{"id":96589,"date":"2020-04-20T15:09:06","date_gmt":"2020-04-20T07:09:06","guid":{"rendered":"http:\/\/4563.org\/?p=96589"},"modified":"2020-05-20T21:43:41","modified_gmt":"2020-05-20T13:43:41","slug":"%e8%bf%98%e5%9c%a8%e7%84%a6%e5%a4%b4%e7%83%82%e9%a2%9d%e8%a3%b8%e5%86%99-scrapy%ef%bc%9f%e8%bf%99%e4%b8%aa%e7%a5%9e%e5%99%a8%e8%ae%a9%e4%bd%a0-90-%e7%a7%92%e5%86%85%e9%85%8d%e5%a5%bd%e4%b8%80%e4%b8%aa","status":"publish","type":"post","link":"http:\/\/4563.org\/?p=96589","title":{"rendered":"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b"},"content":{"rendered":"<div>\n<div>\n<div>\n<h1>                  \u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b               <\/h1>\n<p> <\/p>\n<div>\n<div> <span>\u8cc7\u6df1\u5927\u4f6c : tikazyq <\/span>  <span><i><\/i> 47<\/span> <\/div>\n<div> <\/div>\n<\/p><\/div>\n<\/p><\/div>\n<\/p><\/div>\n<div isfirst=\"1\"> <\/p>\n<h2>\u80cc\u666f<\/h2>\n<p>\u722c\u866b\u662f\u4e00\u4ef6\u6709\u8da3\u7684\u4e8b\u60c5\uff0c\u8ba9\u4f60\u53ef\u4ee5\u901a\u8fc7\u722c\u866b\u7a0b\u5e8f\u81ea\u52a8\u5316\u7684\u5c06\u7f51\u4e0a\u7684\u4fe1\u606f\u6293\u53d6\u4e0b\u6765\uff0c\u514d\u53bb\u4e86\u5f88\u591a\u4eba\u5de5\u64cd\u4f5c\u3002\u5728\u4e00\u4e9b\u4f18\u8d28\u722c\u866b\u6846\u67b6\u51fa\u6765\u4e4b\u524d\uff0c\u5f00\u53d1\u8005\u4eec\u8fd8\u662f\u901a\u8fc7\u7b80\u5355\u7684\u7f51\u7edc\u8bf7\u6c42+\u7f51\u9875\u89e3\u6790\u5668\u7684\u65b9\u5f0f\u6765\u5f00\u53d1\u722c\u866b\u7a0b\u5e8f\uff0c\u4f8b\u5982 Python \u7684 requests + BeautifulSoup\uff0c\u9ad8\u7ea7\u4e00\u70b9\u7684\u722c\u866b\u7a0b\u5e8f\u8fd8\u4f1a\u52a0\u5165\u6570\u636e\u50a8\u5b58\u7684\u6a21\u5757\uff0c\u4f8b\u5982 MySQL\u3001MongoDB\u3002\u8fd9\u79cd\u65b9\u5f0f\u5f00\u53d1\u6548\u7387\u4f4e\uff0c\u7a33\u5b9a\u6027\u4e0d\u4f73\uff0c\u8981\u5f00\u53d1\u597d\u4e00\u4e2a\u5b8c\u5907\u7684\u3001\u751f\u4ea7\u53ef\u7528\u7684\u722c\u866b\u53ef\u80fd\u9700\u8981\u597d\u51e0\u4e2a\u5c0f\u65f6\u3002\u6211\u5c06\u8fd9\u79cd\u65b9\u5f0f\u79f0\u4f5c <strong>\u975e\u6846\u67b6\u722c\u866b<\/strong>\u3002<\/p>\n<p>2011 \u5e74\uff0c\u57fa\u4e8e Twisted \u7f16\u5199\u7684 Scrapy \u722c\u866b\u6846\u67b6\u6a2a\u7a7a\u51fa\u4e16\uff0c\u7a81\u7136\u88ab\u5927\u4f17\u719f\u77e5\uff0c\u6210\u4e3a\u4e86\u9996\u5c48\u4e00\u6307\u7684\u5168\u80fd\u7684\u9ad8\u6027\u80fd\u722c\u866b\u5f02\u6b65\u6846\u67b6\u3002Scrapy \u62bd\u8c61\u51fa\u4e86\u51e0\u4e2a\u6838\u5fc3\u6a21\u5757\uff0c\u8ba9\u5f00\u53d1\u8005\u5c06\u4e3b\u8981\u6ce8\u610f\u529b\u653e\u5728\u722c\u866b\u6293\u53d6\u903b\u8f91\u4e0a\uff0c\u800c\u4e0d\u7528\u7ba1\u6570\u636e\u4e0b\u8f7d\u3001\u9875\u9762\u89e3\u6790\u3001\u4efb\u52a1\u8c03\u5ea6\u7b49\u6bd4\u8f83\u7e41\u7410\u7684\u6a21\u5757\u3002\u5f00\u53d1\u597d\u4e00\u4e2a\u751f\u4ea7\u53ef\u7528\u7684 Scrapy \u722c\u866b\uff0c\u7b80\u5355\u7684\u53ef\u80fd\u53ea\u9700\u8981\u5341\u51e0\u5206\u949f\uff0c\u590d\u6742\u7684\u53ef\u80fd\u9700\u8981 1 \u5c0f\u65f6\u4ee5\u4e0a\u3002\u5f53\u7136\uff0c\u6211\u4eec\u8fd8\u6709\u5176\u4ed6\u5f88\u591a\u4f18\u79c0\u6846\u67b6\uff0c\u4f8b\u5982 PySpider\u3001Colly \u7b49\u3002\u6211\u5c06\u8fd9\u79cd\u722c\u866b\u79f0\u4f5c <strong>\u6846\u67b6\u722c\u866b<\/strong>\u3002\u6846\u67b6\u722c\u866b\u89e3\u653e\u4e86\u751f\u4ea7\u529b\uff0c\u73b0\u5728\u5f88\u591a\u4f01\u4e1a\u5c06\u6846\u67b6\u722c\u866b\u6539\u9020\u540e\u5e94\u7528\u5728\u751f\u4ea7\u73af\u5883\u4e2d\uff0c\u5927\u89c4\u6a21\u6293\u53d6\u6570\u636e\u3002<\/p>\n<p>\u7136\u800c\uff0c\u5bf9\u4e8e\u9700\u8981\u6293\u6210\u767e\u4e0a\u5343\u4e2a\u7f51\u7ad9\u7684\u722c\u866b\u9700\u6c42\u6765\u8bf4\uff0c\u6846\u67b6\u722c\u866b\u53ef\u80fd\u5c31\u6709\u4e9b\u5fc3\u6709\u4f59\u800c\u529b\u4e0d\u8db3\u4e86\uff0c\u7f16\u5199\u722c\u866b\u6210\u4e86\u4f53\u529b\u6d3b\u3002\u4f8b\u5982\uff0c\u5982\u679c\u5e73\u5747\u5f00\u53d1\u4e00\u4e2a\u6846\u67b6\u722c\u866b\u9700\u8981 20 \u5206\u949f\uff0c\u5982\u679c\u4e00\u4e2a\u5168\u804c\u722c\u866b\u5f00\u53d1\u5de5\u7a0b\u5e08\u6bcf\u5929\u5de5\u4f5c 8 \u4e2a\u5c0f\u65f6\uff0c\u90a3\u4e48\u5f00\u53d1 1000 \u4e2a\u7f51\u7ad9\u5c31\u9700\u8981 20000 \u5206\u949f\uff0c333 \u4e2a\u5c0f\u65f6\uff0c42 \u4e2a\u5de5\u4f5c\u65e5\uff0c\u8fd1 2 \u4e2a\u6708\u3002\u5f53\u7136\uff0c\u6211\u4eec\u53ef\u4ee5\u96c7\u4f63 10 \u4e2a\u5168\u804c\u722c\u866b\u5f00\u53d1\u5de5\u7a0b\u5e08\uff0c\u4f46\u8fd9\u540c\u6837\u9700\u8981 4 \u4e2a\u5de5\u4f5c\u65e5\u624d\u80fd\u5b8c\u6210\uff08\u5982\u4e0b\u56fe\uff09\u3002<\/p>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/20200520_5ec532ad84124.