{"id":8434,"date":"2025-05-22T12:24:44","date_gmt":"2025-05-22T03:24:44","guid":{"rendered":"https:\/\/ip.cloudbypass.com\/proxy-information\/?p=8434"},"modified":"2025-05-22T12:24:44","modified_gmt":"2025-05-22T03:24:44","slug":"scrapy%e5%8f%8d%e8%bf%bd%e8%b8%aa%e7%a5%9e%e5%99%a8%ef%bc%9aproxy-middleware%e8%ae%be%e7%bd%ae%e5%85%a8%e6%94%bb%e7%95%a5%ef%bc%8c%e4%bf%9d%e6%8a%a4%e9%9a%90%e7%a7%81%e7%9a%84%e4%bb%a3%e7%90%86ip","status":"publish","type":"post","link":"https:\/\/ip.cloudbypass.com\/proxy-information\/8434.html","title":{"rendered":"Scrapy\u53cd\u8ffd\u8e2a\u795e\u5668\uff1aProxy Middleware\u8bbe\u7f6e\u5168\u653b\u7565\uff0c\u4fdd\u62a4\u9690\u79c1\u7684\u4ee3\u7406IP\u5b9e\u6218\u6f14\u7ec3"},"content":{"rendered":"\n<p>\u5404\u4f4d\u722c\u866b\u7231\u597d\u8005\u4eec\uff0c\u6709\u6ca1\u6709\u5728\u6570\u636e\u91c7\u96c6\u7684\u8def\u4e0a\uff0c\u88ab\u5404\u79cd\u5404\u6837\u7684\u53cd\u722c\u673a\u5236\u201c\u6298\u78e8\u201d\u5f97\u7126\u5934\u70c2\u989d\uff1f\u5c24\u5176\u662f\u5f53\u4f60\u7684\u722c\u866b\u521a\u8dd1\u8d77\u6765\u6ca1\u591a\u4e45\uff0c\u5c31\u88ab\u76ee\u6807\u7f51\u7ad9\u65e0\u60c5\u5730\u5c01\u7981\u4e86IP\uff0c\u90a3\u79cd\u611f\u89c9\u7b80\u76f4\u6bd4\u4ee3\u7801\u62a5\u9519\u8fd8\u8ba9\u4eba\u6293\u72c2\uff01\u522b\u62c5\u5fc3\uff0c\u4eca\u5929\u54b1\u4eec\u5c31\u6765\u6df1\u5165\u804a\u804aScrapy\u91cc\u4e00\u4e2a\u8d85\u7ea7\u5b9e\u7528\u7684\u201c\u53cd\u8ffd\u8e2a\u795e\u5668\u201d\u2014\u2014<strong>Proxy Middleware<\/strong>\u3002\u5b83\u4e0d\u4ec5\u4ec5\u662f\u5e2e\u4f60\u9690\u85cfIP\uff0c\u66f4\u662f\u4e00\u6574\u5957\u4fdd\u62a4\u4f60\u9690\u79c1\u3001\u4fdd\u969c\u6570\u636e\u91c7\u96c6\u8fde\u8d2f\u6027\u7684\u79d8\u5bc6\u6b66\u5668\u3002\u6211\u8fd8\u4f1a\u624b\u628a\u624b\u6559\u4f60\u5982\u4f55\u914d\u7f6e\uff0c\u5e76\u7ed3\u5408\u884c\u4e1a\u9886\u5148\u7684<strong>\u7a7f\u4e91\u4ee3\u7406IP<\/strong>\uff0c\u8ba9\u4f60\u7684\u722c\u866b\u5982\u864e\u6dfb\u7ffc\uff0c\u8f7b\u677e\u7a81\u7834\u5404\u79cd\u53cd\u722c\u9650\u5236\uff01<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">\u7b2c\u4e00\u7ae0\uff1a\u4ee3\u7406IP\u2014\u2014\u4f60\u7684\u722c\u866b\u201c\u9690\u5f62\u6597\u7bf7\u201d<\/h4>\n\n\n\n<p>\u5728\u4e92\u8054\u7f51\u4e0a\uff0cIP\u5730\u5740\u5c31\u50cf\u4f60\u7684\u5bb6\u5ead\u4f4f\u5740\uff0c\u6bcf\u6b21\u4f60\u8bbf\u95ee\u4e00\u4e2a\u7f51\u7ad9\uff0c\u7f51\u7ad9\u670d\u52a1\u5668\u90fd\u80fd\u77e5\u9053\u4f60\u7684IP\u3002\u5bf9\u4e8e\u722c\u866b\u6765\u8bf4\uff0c\u9891\u7e41\u5730\u7528\u540c\u4e00\u4e2aIP\u53bb\u8bbf\u95ee\u4e00\u4e2a\u7f51\u7ad9\uff0c\u5f88\u5bb9\u6613\u88ab\u8bc6\u522b\u4e3a\u673a\u5668\u884c\u4e3a\uff0c\u7136\u540e\u5c31\u88ab\u7f51\u7ad9\u201c\u62c9\u9ed1\u201d\u4e86\uff0c\u4e5f\u5c31\u662f\u6211\u4eec\u5e38\u8bf4\u7684IP\u5c01\u7981\u3002<\/p>\n\n\n\n<p>\u8fd9\u65f6\u5019\uff0c<strong>\u4ee3\u7406IP<\/strong>\u5c31\u6210\u4e86\u4f60\u7684\u201c\u9690\u5f62\u6597\u7bf7\u201d\u3002\u5b83\u5c31\u50cf\u4e00\u4e2a\u4e2d\u95f4\u4eba\uff0c\u4f60\u7684\u8bf7\u6c42\u4e0d\u518d\u76f4\u63a5\u53d1\u7ed9\u76ee\u6807\u7f51\u7ad9\uff0c\u800c\u662f\u5148\u53d1\u7ed9\u4ee3\u7406\u670d\u52a1\u5668\uff0c\u7136\u540e\u4ee3\u7406\u670d\u52a1\u5668\u518d\u4ee3\u66ff\u4f60\u628a\u8bf7\u6c42\u53d1\u7ed9\u76ee\u6807\u7f51\u7ad9\u3002\u8fd9\u6837\u4e00\u6765\uff0c\u76ee\u6807\u7f51\u7ad9\u770b\u5230\u7684\u5c31\u662f\u4ee3\u7406\u670d\u52a1\u5668\u7684IP\uff0c\u800c\u4e0d\u662f\u4f60\u7684\u771f\u5b9eIP\u3002<\/p>\n\n\n\n<p>\u8fd9\u6709\u5565\u597d\u5904\u5462\uff1f<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>\u4fdd\u62a4\u9690\u79c1\uff0c\u5b89\u5168\u7b2c\u4e00<\/strong>\uff1a\u4f60\u7684\u771f\u5b9e\u8eab\u4efd\u548c\u4f4d\u7f6e\u88ab\u9690\u85cf\u8d77\u6765\uff0c\u5927\u5927\u964d\u4f4e\u4e86\u88ab\u8ffd\u8e2a\u7684\u98ce\u9669\uff0c\u8ba9\u4f60\u7684\u6570\u636e\u91c7\u96c6\u8fc7\u7a0b\u66f4\u52a0\u5b89\u5168\u653e\u5fc3\u3002<\/li>\n\n\n\n<li><strong>\u89c4\u907fIP\u5c01\u7981\uff0c\u7545\u901a\u65e0\u963b<\/strong>\uff1a\u4f60\u53ef\u4ee5\u8f6e\u6d41\u4f7f\u7528\u4e0d\u540c\u7684\u4ee3\u7406IP\u8fdb\u884c\u8bbf\u95ee\uff0c\u5373\u4f7f\u67d0\u4e2aIP\u88ab\u5c01\u4e86\uff0c\u4e5f\u80fd\u8fc5\u901f\u5207\u6362\u5230\u65b0\u7684IP\uff0c\u4fdd\u8bc1\u6570\u636e\u91c7\u96c6\u7684\u8fde\u8d2f\u6027\uff0c\u518d\u4e5f\u4e0d\u7528\u62c5\u5fc3\u201c\u65e0\u7c73\u4e0b\u9505\u201d\u4e86\u3002<\/li>\n\n\n\n<li><strong>\u7a81\u7834\u5730\u57df\u9650\u5236\uff0c\u6d77\u7eb3\u767e\u5ddd<\/strong>\uff1a\u6709\u4e9b\u7f51\u7ad9\u7684\u5185\u5bb9\u53ef\u80fd\u53ea\u5bf9\u7279\u5b9a\u5730\u533a\u5f00\u653e\uff0c\u901a\u8fc7\u4f7f\u7528\u8be5\u5730\u533a\u7684\u4ee3\u7406IP\uff0c\u4f60\u5c31\u80fd\u8f7b\u677e\u8bbf\u95ee\u8fd9\u4e9b\u201c\u5730\u57df\