\u5177\u4f53\u7f51\u7ad9\u7684\u53cd\u722c\u866b\u7b56\u7565\u8fdb\u884c\u8fdb\u4e00\u6b65\u7684\u4f18\u5316\u548c\u9002\u914d\u3002\u5e0c\u671b\u672c\u6587\u80fd\u5bf9\u60a8\u7684\u722c\u866b\u5f00\u53d1\u5de5\u4f5c\u6709\u6240\u5e2e\u52a9\u3002<\/p>\n<dl>\n<dt>\n <\/dt>\n<dd>\n   Redis\u5728Node.js\u5f00\u53d1\u4e2d\u7684\u5e94\u7528\uff1a\u5982\u4f55\u5904\u7406\u5927\u91cf\u8bf7\u6c42\n <\/dd>\n<\/dl>\n<dl>\n<dt>\n <\/dt>\n<dd>\n   \u5982\u4f55\u5229\u7528Redis\u548cC#\u5b9e\u73b0\u5206\u5e03\u5f0f\u6d88\u606f\u7cfb\u7edf\n <\/dd>\n<\/dl>\n","protected":false},"excerpt":{"rendered":"<p>\u4f7f\u7528Python\u548cRedis\u6784\u5efa&#46;&#46;&#46;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[101],"tags":[],"class_list":["post-202158","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/202158","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=202158"}],"version-history":[{"count":0,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/202158\/revisions"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=202158"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=202158"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=202158"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}