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<p>\u8fd9\u540c\u6837\u662f\u6bd4\u8f83\u4f4e\u6548\u7684\u3002\u4e3a\u4e86\u514b\u670d\u8fd9\u4e2a\u6548\u7387\u95ee\u9898\uff0c<strong>\u53ef\u914d\u7f6e\u722c\u866b<\/strong> \u5e94\u8fd0\u800c\u751f\u3002<\/p>\n<h2>\u53ef\u914d\u7f6e\u722c\u866b\u4ecb\u7ecd<\/h2>\n<p><strong>\u53ef\u914d\u7f6e\u722c\u866b\uff08 Configurable Spider \uff09<\/strong> \u6b63\u5982\u5176\u540d\u5b57\u8868\u793a\u7684\uff0c\u5c31\u662f\u53ef\u4ee5\u914d\u7f6e\u6293\u53d6\u89c4\u5219\u7684\u722c\u866b\u3002\u53ef\u914d\u7f6e\u722c\u866b\u662f\u4e00\u79cd\u9ad8\u5ea6\u62bd\u8c61\u7684\u722c\u866b\u7a0b\u5e8f\uff0c\u5f00\u53d1\u4eba\u5458\u4e0d\u7528\u7f16\u5199\u722c\u866b\u4ee3\u7801\uff0c\u53ea\u9700\u8981\u5c06\u9700\u8981\u6293\u53d6\u7f51\u9875\u5730\u5740\u3001\u5b57\u6bb5\u3001\u5c5e\u6027\u5199\u5728\u914d\u7f6e\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\uff0c\u8ba9\u7279\u6b8a\u7684\u722c\u866b\u7a0b\u5e8f\u6839\u636e\u914d\u7f6e\u53bb\u6293\u53d6\u6570\u636e\u3002\u53ef\u914d\u7f6e\u722c\u866b\u5c06\u722c\u866b\u4ee3\u7801\u8fdb\u4e00\u6b65\u62bd\u8c61\u6210\u4e86\u914d\u7f6e\u4fe1\u606f\uff0c\u7b80\u5316\u4e86\u722c\u866b\u5f00\u53d1\u7684\u6d41\u7a0b\u3002\u722c\u866b\u5f00\u53d1\u8005\u53ea\u9700\u8981\u505a\u76f8\u5e94\u7684\u914d\u7f6e\u5c31\u53ef\u4ee5\u5b8c\u6210\u722c\u866b\u7684\u5f00\u53d1\u3002\u56e0\u6b64\uff0c\u5f00\u53d1\u8005\u53ef\u4ee5\u901a\u8fc7\u53ef\u914d\u7f6e\u722c\u866b\uff0c\u5927\u89c4\u6a21\u7684\u7f16\u5199\u722c\u866b\u7a0b\u5e8f\uff08\u5982\u4e0b\u56fe\uff09\u3002<\/p>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/20200520_5ec532cecadf3.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<p>\u8fd9\u6837\u7684\u65b9\u5f0f\u8ba9\u6293\u53d6\u6210\u767e\u4e0a\u5343\u7684\u7f51\u7ad9\u6210\u4e86\u53ef\u80fd\uff0c\u4e00\u4e2a\u719f\u7ec3\u7684\u722c\u866b\u914d\u7f6e\u5458\u4e00\u5929\u53ef\u4ee5\u914d\u7f6e 1000 \u4e2a\u65b0\u95fb\u7f51\u7ad9\u7684\u722c\u866b\u3002\u8fd9\u5bf9\u4e8e\u6709\u8206\u60c5\u76d1\u63a7\u9700\u6c42\u7684\u4f01\u4e1a\u6765\u8bf4\u975e\u5e38\u91cd\u8981\uff0c\u56e0\u4e3a\u53ef\u914d\u7f6e\u722c\u866b\u63d0\u9ad8\u4e86\u751f\u4ea7\u529b\uff0c\u8ba9\u5355\u4f4d\u5de5\u4f5c\u65f6\u95f4\u6210\u672c\u964d\u4f4e\uff0c\u63d0\u5347\u4e86\u5f00\u53d1\u6548\u7387\uff0c\u65b9\u4fbf\u540e\u7eed\u7684\u8206\u60c5\u5206\u6790\u548c\u4eba\u5de5\u667a\u80fd\u4ea7\u54c1\u5f00\u53d1\u3002\u5f88\u591a\u4f01\u4e1a\u90fd\u662f\u81ea\u5df1\u7814\u53d1\u7684\u53ef\u914d\u7f6e\u722c\u866b\uff08\u53ef\u80fd\u53eb\u6cd5\u4f1a\u6709\u4e9b\u4e0d\u4e00\u6837\uff0c\u4f46\u5b9e\u8d28\u662f\u4e00\u4e2a\u4e1c\u897f\uff09\uff0c\u7136\u540e\u96c7\u4f63\u4e00\u4e9b\u722c\u866b\u914d\u7f6e\u5458\u4e13\u95e8\u8d1f\u8d23\u914d\u7f6e\u722c\u866b\u3002<\/p>\n<p>\u5e02\u9762\u4e0a\u514d\u8d39\u5f00\u6e90\u7684\u53ef\u914d\u7f6e\u722c\u866b\u6846\u67b6\u5e76\u4e0d\u591a\u3002\u6bd4\u8f83\u65e9\u7684\u6709\u5fae\u8f6f\u5927\u795e\u5d14\u5e86\u624d\u5f00\u53d1\u7684 Gerapy\uff0c\u5c5e\u4e8e\u4e00\u4e2a\u722c\u866b\u7ba1\u7406\u5e73\u53f0\uff0c\u80fd\u591f\u6839\u636e\u914d\u7f6e\u89c4\u5219\u751f\u6210 Scrapy \u9879\u76ee\u6587\u4ef6\u3002\u53e6\u4e00\u4e2a\u6bd4\u8f83\u65b0\u7684\u53ef\u914d\u7f6e\u722c\u866b\u6846\u67b6\u662f Crawlab\uff08\u5176\u5b9e Crawlab \u4e0d\u662f\u53ef\u914d\u7f6e\u722c\u866b\u6846\u67b6\uff0c\u800c\u662f\u4e00\u4e2a\u7075\u6d3b\u5ea6\u5f88\u9ad8\u7684\u722c\u866b\u7ba1\u7406\u5e73\u53f0\uff09\uff0c\u5728 