u9650\u5b9a\u201d\u7684\u5185\u5bb9\uff0c\u62d3\u5bbd\u4f60\u7684\u6570\u636e\u6765\u6e90\u3002<\/li>\n\n\n\n<li><strong>\u5e94\u5bf9\u9ad8\u5e76\u53d1\uff0c\u6548\u7387\u500d\u589e<\/strong>\uff1a\u5f53\u4f60\u9700\u8981\u8fdb\u884c\u5927\u89c4\u6a21\u6570\u636e\u6293\u53d6\u65f6\uff0c\u5355\u4e00IP\u7684\u8bbf\u95ee\u901f\u5ea6\u548c\u9891\u7387\u90fd\u6709\u9650\u3002\u4ee3\u7406IP\u6c60\u80fd\u8ba9\u4f60\u4ee5\u66f4\u9ad8\u7684\u5e76\u53d1\u91cf\u540c\u65f6\u53d1\u8d77\u8bf7\u6c42\uff0c\u5927\u5927\u63d0\u5347\u91c7\u96c6\u6548\u7387\u3002<\/li>\n<\/ol>\n\n\n\n<p>\u6240\u4ee5\u8bf4\uff0c\u4ee3\u7406IP\u662f\u6bcf\u4e2a\u722c\u866b\u5de5\u7a0b\u5e08\u7684\u5fc5\u5907\u6b66\u5668\uff0c\u800cScrapy\u7684Proxy Middleware\u5c31\u662f\u5e2e\u4f60\u9ad8\u6548\u7ba1\u7406\u548c\u4f7f\u7528\u8fd9\u4e9b\u4ee3\u7406IP\u7684\u5173\u952e\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h4 class=\"wp-block-heading\">\u7b2c\u4e8c\u7ae0\uff1aScrapy Proxy Middleware\uff1a\u5982\u4f55\u4e3a\u4f60\u7684\u722c\u866b\u62ab\u4e0a\u201c\u9690\u8eab\u8863\u201d<\/h4>\n\n\n\n<p>Scrapy\u4e4b\u6240\u4ee5\u5f3a\u5927\uff0c\u5f88\u91cd\u8981\u7684\u4e00\u4e2a\u539f\u56e0\u5c31\u662f\u5b83\u63d0\u4f9b\u4e86\u7075\u6d3b\u7684**Middleware\uff08\u4e2d\u95f4\u4ef6\uff09**\u673a\u5236\u3002Middleware\u5c31\u50cf\u662fScrapy\u8bf7\u6c42\u548c\u54cd\u5e94\u5904\u7406\u8fc7\u7a0b\u4e2d\u7684\u4e00\u4e2a\u4e2a\u201c\u5173\u5361\u201d\uff0c\u4f60\u53ef\u4ee5\u5728\u8fd9\u4e9b\u5173\u5361\u4e2d\u5bf9\u8bf7\u6c42\u6216\u54cd\u5e94\u8fdb\u884c\u62e6\u622a\u3001\u4fee\u6539\uff0c\u751a\u81f3\u4e22\u5f03\u3002Proxy Middleware\u5c31\u662f\u7528\u6765\u5904\u7406\u4ee3\u7406IP\u7684\u4e2d\u95f4\u4ef6\u3002<\/p>\n\n\n\n<p><strong>1. \u4ee3\u7406IP\u7684\u51c6\u5907\u2014\u2014\u9009\u62e9\u9ad8\u8d28\u91cf\u7684\u201c\u5f39\u836f\u201d<\/strong><\/p>\n\n\n\n<p>\u5de7\u5987\u96be\u4e3a\u65e0\u7c73\u4e4b\u708a\uff0c\u9ad8\u8d28\u91cf\u7684\u4ee3\u7406IP\u662f\u57fa\u7840\u3002\u5e02\u9762\u4e0a\u7684\u4ee3\u7406IP\u670d\u52a1\u5546\u6709\u5f88\u591a\uff0c\u5b83\u4eec\u63d0\u4f9b\u7684\u4ee3\u7406IP\u7c7b\u578b\u4e5f\u4e94\u82b1\u516b\u95e8\u3002\u8fd9\u91cc\u6211\u8981\u7279\u522b\u63d0\u4e00\u4e0b<strong>\u7a7f\u4e91\u4ee3\u7406IP<\/strong>\u3002<\/p>\n\n\n\n<p>\u7a7f\u4e91\u4ee3\u7406IP\u62e5\u6709<strong>\u4e1a\u5185\u9886\u5148\u7684<a href=\"https:\/\/ip.cloudbypass.com\/\">\u52a8\u6001\u4f4f\u5b85IP<\/a>\u548c<a href=\"https:\/\/ip.cloudbypass.com\/\">\u52a8\u6001\u673a\u623fIP<\/a>\u6c60<\/strong>\u3002\u8fd9\u4e24\u79cdIP\u5404\u6709\u4f18\u52bf\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u52a8\u6001\u4f4f\u5b85IP<\/strong>\uff1a\u987e\u540d\u601d\u4e49\uff0c\u8fd9\u4e9bIP\u6765\u81ea\u771f\u5b9e\u7684\u5bb6\u5ead\u5bbd\u5e26\u7f51\u7edc\uff0c\u5b83\u4eec\u770b\u8d77\u6765\u66f4\u50cf\u771f\u5b9e\u7528\u6237\u7684IP\uff0c\u88ab\u76ee\u6807\u7f51\u7ad9\u8bc6\u522b\u4e3a\u722c\u866b\u7684\u6982\u7387\u6781\u4f4e\uff0c\u56e0\u6b64<strong>\u901a\u8fc7\u7387\u6781\u9ad8<\/strong>\uff0c\u662f\u5e94\u5bf9\u9ad8\u7ea7\u53cd\u722c\u7b56\u7565\u7684\u9996\u9009\u3002\u60f3\u8c61\u4e00\u4e0b\uff0c\u7f51\u7ad9\u6839\u672c\u65e0\u6cd5\u5206\u8fa8\u4f60\u662f\u5728\u7528\u771f\u4eba\u7684\u5bb6\u5ead\u7f51\u7edc\u8bbf\u95ee\uff0c\u8fd8\u662f\u5728\u7528\u722c\u866b\u3002<\/li>\n\n\n\n<li><strong>\u52a8\u6001\u673a\u623fIP<\/strong>\uff1a\u8fd9\u7c7bIP\u901a\u5e38\u6765\u81ea\u6570\u636e\u4e2d\u5fc3\uff0c\u867d\u7136\u4e0d\u5982\u4f4f\u5b85IP\u90a3\u4e48\u201c\u81ea\u7136\u201d\uff0c\u4f46\u80dc\u5728<strong>\u6570\u91cf\u5e9e\u5927\u3001\u5e26\u5bbd\u7a33\u5b9a<\/strong>\uff0c\u975e\u5e38\u9002\u5408\u8fdb\u884c\u5927\u89c4\u6a21\u3001\u9ad8\u5e76\u53d1\u7684\u6293\u53d6\u4efb\u52a1\u3002<\/li>\n<\/ul>\n\n\n\n<p>\u7a7f\u4e91\u4ee3\u7406IP\u8fd8\u63d0\u4f9b<strong>\u6c38\u4e0d\u8fc7\u671f\u7684\u6d77\u5916\u52a8\u6001IP\u6d41\u91cf\u5305<\/strong>\uff0c\u8fd9\u610f\u5473\u7740\u4f60\u4e70\u4e00\u6b21\u6d41\u91cf\uff0c\u5c31\u80fd\u957f\u671f\u4f7f\u7528\uff0c\u4e0d\u7528\u62c5\u5fc3IP\u8fc7\u671f\u7684\u95ee\u9898\u3002\u800c\u4e14\uff0c\u5b83<strong>\u652f\u6301\u57ce\u5e02\u7ea7\u5b9a\u4f4d\u4e0e\u9ad8\u5e76\u53d1\u8bf7\u6c42<\/strong>\uff0c\u65e0\u8bba\u662f\u9700\u8981\u7cbe\u786e\u5230\u67d0\u4e2a\u57ce\u5e02\u7684IP\uff0c\u8fd8\u662f\u9700\u8981\u540c\u65f6\u53d1\u8d77\u6d77\u91cf\u8bf7\u6c42\uff0c\u5b83\u90fd\u80fd\u8f7b\u677e\u5e94\u5bf9\u3002\u8fd9\u4f7f\u5f97\u7a7f\u4e91\u4ee3\u7406IP\u6210\u4e3a<strong>\u4f01\u4e1a\u7528\u6237\u62d3\u5c55\u5168\u7403\u7f51\u7edc\u4e1a\u52a1\u7684\u4f18\u9009\u4ee3\u7406\u5e73\u53f0<\/strong>\uff0c\u56e0\u4e3a\u5b83\u80fd\u7a33\u5b9a\u5e94\u7528\u4e8e<strong>\u6307\u7eb9\u6d4f\u89c8\u5668\u4ee3\u7406IP\u63a5\u5165\u3001\u722c\u866b\u6293\u53d6\u3001\u5e7f\u544a\u9a8c\u8bc1<\/strong>\u7b49\u591a\u79cd\u9ad8\u8981\u6c42\u573a\u666f\u3002<\/p>\n\n\n\n<p><strong>2. Scrapy\u9879\u76ee\u914d\u7f6e\u2014\u2014\u8ba9Proxy Middleware\u201c\u4e0a\u5c97\u201d<\/strong><\/p>\n\n\n\n<p>\u5728\u4f60\u7684Scrapy\u9879\u76ee\u4e2d\uff0c\u6211\u4eec\u9700\u8981\u4fee\u6539<code>settings.py<\/code>\u6587\u4ef6\u548c\u7f16\u5199\u81ea\u5b9a\u4e49\u7684Proxy Middleware\u3002<\/p>\n\n\n\n<p><strong>\u7b2c\u4e00\u6b65\uff1a\u542f\u7528\u81ea\u5b9a\u4e49\u7684Proxy Middleware<\/strong><\/p>\n\n\n\n<p>\u5728<code>settings.py<\/code>\u6587\u4ef6\u4e2d\uff0c\u627e\u5230<code>DOWNLOADER_MIDDLEWARES<\/code>\u5b57\u5178\u3002\u8fd9\u662fScrapy\u7684\u4e0b\u8f7d\u5668\u4e2d\u95f4\u4ef6\u914d\u7f6e\uff0c\u4f60\u9700\u8981\u628a\u4f60\u81ea\u5b9a\u4e49\u7684Proxy Middleware\u7c7b\u6dfb\u52a0\u8fdb\u53bb\uff0c\u5e76\u8bbe\u7f6e\u4e00\u4e2a\u4f18\u5148\u7ea7\u6570\u5b57\u3002\u6570\u5b57\u8d8a\u5c0f\uff0c\u4f18\u5148\u7ea7\u8d8a\u9ad8\u3002<\/p>\n\n\n\n<p>Python<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter\"><img decoding=\"async\" src=\"https:\/\/ip.cloudbypass.com\/proxy-information\/wp-content\/uploads\/2025\/03\/image2025032618.jpg\" alt=\"\" title=\"\"><\/figure>\n<\/div>\n\n\n<pre class=\"wp-block-code\"><code># settings.py\nDOWNLOADER_MIDDLEWARES = {\n    'myproject.middlewares.RandomProxyMiddleware': 543, # 543\u53ea\u662f\u4e00\u4e2a\u793a\u4f8b\u503c\uff0c\u53ea\u8981\u4e0d\u548c\u5176\u4ed6\u91cd\u8981\u7684\u4e2d\u95f4\u4ef6\u51b2\u7a81\u5373\u53ef\n    # \u5176\u4ed6\u4e2d\u95f4\u4ef6...\n}\n<\/code><\/pre>\n\n\n\n<p><strong>\u7b2c\u4e8c\u6b65\uff1a\u51c6\u5907\u4ee3\u7406IP\u5217\u8868\uff08\u65b9\u5f0f\u4e00\uff1a\u76f4\u63a5\u914d\u7f6e\uff09<\/strong><\/p>\n\n\n\n<p>\u5982\u679c\u4f60\u9009\u62e9\u5c06\u4ee3\u7406IP\u76f4\u63a5\u914d\u7f6e\u5728<code>settings.py<\/code>\u4e2d\uff0c\u53ef\u4ee5\u521b\u5efa\u4e00\u4e2a\u5217\u8868\uff1a<\/p>\n\n\n\n<p>Python<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># settings.py\n# \u793a\u4f8b\uff1a\u5047\u8bbe\u4f60\u7684\u4ee3\u7406IP\u662fHTTP\u7c7b\u578b\nPROXIES = &#91;\n    {'ip_port': 'http:\/\/1.1.1.1:8888', 'user_pass': 'user:password'}, # \u5982\u679c\u4ee3\u7406\u9700\u8981\u8ba4\u8bc1\n    {'ip_port': 'http:\/\/2.2.2.2:9999'},\n    # \u66f4\u591a\u4ee3\u7406IP...\n]\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u79cd\u65b9\u5f0f\u9002\u5408\u4ee3\u7406IP\u6570\u91cf\u4e0d\u591a\uff0c\u6216\u8005\u4ee3\u7406IP\u76f8\u5bf9\u56fa\u5b9a\u7684\u573a\u666f\u3002<\/p>\n\n\n\n<p><strong>3. \u7f16\u5199Proxy Middleware\u2014\u2014\u4f60\u7684\u201c\u4ee3\u7406\u8c03\u5ea6\u5458\u201d<\/strong><\/p>\n\n\n\n<p>\u8fd9\u662f\u6838\u5fc3\u73af\u8282\u3002\u4f60\u9700\u8981\u521b\u5efa\u4e00\u4e2aPython\u6587\u4ef6\uff08\u901a\u5e38\u5728\u9879\u76ee\u6839\u76ee\u5f55\u4e0b\u7684<code>myproject\/middlewares.py<\/code>\uff09\uff0c\u7136\u540e\u7f16\u5199\u4f60\u7684Proxy Middleware\u7c7b\u3002\u8fd9\u4e2a\u7c7b\u9700\u8981\u5b9e\u73b0<code>process_request<\/code>\u65b9\u6cd5\u3002<\/p>\n\n\n\n<p>Python<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># myproject\/middlewares.py\nimport random\nfrom scrapy.exceptions import NotConfigured\nfrom scrapy.utils.project import get_project_settings\n\nclass RandomProxyMiddleware(object):\n    \"\"\"\n    \u968f\u673a\u9009\u62e9\u4e00\u4e2a\u4ee3\u7406IP\u5e76\u5c06\u5176\u6dfb\u52a0\u5230\u8bf7\u6c42\u4e2d\n    \"\"\"\n    def __init__(self, settings):\n        self.proxies = settings.getlist('PROXIES')\n        if not self.proxies:\n            raise NotConfigured(\"\u672a\u5728 settings.py \u4e2d\u914d\u7f6e PROXIES \u5217\u8868\uff01\")\n\n    @classmethod\n    def from_crawler(cls, crawler):\n        return cls(crawler.settings)\n\n    def process_request(self, request, spider):\n        # \u5982\u679c\u8bf7\u6c42\u5df2\u7ecf\u6709\u4e86\u4ee3\u7406\u8bbe\u7f6e\uff0c\u5219\u8df3\u8fc7\n        if 'proxy' in request.meta:\n            return\n\n        # \u968f\u673a\u9009\u62e9\u4e00\u4e2a\u4ee3\u7406IP\n        proxy = random.choice(self.proxies)\n        request.meta&#91;'proxy'] = proxy&#91;'ip_port']\n        print(f\"\u6b63\u5728\u4e3a\u8bf7\u6c42 {request.url} \u4f7f\u7528\u4ee3\u7406: {proxy&#91;'ip_port']}\")\n\n        # \u5982\u679c\u4ee3\u7406\u9700\u8981\u8ba4\u8bc1\uff0c\u5219\u6dfb\u52a0\u8ba4\u8bc1\u4fe1\u606f\n        if proxy.get('user_pass'):\n            encoded_user_pass = base64.b64encode(proxy&#91;'user_pass'].encode()).decode()\n            request.headers&#91;'Proxy-Authorization'] = f'Basic {encoded_user_pass}'\n            