v0.4.0 \u4e2d\u53d1\u5e03\u4e86\u53ef\u914d\u7f6e\u722c\u866b\u3002\u53e6\u5916\u8fd8\u6709\u4e00\u4e2a\u57fa\u4e8e Golang \u7684\u5f00\u6e90\u6846\u67b6 Ferret \uff0c\u5f88\u6709\u610f\u601d\uff0c\u7f16\u5199\u722c\u866b\u8ddf\u5199 SQL \u4e00\u6837\u7b80\u5355\u3002\u5176\u4ed6\u8fd8\u6709\u4e00\u4e9b\u5546\u4e1a\u4ea7\u54c1\uff0c\u4f46\u636e\u7528\u6237\u53cd\u9988\u540e\u90fd\u89c9\u5f97\u4e13\u4e1a\u5ea6\u4e0d\u9ad8\uff0c\u4e0d\u80fd\u6ee1\u8db3\u751f\u4ea7\u9700\u6c42\u3002<\/p>\n<p>\u53ef\u914d\u7f6e\u722c\u866b\u7684\u8bde\u751f\uff0c\u4e3b\u8981\u662f\u722c\u866b\u7684\u6a21\u5f0f\u6bd4\u8f83\u5355\u4e00\uff0c\u65e0\u975e\u5c31\u662f\u5217\u8868\u9875+\u8be6\u60c5\u9875\u7684\u7ec4\u5408\uff08\u5982\u4e0b\u56fe\uff09\uff0c\u6216\u8005\u4ec5\u4ec5\u5217\u8868\u9875\u3002\u5f53\u7136\u8fd8\u6709\u7a0d\u5fae\u590d\u6742\u4e00\u70b9\u7684\u901a\u7528\u722c\u866b\uff0c\u8fd9\u4e9b\u4e5f\u53ef\u4ee5\u901a\u8fc7\u89c4\u5219\u914d\u7f6e\u6765\u5b8c\u6210\u3002<\/p>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/20200520_5ec532eab9a0b.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<h2>Crawlab \u53ef\u914d\u7f6e\u722c\u866b<\/h2>\n<p>\u6211\u4eec\u4eca\u5929\u4e3b\u8981\u4ecb\u7ecd\u7684\u662f Crawlab \u7684\u53ef\u914d\u7f6e\u722c\u866b\u3002\u6211\u4eec\u4e4b\u524d\u5728 \u8fd9\u7bc7\u6587\u7ae0 \u4e2d\u6709\u6240\u4ecb\u7ecd\uff0c\u4f46\u5e76\u6ca1\u6709\u6df1\u5165\u8bb2\u89e3\u5982\u4f55\u5e94\u7528\u5230\u5b9e\u6218\u4e2d\u3002\u4eca\u5929\uff0c\u6211\u4eec\u7740\u91cd\u8bb2\u89e3\u4e00\u4e0b\u3002\u5982\u679c\u5bf9 Crawlabb \u7684\u53ef\u914d\u7f6e\u722c\u866b\u6bd4\u8f83\u964c\u751f\uff0c\u8bf7\u53c2\u8003\u53ef\u914d\u7f6e\u722c\u866b\u7684 \u6587\u6863\u3002<\/p>\n<h2>\u53ef\u914d\u7f6e\u722c\u866b\u5b9e\u6218<\/h2>\n<p>\u5b9e\u6218\u90e8\u5206\u7684\u6240\u6709\u6848\u4f8b\u662f\u4f5c\u8005\u7528 Crawlab \u7684 \u5b98\u65b9 Demo \u5e73\u53f0 \u901a\u8fc7\u53ef\u914d\u7f6e\u722c\u866b\u529f\u80fd\u7f16\u5199\u5e76\u5b8c\u6210\u6293\u53d6\u7684\uff0c\u6db5\u76d6\u4e86\u65b0\u95fb\u3001\u91d1\u878d\u3001\u6c7d\u8f66\u3001\u4e66\u7c4d\u3001\u89c6\u9891\u3001\u641c\u7d22\u5f15\u64ce\u3001\u7a0b\u5e8f\u5458\u793e\u533a\u7b49\u9886\u57df\uff08\u89c1\u4e0b\u56fe\uff09\u3002\u4e0b\u9762\u5c06\u4ecb\u7ecd\u5176\u4e2d\u7684\u51e0\u4e2a\uff0c\u6240\u6709\u4f8b\u5b50\u5747\u5728 \u5b98\u65b9 Demo \u5e73\u53f0 \u4e0a\uff0c\u5747\u53ef\u4ee5\u6ce8\u518c\u8d26\u53f7\u767b\u5f55\u67e5\u770b\u3002<\/p>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/20200520_5ec5330413b34.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<h3>\u767e\u5ea6\uff08\u641c\u7d22 &#8220;Crawlab&#8221;\uff09<\/h3>\n<p><strong>\u722c\u866b\u5730\u5740<\/strong>\uff1a http:\/\/crawlab.cn\/demo#\/spiders\/5e27d055b8f9c90019f42a83<\/p>\n<h4>\u722c\u866b\u914d\u7f6e<\/h4>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/16fcc722f774b8few2892amph822ampfpngamps175478.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<h4>Spiderfile<\/h4>\n<pre><code>version: 0.4.4 engine: scrapy start_url: http:\/\/www.baidu.com\/s?wd=crawlab start_stage: list stages: - name: list   is_list: true   list_css: \"\"   list_xpath: \/\/*[contains(@class, \"c-container\")]   page_css: \"\"   page_xpath: \/\/*[@id=\"page\"]\/\/a[@class=\"n\"][last()]   page_attr: href   fields:   - name: title     css: \"\"     xpath: .\/\/h3\/a     attr: \"\"     next_stage: \"\"     remark: \"\"   - name: url     css: \"\"     xpath: .\/\/h3\/a     attr: href     next_stage: \"\"     remark: \"\"   - name: abstract     css: \"\"     xpath: .\/\/*[@class=\"c-abstract\"]     attr: \"\"     next_stage: \"\"     remark: \"\" settings:   ROBOTSTXT_OBEY: \"false\"   USER_AGENT: Mozilla\/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit\/537.36 (KHTML,     like Gecko) Chrome\/78.0.3904.108 Safari\/537.36 <\/code><\/pre>\n<h4>\u6293\u53d6\u7ed3\u679c<\/h4>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/20200520_5ec53330409c5.