print(f\"\u4ee3\u7406\u9700\u8981\u8ba4\u8bc1\uff0c\u6dfb\u52a0\u4e86\u8ba4\u8bc1\u4fe1\u606f\u3002\")\n\n<\/code><\/pre>\n\n\n\n<p><strong>\u4ee3\u7801\u89e3\u6790\uff1a<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><code>__init__<\/code>\u548c<code>from_crawler<\/code>\uff1a\u8fd9\u662fScrapy\u4e2d\u95f4\u4ef6\u7684\u521d\u59cb\u5316\u65b9\u6cd5\uff0c\u7528\u4e8e\u83b7\u53d6<code>settings.py<\/code>\u4e2d\u7684\u914d\u7f6e\u4fe1\u606f\uff0c\u8fd9\u91cc\u662f\u83b7\u53d6<code>PROXIES<\/code>\u5217\u8868\u3002<\/li>\n\n\n\n<li><code>process_request(self, request, spider)<\/code>\uff1a\u8fd9\u662f\u5173\u952e\u65b9\u6cd5\u3002Scrapy\u5728\u53d1\u9001\u6bcf\u4e2a\u8bf7\u6c42\u4e4b\u524d\uff0c\u90fd\u4f1a\u8c03\u7528\u8fd9\u4e2a\u65b9\u6cd5\u3002\n<ul class=\"wp-block-list\">\n<li>\u5b83\u9996\u5148\u68c0\u67e5<code>request.meta<\/code>\u4e2d\u662f\u5426\u5df2\u7ecf\u6709\u4e86<code>proxy<\/code>\u952e\u3002\u8fd9\u662f\u4e3a\u4e86\u907f\u514d\u91cd\u590d\u8bbe\u7f6e\u4ee3\u7406\uff0c\u6216\u8005\u5982\u679c\u4f60\u6709\u5176\u4ed6\u66f4\u9ad8\u7ea7\u7684\u4ee3\u7406\u903b\u8f91\uff0c\u53ef\u4ee5\u81ea\u884c\u63a7\u5236\u3002<\/li>\n\n\n\n<li><code>random.choice(self.proxies)<\/code>\uff1a\u4ece\u6211\u4eec\u914d\u7f6e\u7684\u4ee3\u7406IP\u5217\u8868\u4e2d\u968f\u673a\u9009\u62e9\u4e00\u4e2aIP\u3002\u8fd9\u662f\u6700\u57fa\u672c\u7684\u8f6e\u6362\u7b56\u7565\uff0c\u53ef\u4ee5\u6709\u6548\u5206\u6563\u8bf7\u6c42\u538b\u529b\u3002<\/li>\n\n\n\n<li><code>request.meta['proxy'] = proxy['ip_port']<\/code>\uff1a\u5c06\u9009\u5b9a\u7684\u4ee3\u7406IP\u8bbe\u7f6e\u5230\u8bf7\u6c42\u7684<code>meta<\/code>\u5c5e\u6027\u4e2d\u3002Scrapy\u4f1a\u8bc6\u522b\u8fd9\u4e2a<code>proxy<\/code>\u952e\uff0c\u5e76\u901a\u8fc7\u8fd9\u4e2a\u4ee3\u7406\u53d1\u9001\u8bf7\u6c42\u3002<\/li>\n\n\n\n<li><strong>\u4ee3\u7406\u8ba4\u8bc1<\/strong>\uff1a\u5982\u679c\u4f60\u7684\u4ee3\u7406IP\u9700\u8981\u7528\u6237\u540d\u548c\u5bc6\u7801\u8ba4\u8bc1\uff08\u6bd4\u5982\u7a7f\u4e91\u4ee3\u7406IP\uff09\uff0c\u4f60\u9700\u8981\u5c06\u8ba4\u8bc1\u4fe1\u606f\u4ee5<code>Proxy-Authorization<\/code>\u5934\u7684\u5f62\u5f0f\u6dfb\u52a0\u5230\u8bf7\u6c42\u4e2d\u3002\u6ce8\u610f\uff0c<code>user:password<\/code>\u9700\u8981\u8fdb\u884cBase64\u7f16\u7801\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n\n\n\n<p><strong>4. \u7ed3\u5408Spider\u4f7f\u7528\u2014\u2014\u65e0\u611f\u63a5\u5165<\/strong><\/p>\n\n\n\n<p>\u4e00\u65e6Proxy Middleware\u8bbe\u7f6e\u597d\u5e76\u542f\u7528\uff0c\u4f60\u7684Spider\u4ee3\u7801\u51e0\u4e4e\u4e0d\u9700\u8981\u505a\u4efb\u4f55\u6539\u52a8\u3002\u56e0\u4e3aMiddleware\u4f1a\u5728\u8bf7\u6c42\u53d1\u9001\u51fa\u53bb\u4e4b\u524d\u81ea\u52a8\u6dfb\u52a0\u4ee3\u7406\u4fe1\u606f\uff0c\u4f60\u7684Spider\u53ef\u4ee5\u50cf\u5f80\u5e38\u4e00\u6837\u7f16\u5199\u3002<\/p>\n\n\n\n<p>Python<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>import scrapy\n\nclass MySpider(scrapy.Spider):\n    name = 'myspider'\n    start_urls = &#91;'http:\/\/quotes.toscrape.com\/'] # \u4f60\u7684\u76ee\u6807URL\n\n    def parse(self, response):\n        # \u6b63\u5e38\u89e3\u6790\u9875\u9762\u5185\u5bb9\uff0c\u65e0\u9700\u5173\u5fc3\u4ee3\u7406IP\u7684\u7ec6\u8282\n        title = response.css('title::text').get()\n        print(f\"\u9875\u9762\u6807\u9898: {title}\")\n        # \u7ee7\u7eed\u722c\u53d6\u5176\u4ed6\u94fe\u63a5\u6216\u6570\u636e\n        for quote in response.css('div.quote'):\n            text = quote.css('span.text::text').get()\n            author = quote.css('small.author::text').get()\n            yield {\n                'text': text,\n                'author': author,\n            }\n\n        next_page = response.css('li.next a::attr(href)').get()\n        if next_page is not None:\n            yield response.follow(next_page, callback=self.parse)\n<\/code><\/pre>\n\n\n\n<p>\u4f60\u4f1a\u53d1\u73b0\uff0c\u5373\u4f7fSpider\u4ee3\u7801\u5f88\u7b80\u5355\uff0c\u4f46\u5b9e\u9645\u4e0a\u6bcf\u4e2a\u8bf7\u6c42\u90fd\u53ef\u80fd\u901a\u8fc7\u4e0d\u540c\u7684\u4ee3\u7406IP\u53d1\u9001\uff0c\u4ece\u800c\u8fbe\u5230\u4e86\u53cd\u8ffd\u8e2a\u548c\u907f\u514d\u5c01\u7981\u7684\u76ee\u7684\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h4 class=\"wp-block-heading\">\u7b2c\u4e09\u7ae0\uff1a\u9ad8\u7ea7\u73a9\u6cd5\uff1a\u52a8\u6001\u4ee3\u7406IP\u6c60\u4e0e\u7a7f\u4e91\u4ee3\u7406IP\u7684\u6df1\u5ea6\u878d\u5408<\/h4>\n\n\n\n<p>\u76f4\u63a5\u5728<code>settings.py<\/code>\u4e2d\u914d\u7f6e\u4ee3\u7406IP\u5217\u8868\u7684\u65b9\u5f0f\u867d\u7136\u7b80\u5355\uff0c\u4f46\u5bf9\u4e8e\u5927\u89c4\u6a21\u3001\u957f\u671f\u8fd0\u884c\u7684\u722c\u866b\u6765\u8bf4\uff0c\u5e76\u4e0d\u591f\u7075\u6d3b\u3002\u56e0\u4e3a\u4ee3\u7406IP\u7684\u53ef\u7528\u6027\u662f\u4f1a\u53d8\u5316\u7684\uff0c\u6709\u4e9b\u53ef\u80fd\u4f1a\u5931\u6548\uff0c\u6709\u4e9b\u53ef\u80fd\u901f\u5ea6\u53d8\u6162\u3002\u8fd9\u65f6\u5019\uff0c\u6211\u4eec\u5c31\u9700\u8981\u4e00\u4e2a<strong>\u52a8\u6001\u4ee3\u7406IP\u6c60<\/strong>\u3002<\/p>\n\n\n\n<p>\u52a8\u6001\u4ee3\u7406IP\u6c60\u901a\u5e38\u7531\u4ee5\u4e0b\u51e0\u4e2a\u90e8\u5206\u7ec4\u6210\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>IP\u83b7\u53d6\u6a21\u5757<\/strong>\uff1a\u4ece\u4ee3\u7406\u670d\u52a1\u5546\uff08\u6bd4\u5982\u7a7f\u4e91\u4ee3\u7406IP\uff09\u83b7\u53d6\u65b0\u7684\u53ef\u7528IP\u3002<\/li>\n\n\n\n<li><strong>IP\u68c0\u6d4b\u6a21\u5757<\/strong>\uff1a\u5b9a\u671f\u68c0\u6d4b\u6c60\u4e2dIP\u7684\u53ef\u7528\u6027\u3001\u901f\u5ea6\u548c\u533f\u540d\u5ea6\uff0c\u6dd8\u6c70\u6389\u4e0d\u53ef\u7528\u7684IP\u3002<\/li>\n\n\n\n<li><strong>IP\u8c03\u5ea6\u6a21\u5757<\/strong>\uff1a\u6839\u636e\u7b56\u7565\uff08\u4f8b\u5982\u968f\u673a\u3001\u8f6e\u8be2\u3001\u6839\u636e\u6210\u529f\u7387\u9009\u62e9\u7b49\uff09\u4e3a\u8bf7\u6c42\u5206\u914dIP\u3002<\/li>\n<\/ul>\n\n\n\n<p><strong>\u5982\u4f55\u5c06\u7a7f\u4e91\u4ee3\u7406IP\u4e0eScrapy\u6df1\u5ea6\u878d\u5408\uff1f<\/strong><\/p>\n\n\n\n<p>\u7a7f\u4e91\u4ee3\u7406IP\u63d0\u4f9b\u4e86\u975e\u5e38\u7075\u6d3b\u7684\u63a5\u53e3\uff0c\u4f60\u53ef\u4ee5\u901a\u8fc7API\u8bf7\u6c42\u6765\u83b7\u53d6\u4ee3\u7406IP\u3002\u8fd9\u610f\u5473\u7740\u4f60\u53ef\u4ee5\u5728\u4f60\u7684Proxy Middleware\u4e2d\uff0c<strong>\u52a8\u6001\u5730\u5411\u7a7f\u4e91API\u53d1\u9001\u8bf7\u6c42\uff0c\u83b7\u53d6\u6700\u65b0\u7684\u3001\u9ad8\u8d28\u91cf\u7684\u4ee3\u7406IP\uff0c\u5e76\u5c06\u5176\u5e94\u7528\u4e8e\u5f53\u524d\u8bf7\u6c42\u3002<\/strong><\/p>\n\n\n\n<p><strong>\u4ee5\u7a7f\u4e91\u4ee3\u7406IP\u4e3a\u4f8b\u7684\u96c6\u6210\u601d\u8def\uff1a<\/strong><\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>API\u96c6\u6210<\/strong>\uff1a\u4f60\u7684Proxy Middleware\u4e0d\u518d\u4ec5\u4ec5\u662f\u4ece\u672c\u5730\u5217\u8868\u83b7\u53d6IP\uff0c\u800c\u662f\u901a\u8fc7<code>requests<\/code>\u5e93\u7b49\u5de5\u5177\uff0c\u5411\u7a7f\u4e91\u4ee3\u7406IP\u7684API\u63a5\u53e3\u53d1\u8d77\u8bf7\u6c42\uff0c\u83b7\u53d6\u4e00\u4e2a<strong>\u6c38\u4e0d\u8fc7\u671f\u4e14\u9ad8\u8d28\u91cf<\/strong>\u7684\u52a8\u6001\u4f4f\u5b85IP\u6216\u673a\u623fIP\u3002\u7a7f\u4e91\u4ee3\u7406IP\u652f\u6301<strong>\u9ad8\u5e76\u53d1\u8bf7\u6c42<\/strong>\uff0c\u6240\u4ee5\u4f60\u53ef\u4ee5\u653e\u5fc3\u5927\u80c6\u5730\u5728Middleware\u4e2d\u8c03\u7528\u3002<\/li>\n\n\n\n<li><strong>IP\u7f13\u5b58\u4e0e\u5237\u65b0<\/strong>\uff1a\u4e3a\u4e86\u907f\u514d\u6bcf\u6b21\u8bf7\u6c42\u90fd\u53bb\u8c03\u7528API\uff0c\u4f60\u53ef\u4ee5\u8003\u8651\u5728Middleware\u5185\u90e8\u7ef4\u62a4\u4e00\u4e2a\u5c0f\u7684IP\u7f13\u5b58\u3002\u4f8b\u5982\uff0c\u6bcf\u6b21\u4ece\u7a7f\u4e91API\u83b7\u53d6\u4e00\u6279IP\uff0c\u5b58\u5165\u5185\u5b58\uff0c\u7528\u5b8c\u6216\u8005\u5931\u6548\u540e\u518d\u53bb\u83b7\u53d6\u65b0\u7684\u3002<\/li>\n\n\n\n<li><strong>\u9519\u8bef\u5904\u7406\u4e0eIP\u5207\u6362<\/strong>\uff1a\u5f53\u67d0\u4e2a\u4ee3\u7406IP\u8fd4\u56de\u9519\u8bef\u72b6\u6001\u7801\uff08\u4f8b\u5982403\u3001500\uff09\u6216\u8005\u8fde\u63a5\u8d85\u65f6\u65f6\uff0cProxy Middleware\u5e94\u8be5\u80fd\u591f\u8bc6\u522b\u5e76\u6807\u8bb0\u8fd9\u4e2aIP\u4e3a\u4e0d\u53ef\u7528\uff0c\u7136\u540e\u4ece\u7a7f\u4e91\u4ee3\u7406IP\u6c60\u4e2d<strong>\u83b7\u53d6\u4e00\u4e2a\u65b0\u7684IP\u8fdb\u884c\u91cd\u8bd5<\/strong>\u3002\u7a7f\u4e91\u4ee3\u7406IP\u63d0\u4f9b\u7684<strong>\u57ce\u5e02\u7ea7\u5b9a\u4f4d<\/strong>\u529f\u80fd\uff0c\u4e5f\u80fd\u8ba9\u4f60\u5728IP\u5931\u6548\u540e\uff0c\u8fc5\u901f\u5207\u6362\u5230\u540c\u4e00\u57ce\u5e02\u6216\u90bb\u8fd1\u57ce\u5e02\u7684\u5176\u4ed6\u53ef\u7528IP\uff0c\u4fdd\u8bc1\u6570\u636e\u7684\u8fde\u7eed\u6027\u3002<\/li>\n<\/ol>\n\n\n\n<p><strong>\u793a\u4f8b\u4ee3\u7801\u7247\u6bb5\uff08\u6982\u5ff5\u6027\uff0c\u9700\u6839\u636e\u7a7f\u4e91API\u6587\u6863\u7ec6\u5316\uff09\uff1a<\/strong><\/p>\n\n\n\n<p>Python<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># myproject\/middlewares.py (\u5047\u8bbe\u4f60\u7684\u7a7f\u4e91API\u8fd4\u56deJSON\u683c\u5f0f\u7684\u4ee3\u7406\u4fe1\u606f)\nimport requests\nimport json\nimport base64\nimport random\nfrom scrapy.exceptions import NotConfigured\nfrom scrapy.utils.project import get_project_settings\n\nclass CloudBypassProxyMiddleware(object):\n    def __init__(self, settings):\n        self.api_url = settings.get('CLOUDBYPASS_API_URL')\n        self.api_key = settings.get('CLOUDBYPASS_API_KEY') # \u5982\u679cAPI\u9700\u8981\u8ba4\u8bc1\n        self.proxy_cache = &#91;] # \u7f13\u5b58\u4eceAPI\u83b7\u53d6\u7684\u4ee3\u7406IP\n        self.max_cache_size = 10 # \u7f13\u5b58\u7684\u4ee3\u7406IP\u6570\u91cf\n        