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<h3>SegmentFault \uff08\u6700\u65b0\u6587\u7ae0\uff09<\/h3>\n<p><strong>\u722c\u866b\u5730\u5740<\/strong>\uff1a http:\/\/crawlab.cn\/demo#\/spiders\/5e27d116b8f9c90019f42a87<\/p>\n<h4>\u722c\u866b\u914d\u7f6e<\/h4>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/20200520_5ec5334520905.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<h4>Spiderfile<\/h4>\n<pre><code>version: 0.4.4 engine: scrapy start_url: https:\/\/segmentfault.com\/newest start_stage: list stages: - name: list   is_list: true   list_css: .news-list &gt; .news-item   list_xpath: \"\"   page_css: \"\"   page_xpath: \"\"   page_attr: \"\"   fields:   - name: title     css: h4.news__item-title     xpath: \"\"     attr: \"\"     next_stage: \"\"     remark: \"\"   - name: url     css: .news-img     xpath: \"\"     attr: href     next_stage: \"\"     remark: \"\"   - name: abstract     css: .article-excerpt     xpath: \"\"     attr: \"\"     next_stage: \"\"     remark: \"\" settings:   ROBOTSTXT_OBEY: \"false\"   USER_AGENT: Mozilla\/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit\/537.36 (KHTML,     like Gecko) Chrome\/78.0.3904.108 Safari\/537.36 <\/code><\/pre>\n<h4>\u6293\u53d6\u7ed3\u679c<\/h4>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/20200520_5ec533561fb31.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<h3>\u4e9a\u9a6c\u900a\u4e2d\u56fd\uff08\u641c\u7d22&#8221;\u624b\u673a&#8221;\uff09<\/h3>\n<p><strong>\u722c\u866b\u5730\u5740<\/strong>\uff1a http:\/\/crawlab.cn\/demo#\/spiders\/5e27e157b8f9c90019f42afb<\/p>\n<h4>\u722c\u866b\u914d\u7f6e<\/h4>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/20200520_5ec533745f621.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<h4>Spiderfile<\/h4>\n<pre><code>version: 0.4.4 engine: scrapy start_url: https:\/\/www.amazon.cn\/s?k=%E6%89%8B%E6%9C%BA&amp;__mk_zh_CN=%E4%BA%9A%E9%A9%AC%E9%80%8A%E7%BD%91%E7%AB%99&amp;ref=nb_sb_noss_2 start_stage: list stages: - name: list   is_list: true   list_css: .s-result-item   list_xpath: \"\"   page_css: .a-last &gt; a   page_xpath: \"\"   page_attr: href   fields:   - name: title     css: span.a-text-normal     xpath: \"\"     attr: \"\"     next_stage: \"\"     remark: \"\"   - name: url     css: .a-link-normal     xpath: \"\"     attr: href     next_stage: \"\"     remark: \"\"   - name: price     css: \"\"     xpath: .\/\/*[@class=\"a-price-whole\"]     attr: \"\"     next_stage: \"\"     remark: \"\"   - name: price_fraction     css: \"\"     xpath: .\/\/*[@class=\"a-price-fraction\"]     attr: \"\"     next_stage: \"\"     remark: \"\"   - name: img     css: .s-image-square-aspect &gt; img     xpath: \"\"     attr: src     next_stage: \"\"     remark: \"\" settings:   ROBOTSTXT_OBEY: \"false\"   USER_AGENT: Mozilla\/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit\/537.36 (KHTML,     like Gecko) Chrome\/78.0.3904.108 Safari\/537.36 <\/code><\/pre>\n<h4>\u6293\u53d6\u7ed3\u679c<\/h4>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/16fcc7944add3028w2904amph1262ampfpngamps504113.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<h3>V2ex<\/h3>\n<p><strong>\u722c\u866b\u5730\u5740<\/strong>\uff1a http:\/\/crawlab.cn\/demo#\/spiders\/5e27dd67b8f9c90019f42ad9<\/p>\n<h4>\u722c\u866b\u914d\u7f6e<\/h4>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/16fcc7b33ca04269w2892amph1112ampfpngamps233714.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<h4>Spiderfile<\/h4>\n<pre><code>version: 0.4.4 engine: scrapy start_url: https:\/\/v2ex.com\/ start_stage: list stages: - name: list   is_list: true   list_css: .cell.item   list_xpath: \"\"   page_css: \"\"   page_xpath: \"\"   page_attr: href   fields:   - name: title     css: a.topic-link     xpath: \"\"     attr: \"\"     next_stage: \"\"     remark: \"\"   - name: url     css: a.topic-link     xpath: \"\"     attr: href     next_stage: detail     remark: \"\"   - name: replies     css: .count_livid     xpath: \"\"     attr: \"\"     next_stage: \"\"     remark: \"\" - name: detail   is_list: false   list_css: \"\"   list_xpath: \"\"   page_css: \"\"   page_xpath: \"\"   page_attr: \"\"   fields:   - name: content     css: \"\"     xpath: .