self.get_new_proxy() # \u521d\u59cb\u5316\u65f6\u83b7\u53d6\u4e00\u6279\u4ee3\u7406\n\n        if not self.api_url:\n            raise NotConfigured(\"\u8bf7\u5728 settings.py \u4e2d\u914d\u7f6e CLOUDBYPASS_API_URL\uff01\")\n\n    @classmethod\n    def from_crawler(cls, crawler):\n        return cls(crawler.settings)\n\n    def get_new_proxy(self):\n        \"\"\"\u4ece\u7a7f\u4e91API\u83b7\u53d6\u65b0\u7684\u4ee3\u7406IP\"\"\"\n        headers = {\n            \"Content-Type\": \"application\/json\",\n            # \u5982\u679cAPI\u9700\u8981\u8ba4\u8bc1\uff0c\u8bf7\u6dfb\u52a0 Authorization header\n            # \"Authorization\": f\"Bearer {self.api_key}\"\n        }\n        # \u5b9e\u9645\u7684\u8bf7\u6c42\u53c2\u6570\u548c\u8fd4\u56de\u683c\u5f0f\u8bf7\u53c2\u7167\u7a7f\u4e91API\u6587\u6863\n        payload = {\n            \"type\": \"residential\", # \u6216\u8005 \"datacenter\"\uff0c\u6839\u636e\u9700\u6c42\u9009\u62e9\n            \"count\": self.max_cache_size # \u8bf7\u6c42\u4e00\u6279\u4ee3\u7406IP\n        }\n        try:\n            response = requests.post(self.api_url, headers=headers, json=payload, timeout=10)\n            response.raise_for_status() # \u68c0\u67e5HTTP\u9519\u8bef\n            data = response.json()\n            if data and data.get('success') and data.get('proxies'):\n                self.proxy_cache = &#91;{'ip_port': f\"{p&#91;'protocol']}:\/\/{p&#91;'ip']}:{p&#91;'port']}\", 'user_pass': p.get('username_password')} for p in data&#91;'proxies']]\n                print(f\"\u6210\u529f\u4ece\u7a7f\u4e91API\u83b7\u53d6 {len(self.proxy_cache)} \u4e2a\u65b0\u4ee3\u7406IP\u3002\")\n            else:\n                print(f\"\u4ece\u7a7f\u4e91API\u83b7\u53d6\u4ee3\u7406\u5931\u8d25: {data.get('message', '\u672a\u77e5\u9519\u8bef')}\")\n        except requests.exceptions.RequestException as e:\n            print(f\"\u8c03\u7528\u7a7f\u4e91API\u51fa\u9519: {e}\")\n            self.proxy_cache = &#91;] # \u6e05\u7a7a\u7f13\u5b58\uff0c\u7b49\u5f85\u4e0b\u6b21\u83b7\u53d6\n\n    def process_request(self, request, spider):\n        if 'proxy' in request.meta:\n            return\n\n        if not self.proxy_cache:\n            print(\"\u4ee3\u7406IP\u7f13\u5b58\u4e3a\u7a7a\uff0c\u5c1d\u8bd5\u91cd\u65b0\u83b7\u53d6...\")\n            self.get_new_proxy()\n            if not self.proxy_cache:\n                print(\"\u672a\u80fd\u83b7\u53d6\u5230\u53ef\u7528\u4ee3\u7406IP\uff0c\u8bf7\u6c42\u5c06\u4e0d\u4f7f\u7528\u4ee3\u7406\u3002\")\n                return\n\n        proxy_info = random.choice(self.proxy_cache)\n        request.meta&#91;'proxy'] = proxy_info&#91;'ip_port']\n        print(f\"\u6b63\u5728\u4e3a\u8bf7\u6c42 {request.url} \u4f7f\u7528\u7a7f\u4e91\u4ee3\u7406: {proxy_info&#91;'ip_port']}\")\n\n        if proxy_info.get('user_pass'):\n            encoded_user_pass = base64.b64encode(proxy_info&#91;'user_pass'].encode()).decode()\n            request.headers&#91;'Proxy-Authorization'] = f'Basic {encoded_user_pass}'\n            print(f\"\u7a7f\u4e91\u4ee3\u7406\u9700\u8981\u8ba4\u8bc1\uff0c\u6dfb\u52a0\u4e86\u8ba4\u8bc1\u4fe1\u606f\u3002\")\n\n    def process_exception(self, request, exception, spider):\n        # \u5f53\u8bf7\u6c42\u53d1\u751f\u5f02\u5e38\u65f6\uff08\u4f8b\u5982\u4ee3\u7406\u8fde\u63a5\u5931\u8d25\uff09\uff0c\u53ef\u4ee5\u8003\u8651\u5c06\u5f53\u524d\u4f7f\u7528\u7684\u4ee3\u7406\u4ece\u7f13\u5b58\u4e2d\u79fb\u9664\n        if 'proxy' in request.meta:\n            failed_proxy = request.meta&#91;'proxy']\n            print(f\"\u4ee3\u7406 {failed_proxy} \u53d1\u751f\u5f02\u5e38: {exception}\uff0c\u5c1d\u8bd5\u4ece\u7f13\u5b58\u4e2d\u79fb\u9664\u3002\")\n            # \u7b80\u5355\u79fb\u9664\uff0c\u66f4\u590d\u6742\u7684\u903b\u8f91\u53ef\u80fd\u9700\u8981\u6839\u636e\u5f02\u5e38\u7c7b\u578b\u5224\u65ad\u662f\u5426\u662f\u4ee3\u7406\u95ee\u9898\n            self.proxy_cache = &#91;p for p in self.proxy_cache if p&#91;'ip_port'] != failed_proxy]\n            if not self.proxy_cache:\n                print(\"\u6240\u6709\u7f13\u5b58\u4ee3\u7406\u5747\u5df2\u5931\u6548\uff0c\u5c06\u5c1d\u8bd5\u91cd\u65b0\u83b7\u53d6...\")\n                self.get_new_proxy() # \u7f13\u5b58\u4e3a\u7a7a\u65f6\uff0c\u5c1d\u8bd5\u91cd\u65b0\u83b7\u53d6\n\n\n# settings.py \u4e2d\u914d\u7f6e\u7a7f\u4e91API\u7684URL\u548cKey\nCLOUDBYPASS_API_URL = '\u4f60\u7684\u7a7f\u4e91\u4ee3\u7406API\u63a5\u53e3\u5730\u5740'\nCLOUDBYPASS_API_KEY = '\u4f60\u7684API Key' # \u5982\u679c\u6709\n<\/code><\/pre>\n\n\n\n<p><strong>\u8fd9\u79cd\u6df1\u5ea6\u878d\u5408\u7684\u597d\u5904\u663e\u800c\u6613\u89c1\uff1a<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>IP\u6c38\u4e0d\u8fc7\u671f<\/strong>\uff1a\u4f60\u4e0d\u518d\u9700\u8981\u624b\u52a8\u7ef4\u62a4IP\u5217\u8868\uff0c\u7a7f\u4e91API\u63d0\u4f9b\u7684\u662f\u6309\u6d41\u91cf\u6216\u6309\u8bf7\u6c42\u8ba1\u8d39\u7684\u52a8\u6001IP\uff0c\u786e\u4fdd\u4f60\u603b\u80fd\u62ff\u5230\u65b0\u9c9c\u53ef\u7528\u7684IP\u3002<\/li>\n\n\n\n<li><strong>\u9ad8\u53ef\u7528\u6027<\/strong>\uff1a\u7a7f\u4e91\u4ee3\u7406IP\u7684\u52a8\u6001\u4f4f\u5b85IP\u548c\u673a\u623fIP\u6c60\u7ecf\u8fc7\u4f18\u5316\uff0c\u80fd\u63d0\u4f9b\u6781\u9ad8\u7684\u901a\u8fc7\u7387\u548c\u7a33\u5b9a\u6027\uff0c\u5927\u5927\u51cf\u5c11\u56e0IP\u95ee\u9898\u5bfc\u81f4\u7684\u722c\u866b\u4e2d\u65ad\u3002<\/li>\n\n\n\n<li><strong>\u81ea\u52a8\u5316\u7ba1\u7406<\/strong>\uff1aProxy Middleware\u81ea\u52a8\u5904\u7406IP\u7684\u83b7\u53d6\u3001\u9009\u62e9\u548c\u9519\u8bef\u91cd\u8bd5\uff0c\u8ba9\u4f60\u628a\u66f4\u591a\u7cbe\u529b\u653e\u5728\u6570\u636e\u89e3\u6790\u548c\u4e1a\u52a1\u903b\u8f91\u4e0a\u3002<\/li>\n\n\n\n<li><strong>\u591a\u573a\u666f\u9002\u7528<\/strong>\uff1a\u65e0\u8bba\u662f\u5e38\u89c4\u7684\u722c\u866b\u6293\u53d6\uff0c\u8fd8\u662f\u5bf9IP\u8d28\u91cf\u8981\u6c42\u6781\u9ad8\u7684\u5e7f\u544a\u9a8c\u8bc1\u3001\u6307\u7eb9\u6d4f\u89c8\u5668\u63a5\u5165\u7b49\u573a\u666f\uff0c\u7a7f\u4e91\u4ee3\u7406IP\u90fd\u80fd\u63d0\u4f9b\u7a33\u5b9a\u53ef\u9760\u7684\u89e3\u51b3\u65b9\u6848\u3002<\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h4 class=\"wp-block-heading\">\u7b2c\u56db\u7ae0\uff1a\u722c\u866b\u5b89\u5168\u4e0e\u6548\u7387\u7684\u201c\u9ec4\u91d1\u6cd5\u5219\u201d<\/h4>\n\n\n\n<p>\u9664\u4e86Proxy Middleware\u548c\u9ad8\u8d28\u91cf\u7684\u4ee3\u7406IP\uff0c\u8fd8\u6709\u4e00\u4e9b\u201c\u9ec4\u91d1\u6cd5\u5219\u201d\u80fd\u8ba9\u4f60\u7684\u722c\u866b\u66f4\u5b89\u5168\u3001\u66f4\u9ad8\u6548\uff1a<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>User-Agent\u8f6e\u6362<\/strong>\uff1a\u76ee\u6807\u7f51\u7ad9\u9664\u4e86\u68c0\u67e5IP\uff0c\u8fd8\u4f1a\u68c0\u67e5\u4f60\u7684\u6d4f\u89c8\u5668User-Agent\u3002\u7ef4\u62a4\u4e00\u4e2aUser-Agent\u6c60\uff0c\u6bcf\u6b21\u8bf7\u6c42\u968f\u673a\u9009\u62e9\u4e00\u4e2a\uff0c\u80fd\u8ba9\u4f60\u770b\u8d77\u6765\u66f4\u50cf\u201c\u6b63\u5e38\u7528\u6237\u201d\u3002Scrapy\u7684<code>UserAgentMiddleware<\/code>\u53ef\u4ee5\u5e2e\u52a9\u4f60\u3002<\/li>\n\n\n\n<li><strong>Referer\u8bbe\u7f6e<\/strong>\uff1a\u4f2a\u9020<code>Referer<\/code>\u5934\uff0c\u8ba9\u4f60\u7684\u8bf7\u6c42\u770b\u8d77\u6765\u662f\u4ece\u67d0\u4e2a\u5408\u6cd5\u9875\u9762\u8df3\u8f6c\u800c\u6765\uff0c\u4e5f\u80fd\u589e\u52a0\u8ff7\u60d1\u6027\u3002<\/li>\n\n\n\n<li><strong>\u4e0b\u8f7d\u5ef6\u8fdf\uff08DOWNLOAD_DELAY\uff09<\/strong>\uff1a\u8bbe\u7f6e\u8bf7\u6c42\u4e4b\u95f4\u7684\u5ef6\u8fdf\u65f6\u95f4\uff0c\u4e0d\u8981\u5bf9\u76ee\u6807\u7f51\u7ad9\u8fdb\u884c\u201c\u72c2\u8f70\u6ee5\u70b8\u201d\uff0c\u7ed9\u670d\u52a1\u5668\u7559\u70b9\u5598\u606f\u7a7a\u95f4\uff0c\u964d\u4f4e\u88ab\u8bc6\u522b\u548c\u5c01\u7981\u7684\u98ce\u9669\u3002<\/li>\n\n\n\n<li><strong>\u5e76\u53d1\u8bf7\u6c42\u63a7\u5236<\/strong>\uff1a\u5408\u7406\u8bbe\u7f6e<code>CONCURRENT_REQUESTS<\/code>\uff0c\u63a7\u5236\u540c\u65f6\u53d1\u51fa\u7684\u8bf7\u6c42\u6570\u91cf\uff0c\u907f\u514d\u7ed9\u76ee\u6807\u7f51\u7ad9\u9020\u6210\u8fc7\u5927\u538b\u529b\uff0c\u4e5f\u80fd\u51cf\u5c11\u81ea\u8eab\u670d\u52a1\u5668\u7684\u8d1f\u8f7d\u3002<\/li>\n\n\n\n<li><strong>Cookie\u7ba1\u7406<\/strong>\uff1a\u6709\u4e9b\u7f51\u7ad9\u901a\u8fc7Cookie\u8ddf\u8e2a\u7528\u6237\u4f1a\u8bdd\u3002Scrapy\u7684Cookie Middleware\u80fd\u5e2e\u4f60\u7ba1\u7406Cookie\uff0c\u5fc5\u8981\u65f6\u6e05\u9664\u6216\u66f4\u65b0Cookie\uff0c\u6a21\u62df\u65b0\u4f1a\u8bdd\u3002<\/li>\n\n\n\n<li><strong>\u8bf7\u6c42\u5934\u4f2a\u88c5<\/strong>\uff1a\u9664\u4e86UA\u548cReferer\uff0c\u8fd8\u53ef\u4ee5\u8bbe\u7f6e\u5176\u4ed6\u8bf7\u6c42\u5934\uff0c\u4f8b\u5982<code>Accept<\/code>\u3001<code>Accept-Language<\/code>\u7b49\uff0c\u8ba9\u8bf7\u6c42\u770b\u8d77\u6765\u66f4\u5b8c\u6574\u3001\u66f4\u771f\u5b9e\u3002<\/li>\n\n\n\n<li><strong>\u5f02\u5e38\u5904\u7406\u4e0e\u91cd\u8bd5<\/strong>\uff1a\u5728\u4ee3\u7801\u4e2d\u505a\u597d\u9519\u8bef\u5904\u7406\uff0c\u4f8b\u5982\u7f51\u7edc\u8d85\u65f6\u3001\u4ee3\u7406\u5931\u6548\u3001HTTP\u72b6\u6001\u7801\u975e200\u7b49\u3002Scrapy\u7684\u91cd\u8bd5Middleware\u53ef\u4ee5\u5e2e\u52a9\u4f60\uff0c\u4f46\u4f60\u4e5f\u53ef\u4ee5\u5728\u81ea\u5b9a\u4e49Middleware\u4e2d\u5b9e\u73b0\u66f4\u7cbe\u7ec6\u7684\u91cd\u8bd5\u903b\u8f91\uff0c\u4f8b\u5982\u9488\u5bf9\u4ee3\u7406\u5931\u6548\u7684\u91cd\u8bd5\u3002<\/li>\n\n\n\n<li><strong>\u65e5\u5fd7\u8bb0\u5f55<\/strong>\uff1a\u8be6\u7ec6\u7684\u65e5\u5fd7\u80fd\u8ba9\u4f60\u6e05\u6670\u5730\u4e86\u89e3\u722c\u866b\u7684\u8fd0\u884c\u72b6\u6001\uff0c\u54ea\u4e2aIP\u5728\u54ea\u4e2a\u65f6\u95f4\u70b9\u8bf7\u6c42\u4e86\u54ea\u4e2aURL\uff0c\u662f\u5426\u6210\u529f\uff0c\u662f\u5426\u6709\u5f02\u5e38\u3002\u8fd9\u5bf9\u4e8e\u8c03\u8bd5\u548c\u4f18\u5316\u81f3\u5173\u91cd\u8981\u3002<\/li>\n\n\n\n<li><strong>\u9075\u5faa<code>robots.txt<\/code><\/strong>\uff1a\u4f5c\u4e3a\u201c\u6709\u9053\u5fb7\u201d\u7684\u722c\u866b\uff0c\u59cb\u7ec8\u68c0\u67e5\u5e76\u9075\u5faa\u76ee\u6807\u7f51\u7ad9\u7684<code>robots.txt<\/code>\u6587\u4ef6\uff0c\u5c0a\u91cd\u7f51\u7ad9\u7684\u722c\u53d6\u89c4\u5219\u3002<\/li>\n<\/ol>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h4 