\/\/*[@class=\"markdown_body\"]     attr: \"\"     next_stage: \"\"     remark: \"\" settings:   AUTOTHROTTLE_ENABLED: \"true\"   ROBOTSTXT_OBEY: \"false\"   USER_AGENT: Mozilla\/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit\/537.36 (KHTML,     like Gecko) Chrome\/79.0.3945.117 Safari\/537.36 <\/code><\/pre>\n<h4>\u6293\u53d6\u7ed3\u679c<\/h4>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/16fcc7be24a4cbaew2912amph1366ampfpngamps501214.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<h3>36 \u6c2a<\/h3>\n<p><strong>\u722c\u866b\u5730\u5740<\/strong>\uff1a http:\/\/crawlab.cn\/demo#\/spiders\/5e27ec82b8f9c90019f42b59<\/p>\n<h4>\u722c\u866b\u914d\u7f6e<\/h4>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/20200520_5ec533c073faa.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<h4>Spiderfile<\/h4>\n<pre><code>version: 0.4.4 engine: scrapy start_url: https:\/\/36kr.com\/information\/web_news start_stage: list stages: - name: list   is_list: true   list_css: .kr-flow-article-item   list_xpath: \"\"   page_css: \"\"   page_xpath: \"\"   page_attr: \"\"   fields:   - name: title     css: .article-item-title     xpath: \"\"     attr: \"\"     next_stage: \"\"     remark: \"\"   - name: url     css: body     xpath: \"\"     attr: href     next_stage: detail     remark: \"\"   - name: abstract     css: body     xpath: \"\"     attr: \"\"     next_stage: \"\"     remark: \"\"   - name: author     css: .kr-flow-bar-author     xpath: \"\"     attr: \"\"     next_stage: \"\"     remark: \"\"   - name: time     css: .kr-flow-bar-time     xpath: \"\"     attr: \"\"     next_stage: \"\"     remark: \"\" - name: detail   is_list: false   list_css: \"\"   list_xpath: \"\"   page_css: \"\"   page_xpath: \"\"   page_attr: \"\"   fields:   - name: content     css: \"\"     xpath: .\/\/*[@class=\"common-width content articleDetailContent kr-rich-text-wrapper\"]     attr: \"\"     next_stage: \"\"     remark: \"\" settings:   ROBOTSTXT_OBEY: \"false\"   USER_AGENT: Mozilla\/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit\/537.36 (KHTML,     like Gecko) Chrome\/78.0.3904.108 Safari\/537.36 <\/code><\/pre>\n<h4>\u6293\u53d6\u7ed3\u679c<\/h4>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/20200520_5ec533d5f1f8f.png\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<h3>\u5b9e\u6218\u722c\u866b\u4e00\u89c8<\/h3>\n<p>\u722c\u866b\u540d\u79f0 | \u722c\u866b\u7c7b\u522b &#8212; | &#8212; \u767e\u5ea6 | \u5217\u8868\u9875+\u5206\u9875 SegmentFault | \u5217\u8868\u9875 CSDN | \u5217\u8868\u9875+\u5206\u9875+\u8be6\u60c5\u9875 V2ex | \u5217\u8868\u9875+\u8be6\u60c5\u9875 \u7eb5\u6a2a | \u5217\u8868\u9875 \u4e9a\u9a6c\u900a\u4e2d\u56fd | \u5217\u8868\u9875+\u5206\u9875 \u96ea\u7403\u7f51 | \u5217\u8868\u9875+\u8be6\u60c5\u9875 \u6c7d\u8f66\u4e4b\u5bb6 | \u5217\u8868\u9875+\u5206\u9875 \u8c46\u74e3\u8bfb\u4e66 | \u5217\u8868\u9875 36 \u6c2a | \u5217\u8868\u9875+\u8be6\u60c5\u9875 \u817e\u8baf\u89c6\u9891 | \u5217\u8868\u9875<\/p>\n<h2>\u603b\u7ed3<\/h2>\n<p>Crawlab \u7684\u53ef\u914d\u7f6e\u722c\u866b\u975e\u5e38\u65b9\u4fbf\uff0c\u8ba9\u7a0b\u5e8f\u5458\u53ef\u4ee5\u5feb\u901f\u914d\u7f6e\u51fa\u81ea\u5df1\u9700\u8981\u7684\u722c\u866b\u3002\u914d\u7f6e\u4e0a\u8ff0 11 \u4e2a\u722c\u866b\u603b\u5171\u82b1\u8d39\u4e86\u4f5c\u8005\u4e0d\u5230 40 \u5206\u949f\u7684\u65f6\u95f4\uff08\u8003\u8651\u5230\u6709\u53cd\u722c\u8c03\u8bd5\u5728\u91cc\u9762\uff09\uff0c\u5176\u4e2d\u51e0\u4e2a\u6bd4\u8f83\u7b80\u5355\u7684\u722c\u866b\u5728 1-2 \u5206\u949f\u4e0d\u5230\u5c31\u914d\u7f6e\u5b8c\u6210\u4e86\u3002\u800c\u4e14\u4f5c\u8005\u4e00\u884c\u4ee3\u7801\u4e5f\u6ca1\u6709\u5199\uff0c\u6240\u6709\u914d\u7f6e\u5747\u5728\u754c\u9762\u4e0a\u5b8c\u6210\u3002\u800c\u4e14\uff0cCrawlab \u53ef\u914d\u7f6e\u722c\u866b\u4e0d\u4ec5\u652f\u6301\u5728\u754c\u9762\u4e0a\u7684\u914d\u7f6e\uff0c\u540c\u65f6\u8fd8\u652f\u6301\u7f16\u5199\u4e00\u4e2a Yaml \u6587\u4ef6 Spiderfile \u6765\u5b8c\u6210\u914d\u7f6e\uff08\u5176\u5b9e\uff0c\u6240\u6709\u7684\u914d\u7f6e\u5747\u53ef\u4ee5\u6620\u5c04\u5230 Spiderfile \u4e2d\uff09\u3002Crawlab \u53ef\u914d\u7f6e\u722c\u866b\u662f\u57fa\u4e8e Scrapy \u7684\uff0c\u56e0\u6b64\u652f\u6301 Scrapy \u7edd\u5927\u591a\u6570\u7279\u6027\uff0c\u53ef\u4ee5\u901a\u8fc7 <strong>\u8bbe\u7f6e<\/strong> \u6765\u914d\u7f6e\u53ef\u914d\u7f6e\u722c\u866b\u7684\u6269\u5c55\u5c5e\u6027\uff0c\u5305\u62ec <code>USER_AGENT<\/code>\u3001<code>ROBOTSTXT_OBEY<\/code> \u7b49\u7b49\u3002\u4e3a\u4ec0\u4e48\u8981\u7528 Crawlab \u4f5c\u4e3a\u53ef\u914d\u7f6e\u722c\u866b\u7684\u9996\u9009\u5462\uff1f\u56e0\u4e3a Crawlab \u53ef\u914d\u7f6e\u722c\u866b\u4e0d\u4ec5\u80fd\u591f\u914d\u7f6e\u722c\u866b\uff0c\u8fd8\u80fd\u4eab\u53d7 Crawlab \u722c\u866b\u7ba1\u7406\u5e73\u53f0\u7684\u6838\u5fc3\u529f\u80fd\uff0c\u5305\u62ec\u4efb\u52a1\u8c03\u5ea6\u3001\u4efb\u52a1\u76d1\u63a7\u3001\u5b9a\u65f6\u4efb\u52a1\u3001\u65e5\u5fd7\u7ba1\u7406\u3001\u6d88\u606f\u901a\u77e5\u7b49\u5b9e\u7528\u529f\u80fd\u3002\u800c\u5728\u540e\u7eed\u5f00\u53d1\u4e2d\uff0cCrawlab \u5f00\u53d1\u7ec4\u8fd8\u5c06\u4e0d\u65ad\u5b8c\u5584\u53ef\u914d\u7f6e\u722c\u866b\uff0c\u8ba9\u5176\u652f\u6301\u66f4\u591a\u7684\u529f\u80fd\uff0c\u5305\u62ec\u52a8\u6001\u5185\u5bb9\u3001\u66f4\u591a\u7684\u5f15\u64ce\u3001CrawlSpider \u7684\u5b9e\u73b0\u7b49\u7b49\u3002<\/p>\n<p>\u8981\u6ce8\u610f\u7684\u662f\uff0c\u4e0d\u9075\u5b88 robots.txt \u53ef\u80fd\u4f1a\u9020\u6210\u6cd5\u5f8b\u98ce\u9669\uff0c\u672c\u6587\u7684\u5b9e\u6218\u722c\u866b\u5747\u4e3a\u5b66\u4e60\u4ea4\u6d41\u7528\uff0c\u5207\u52ff\u4f5c\u4e3a\u751f\u4ea7\u73af\u5883\uff0c\u4efb\u4f55\u6ee5\u7528\u8005\u81ea\u884c\u627f\u62c5\u6cd5\u5f8b\u8d23\u4efb\u3002<\/p>\n<h2>\u53c2\u8003<\/h2>\n<ul>\n<li>Github: https:\/\/github.com\/crawlab-team\/crawlab<\/li>\n<li>Demo: http:\/\/crawlab.cn\/demo<\/li>\n<li>\u6587\u6863: http:\/\/docs.crawlab.cn\/<\/li>\n<\/ul>\n<p>\u5982\u679c\u60a8\u89c9\u5f97 Crawlab \u5bf9\u60a8\u7684\u65e5\u5e38\u5f00\u53d1\u6216\u516c\u53f8\u6709\u5e2e\u52a9\uff0c\u8bf7\u52a0\u4f5c\u8005\u5fae\u4fe1 tikazyq1 \u5e76\u6ce8\u660e &#8220;Crawlab&#8221;\uff0c\u4f5c\u8005\u4f1a\u5c06\u4f60\u62c9\u5165\u7fa4\u3002\u6b22\u8fce\u5728 Github \u4e0a\u8fdb\u884c star\uff0c\u4ee5\u53ca\uff0c\u5982\u679c\u9047\u5230\u4efb\u4f55\u95ee\u9898\uff0c\u8bf7\u968f\u65f6\u5728 Github \u4e0a\u63d0 issue\u3002\u53e6\u5916\uff0c\u6b22\u8fce\u60a8\u5bf9 Crawlab \u505a\u5f00\u53d1\u8d21\u732e\u3002<\/p>\n<p><img decoding=\"async\" src=\"http:\/\/4563.org\/wp-content\/uploads\/2020\/05\/20200520_5ec533f7cfc05.webp\" alt=\"\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9\u4e2a\u795e\u5668\u8ba9\u4f60 90 \u79d2\u5185\u914d\u597d\u4e00\u4e2a\u722c\u866b\" \/><\/p>\n<\/p><\/div>\n<div> <b>\u5927\u4f6c\u6709\u8a71\u8aaa<\/b> (<span>18<\/span>)        <\/div>\n<div> <\/div>\n<\/p><\/div>\n<\/p><\/div>\n<ul>\n<li data-pid=\"876270\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u8cc7\u6df1\u5927\u4f6c : AX5N <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             \u8fd9\u79cd\u914d\u7f6e\u6587\u4ef6\u5f0f\u7684\u722c\u866b\u8868\u8fbe\u80fd\u529b\u592a\u5f31\uff0c\u78b0\u5230\u590d\u6742\u70b9\u7684\u7f51\u7ad9\u5c31\u641e\u4e0d\u5b9a\u4e86\u3002                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876271\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u4e3b<\/span> <span>\u8cc7\u6df1\u5927\u4f6c : tikazyq <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             @AX5N \u8fd9\u662f\u56e0\u4e3a\u53ef\u914d\u7f6e\u722c\u866b\u8fd8\u4e0d\u591f\u7075\u6d3b\uff0c\u73b0\u5728\u6709\u4e9b\u5c40\u9650\u6027\uff0c\u4e0d\u8fc7\u540e\u9762\u4f1a\u4e0d\u65ad\u53d1\u5c55\uff0c\u9700\u6c42\u8fd8\u662f\u6709\u7684\u3002\u5bf9\u4e8e\u590d\u6742\u722c\u866b\uff0c\u53ef\u4ee5\u91c7\u7528 crawlab \u7684\u81ea\u5b9a\u4e49\u722c\u866b                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876272\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u8cc7\u6df1\u5927\u4f6c : optional <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             \u8fd9\u79cd\u722c\u866b\uff0c\u706b\u8f66\u5934\u90fd\u53ef\u4ee5\u76f4\u63a5\u7528                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876273\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u8cc7\u6df1\u5927\u4f6c : locoz <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             @AX5N #1 <br \/>@optional #3 <br \/>\u8fd9\u4e1c\u897f\u7684\u53ef\u914d\u7f6e\u722c\u866b\u53ea\u662f\u987a\u5e26\u7684\u529f\u80fd\uff0c\u6838\u5fc3\u5176\u5b9e\u662f\u4f5c\u4e3a\u7ba1\u7406\u5e73\u53f0\u6765\u4f7f\u7528\u3002                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876274\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u8cc7\u6df1\u5927\u4f6c : huruwo <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             \u50cf\u6296\u97f3 \u5c0f\u7ea2\u4e66\u8fd9\u79cd\u8f6f\u4ef6\u7684\u6570\u636e\u80fd\u722c\u53d6\u5417                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876275\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u8cc7\u6df1\u5927\u4f6c : Canthony <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             \u5f31\u5f31\u95ee\u4e00\u53e5\uff0c\u56fe\u5462\uff1f                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876276\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u8cc7\u6df1\u5927\u4f6c : JaneWang <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             \u4e2a\u4eba\u89c9\u5f97\u722c\u866b\u7ba1\u7406\u9700\u6c42\u4e0d\u5927\u3002\u53cd\u800c\u662f\u767b\u5f55\uff0c\u9a8c\u8bc1\u7801\uff0c\u53cd\u722c\u7b49\u7279\u6027\u9700\u6c42\u66f4\u5927\u3002                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876277\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u4e3b<\/span> <span>\u8cc7\u6df1\u5927\u4f6c : tikazyq <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             @optional \u706b\u8f66\u5934\u662f\u7ed9\u5c0f\u767d\u7528\u7684\uff0ccrawlab \u662f\u7ed9\u4e13\u4e1a\u4eba\u58eb\u7528\u7684                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876278\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u4e3b<\/span> <span>\u8cc7\u6df1\u5927\u4f6c : tikazyq <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             @locoz \u5927\u4f6c\u61c2\u6211                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876279\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u4e3b<\/span> <span>\u8cc7\u6df1\u5927\u4f6c : tikazyq <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             @huruwo \u5bf9\u4e8e\u590d\u6742\u7684\u53cd\u722c\u63aa\u65bd\uff0c\u53ef\u914d\u7f6e\u722c\u866b\u6682\u65f6\u4e0d\u80fd\u7ed5\u8fc7\uff0c\u4f46\u540e\u7eed\u53ef\u80fd\u4f1a\u5f00\u53d1\u66f4\u590d\u6742\u7684\u53ef\u914d\u7f6e\u722c\u866b                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876280\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u4e3b<\/span> <span>\u8cc7\u6df1\u5927\u4f6c : tikazyq <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             @Canthony \u539f\u6587\u89c1\u6b64\u94fe\u63a5\uff1a https:\/\/juejin.im\/entry\/5e2817d3f265da3e4244e9c1                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876281\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u4e3b<\/span> <span>\u8cc7\u6df1\u5927\u4f6c : tikazyq <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             @JaneWang \u53cd\u722c\u7279\u6027\u7684\u722c\u866b\u53ef\u4ee5\u7528\u81ea\u5b9a\u4e49\u722c\u866b\uff0c\u4f46\u722c\u866b\u7ba1\u7406\u662f\u4e00\u4e2a\u6bd4\u8f83\u91cd\u8981\u7684\u529f\u80fd\uff0c\u9664\u975e\u4f60\u7684\u722c\u866b\u6839\u672c\u4e0d\u6210\u89c4\u6a21\uff0c\u6216\u8005\u5904\u4e8e demo \u9636\u6bb5\u2026 \u8be6\u60c5\u53ef\u4ee5\u770b\u6211\u6398\u91d1\u4e0a\u5173\u4e8e\u722c\u866b\u7ba1\u7406\u5e73\u53f0\u7684\u6587\u7ae0                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876282\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u8cc7\u6df1\u5927\u4f6c : huruwo <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             @tikazyq \u6211\u7684\u9700\u6c42\u53ef\u80fd\u662f\u9488\u5bf9\u4e8e\u624b\u673a\u4e0a\u7684\u6570\u636e\u722c\u53d6\u3002\u7c7b\u4f3c\u51e0\u4e07\u4e2a\u6296\u97f3\u8d26\u53f7\u9700\u8981\u5feb\u901f\u67e5\u51fa\u6bcf\u4e2a\u8d26\u53f7\u7684\u4fe1\u606f \u4f5c\u54c1 \u559c\u6b22\u5217\u8868\u3002\u8be5\u6846\u67b6\u662f\u53ea\u9488\u5bf9\u7f51\u9875\u722c\u866b\u8fd8\u662f\u901a\u7528\u4e8e\u624b\u673a\u722c\u866b                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876283\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u4e3b<\/span> <span>\u8cc7\u6df1\u5927\u4f6c : tikazyq <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             @huruwo crawlab \u9488\u5bf9\u722c\u866b\u7ba1\u7406\uff0c\u53ef\u914d\u7f6e\u722c\u866b\u6682\u65f6\u4ec5\u9650\u4e8e web\uff0c\u624b\u673a app \u722c\u866b\u8fd8\u9700\u8981\u7528\u81ea\u5b9a\u4e49\u722c\u866b\u5f00\u53d1                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876284\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u8cc7\u6df1\u5927\u4f6c : winglight2016 <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             \u5efa\u8bae lz \u6253\u5305\u4e2a docker \u7248\uff0cdocker-compose \u914d\u7f6e\uff0c\u65b9\u4fbf\u4f7f\u7528\u5916\u90e8 mongodb \u548c redis\u3002                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876285\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u4e3b<\/span> <span>\u8cc7\u6df1\u5927\u4f6c : tikazyq <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             @winglight2016 \u5df2\u7ecf\u505a\u4e86\uff0c\u8bf7\u53c2\u7167 github\uff0cdocker-compose \u662f\u63a8\u8350\u90e8\u7f72\u65b9\u5f0f                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876286\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u8cc7\u6df1\u5927\u4f6c : Harlaus <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             \u722c\u866b\u5e73\u53f0\u80fd\u4e0d\u80fd\u4e0d\u8981\u5c40\u9650\u5728 scrapy \u91cc                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li data-pid=\"876287\" data-uid=\"2\">\n<div>\n<div>\n<div> <span>\u4e3b<\/span> <span>\u8cc7\u6df1\u5927\u4f6c : tikazyq <\/span>  <\/div>\n<div> <i title=\"\u5f15\u7528\"><\/i>  <span>          <\/span> <\/div>\n<\/p><\/div>\n<div>                                                             @Harlaus crawlab \u53ef\u4ee5\u8fd0\u884c\u4efb\u4f55\u8bed\u8a00\uff0c\u4efb\u4f55\u6846\u67b6\uff0c\u4e0d\u5c40\u9650\u4e8e scrapy \u54e6                                                            <\/div>\n<\/p><\/div>\n<\/li>\n<li>\n","protected":false},"excerpt":{"rendered":"<p>\u8fd8\u5728\u7126\u5934\u70c2\u989d\u88f8\u5199 Scrapy\uff1f\u8fd9&hellip;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[],"tags":[],"_links":{"self":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/96589"}],"collection":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=96589"}],"version-history":[{"count":1,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/96589\/revisions"}],"predecessor-version":[{"id":96594,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/96589\/revisions\/96594"}],"wp:attachment":[{"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=96589"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=96589"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=96589"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}