class=\"wp-block-heading\">\u7b2c\u4e94\u7ae0\uff1a\u603b\u7ed3\u4e0e\u5c55\u671b<\/h4>\n\n\n\n<p>Scrapy Proxy Middleware\u662f\u5b9e\u73b0\u722c\u866b\u53cd\u8ffd\u8e2a\u3001\u4fdd\u62a4\u9690\u79c1\u7684\u57fa\u77f3\u3002\u901a\u8fc7\u5408\u7406\u914d\u7f6e\u548c\u7f16\u5199\uff0c\u5b83\u80fd\u8ba9\u4f60\u7684\u722c\u866b\u5728\u9762\u5bf9\u5404\u79cd\u53cd\u722c\u673a\u5236\u65f6\uff0c\u62e5\u6709\u66f4\u5f3a\u7684\u9002\u5e94\u6027\u548c\u9690\u853d\u6027\u3002\u800c\u50cf<strong>\u7a7f\u4e91\u4ee3\u7406IP<\/strong>\u8fd9\u6837\u63d0\u4f9b<strong>\u52a8\u6001\u4f4f\u5b85IP\u548c\u52a8\u6001\u673a\u623fIP\u6c60<\/strong>\uff0c\u5e76\u652f\u6301<strong>\u57ce\u5e02\u7ea7\u5b9a\u4f4d\u4e0e\u9ad8\u5e76\u53d1\u8bf7\u6c42<\/strong>\u7684\u9ad8\u8d28\u91cf\u4ee3\u7406\u670d\u52a1\u5546\uff0c\u66f4\u662f\u4e3a\u4f60\u7684\u722c\u866b\u63d0\u4f9b\u4e86\u6e90\u6e90\u4e0d\u65ad\u7684\u201c\u9ad8\u8d28\u91cf\u5f39\u836f\u201d\uff0c\u786e\u4fdd\u4f60\u7684\u6570\u636e\u91c7\u96c6\u4efb\u52a1\u80fd\u591f<strong>\u6c38\u4e0d\u8fc7\u671f\u3001\u7a33\u5b9a\u9ad8\u6548<\/strong>\u5730\u8fdb\u884c\u3002<\/p>\n\n\n\n<p>\u8bb0\u4f4f\uff0c\u722c\u866b\u4e0e\u53cd\u722c\u662f\u4e00\u573a\u6c38\u65e0\u6b62\u5883\u7684\u201c\u732b\u9f20\u6e38\u620f\u201d\u3002\u4f5c\u4e3a\u722c\u866b\u5de5\u7a0b\u5e08\uff0c\u6211\u4eec\u4e0d\u4ec5\u8981\u638c\u63e1\u5de5\u5177\u7684\u4f7f\u7528\uff0c\u66f4\u8981\u6df1\u5165\u7406\u89e3\u53cd\u722c\u673a\u5236\u7684\u539f\u7406\uff0c\u5e76\u5584\u4e8e\u5229\u7528\u5404\u79cd\u5148\u8fdb\u7684\u6280\u672f\u548c\u4f18\u8d28\u7684\u670d\u52a1\uff0c\u624d\u80fd\u5728\u8fd9\u573a\u201c\u6218\u5f79\u201d\u4e2d\u7acb\u4e8e\u4e0d\u8d25\u4e4b\u5730\u3002<\/p>\n\n\n\n<p>\u5e0c\u671b\u8fd9\u7bc7Scrapy Proxy Middleware\u8bbe\u7f6e\u5168\u653b\u7565\uff0c\u80fd\u4e3a\u4f60\u5e26\u6765\u5b9e\u5b9e\u5728\u5728\u7684\u5e2e\u52a9\uff01\u5982\u679c\u4f60\u5728\u6570\u636e\u91c7\u96c6\u7684\u9053\u8def\u4e0a\u9047\u5230\u4e86\u66f4\u591a\u6311\u6218\uff0c\u6216\u8005\u60f3\u8fdb\u4e00\u6b65\u4e86\u89e3\u7a7f\u4e91\u4ee3\u7406IP\u7684\u5f3a\u5927\u529f\u80fd\uff0c\u4e0d\u59a8\u53bb\u4ed6\u4eec\u7684\u5b98\u7f51\u4e86\u89e3\u4e00\u4e0b\uff0c\u6216\u8005\u76f4\u63a5\u8054\u7cfb\u4ed6\u4eec\u7684\u6280\u672f\u652f\u6301\uff0c\u76f8\u4fe1\u4f60\u4f1a\u627e\u5230\u6ee1\u610f\u7684\u89e3\u51b3\u65b9\u6848<\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5404\u4f4d\u722c\u866b\u7231\u597d\u8005\u4eec\uff0c\u6709\u6ca1\u6709\u5728\u6570\u636e\u91c7\u96c6\u7684\u8def\u4e0a\uff0c\u88ab\u5404\u79cd\u5404\u6837\u7684\u53cd\u722c\u673a\u5236\u201c\u6298\u78e8\u201d\u5f97\u7126\u5934\u70c2\u989d\uff1f\u5c24\u5176\u662f\u5f53\u4f60\u7684\u722c [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[58],"tags":[],"class_list":["post-8434","post","type-post","status-publish","format-standard","hentry","category-high-speed-socks5-node-purchase"],"_links":{"self":[{"href":"https:\/\/ip.cloudbypass.com\/proxy-information\/wp-json\/wp\/v2\/posts\/8434","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ip.cloudbypass.com\/proxy-information\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ip.cloudbypass.com\/proxy-information\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ip.cloudbypass.com\/proxy-information\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ip.cloudbypass.com\/proxy-information\/wp-json\/wp\/v2\/comments?post=8434"}],"version-history":[{"count":1,"href":"https:\/\/ip.cloudbypass.com\/proxy-information\/wp-json\/wp\/v2\/posts\/8434\/revisions"}],"predecessor-version":[{"id":8435,"href":"https:\/\/ip.cloudbypass.com\/proxy-information\/wp-json\/wp\/v2\/posts\/8434\/revisions\/8435"}],"wp:attachment":[{"href":"https:\/\/ip.cloudbypass.com\/proxy-information\/wp-json\/wp\/v2\/media?parent=8434"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ip.cloudbypass.com\/proxy-information\/wp-json\/wp\/v2\/categories?post=8434"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ip.cloudbypass.com\/proxy-information\/wp-json\/wp\/v2\/tags?post=8434"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}