{"id":77,"date":"2024-03-09T06:35:25","date_gmt":"2023-11-10T13:21:46","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/index.php\/2023\/11\/30\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/"},"modified":"2025-07-31T22:30:33","modified_gmt":"2025-07-31T14:30:33","slug":"%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/","title":{"rendered":"Scrapy\u4e0ePython 3\u7f51\u9875\u6293\u53d6\u5b9e\u6218\uff1a\u4ece\u5165\u95e8\u5230\u7cbe\u901a"},"content":{"rendered":"<h3>\u5f15\u8a00<\/h3>\n<p>\u7f51\u9875\u6293\u53d6\uff0c\u901a\u5e38\u88ab\u79f0\u4e3a\u7f51\u7edc\u722c\u866b\u6216\u7f51\u7edc\u8718\u86db\uff0c\u662f\u6307\u4ee5\u7a0b\u5e8f\u5316\u65b9\u5f0f\u6d4f\u89c8\u4e00\u7cfb\u5217\u7f51\u9875\u5e76\u4ece\u4e2d\u63d0\u53d6\u6570\u636e\u7684\u884c\u4e3a\u3002\u5b83\u662f\u5904\u7406\u7f51\u7edc\u6570\u636e\u7684\u5f3a\u5927\u5de5\u5177\u3002<\/p>\n<p>\u4f7f\u7528\u7f51\u7edc\u722c\u866b\uff0c\u4f60\u53ef\u4ee5\u63d0\u53d6\u5173\u4e8e\u4e00\u7cfb\u5217\u4ea7\u54c1\u7684\u6570\u636e\u3001\u83b7\u53d6\u5927\u91cf\u6587\u672c\u6216\u6570\u503c\u6570\u636e\u8fdb\u884c\u5904\u7406\u3001\u4ece\u6ca1\u6709\u5b98\u65b9API\u7684\u7f51\u7ad9\u68c0\u7d22\u6570\u636e\uff0c\u6216\u8005\u4ec5\u4ec5\u6ee1\u8db3\u4e2a\u4eba\u7684\u597d\u5947\u5fc3\u3002<\/p>\n<p>\u5728\u672c\u6559\u7a0b\u4e2d\uff0c\u60a8\u5c06\u4e86\u89e3\u7f51\u9875\u6293\u53d6\u548c\u722c\u866b\u8fc7\u7a0b\u7684\u57fa\u672c\u77e5\u8bc6\uff0c\u540c\u65f6\u63a2\u7d22\u4e00\u4e2a\u6709\u8da3\u7684\u6570\u636e\u96c6\u3002\u6211\u4eec\u5c06\u4f7f\u7528\u201cQuotes to Scrape\u201d\uff0c\u8fd9\u662f\u4e00\u4e2a\u6258\u7ba1\u5728\u4e13\u95e8\u7528\u4e8e\u6d4b\u8bd5\u7f51\u7edc\u722c\u866b\u7684\u7f51\u7ad9\u4e0a\u7684\u5f15\u8bed\u6570\u636e\u5e93\u3002\u901a\u8fc7\u672c\u6559\u7a0b\u7684\u5b66\u4e60\uff0c\u60a8\u5c06\u5f97\u5230\u4e00\u4e2a\u529f\u80fd\u5b8c\u5907\u7684Python\u7f51\u7edc\u722c\u866b\uff0c\u5b83\u80fd\u591f\u6d4f\u89c8\u5305\u542b\u5f15\u8bed\u7684\u4e00\u7cfb\u5217\u9875\u9762\uff0c\u5e76\u5728\u60a8\u7684\u5c4f\u5e55\u4e0a\u663e\u793a\u5b83\u4eec\u3002<\/p>\n<p>\u8fd9\u4e2a\u7f51\u7edc\u722c\u866b\u5c06\u5f88\u5bb9\u6613\u8fdb\u884c\u6269\u5c55\uff0c\u4f60\u53ef\u4ee5\u968f\u5fc3\u6240\u6b32\u5730\u4fee\u6539\u5b83\uff0c\u5e76\u5c06\u5176\u4f5c\u4e3a\u4ece\u7f51\u7edc\u4e0a\u6293\u53d6\u6570\u636e\u7684\u57fa\u7840\uff0c\u7528\u4e8e\u4f60\u81ea\u5df1\u7684\u9879\u76ee\u3002<\/p>\n<h2>\u5148\u51b3\u6761\u4ef6<\/h2>\n<p>\u5b8c\u6210\u672c\u6559\u7a0b\uff0c\u4f60\u9700\u8981\u4e00\u4e2a\u9002\u7528\u4e8ePython 3\u7684\u672c\u5730\u5f00\u53d1\u73af\u5883\u3002\u4f60\u53ef\u4ee5\u6309\u7167\u300a\u5982\u4f55\u5b89\u88c5\u548c\u914d\u7f6ePython 3\u7684\u672c\u5730\u7f16\u7a0b\u73af\u5883\u300b\u7684\u6307\u5357\u6765\u914d\u7f6e\u6240\u9700\u7684\u4e00\u5207\u3002<\/p>\n<h2>\u7b2c\u4e00\u6b65 &#8211; \u521b\u5efa\u57fa\u672c\u7684\u7f51\u7edc\u722c\u866b<\/h2>\n<p>\u6293\u53d6\u6570\u636e\u662f\u4e00\u4e2a\u4e24\u6b65\u8fc7\u7a0b\uff1a<\/p>\n<ol>\n<li>\u7cfb\u7edf\u5730\u67e5\u627e\u548c\u4e0b\u8f7d\u7f51\u9875\u3002<\/li>\n<li>\u4ece\u4e0b\u8f7d\u7684\u7f51\u9875\u4e2d\u63d0\u53d6\u4fe1\u606f\u3002<\/li>\n<\/ol>\n<p>\u8fd9\u4e24\u4e2a\u6b65\u9aa4\u53ef\u4ee5\u7528\u591a\u79cd\u8bed\u8a00\u7684\u591a\u79cd\u65b9\u5f0f\u6765\u5b9e\u73b0\u3002<\/p>\n<p>\u60a8\u53ef\u4ee5\u4f7f\u7528\u7f16\u7a0b\u8bed\u8a00\u63d0\u4f9b\u7684\u6a21\u5757\u6216\u5e93\u4ece\u5934\u5f00\u59cb\u6784\u5efa\u4e00\u4e2a\u722c\u866b\uff0c\u4f46\u968f\u7740\u722c\u866b\u53d8\u5f97\u66f4\u52a0\u590d\u6742\uff0c\u60a8\u53ef\u80fd\u9700\u8981\u5904\u7406\u4e00\u4e9b\u6f5c\u5728\u7684\u9ebb\u70e6\u3002\u4f8b\u5982\uff0c\u60a8\u9700\u8981\u5904\u7406\u5e76\u53d1\uff0c\u4ee5\u4fbf\u540c\u65f6\u6293\u53d6\u591a\u4e2a\u9875\u9762\u3002\u60a8\u53ef\u80fd\u8fd8\u60f3\u529e\u6cd5\u5c06\u6293\u53d6\u7684\u6570\u636e\u8f6c\u6362\u4e3a\u4e0d\u540c\u7684\u683c\u5f0f\uff0c\u5982CSV\u3001XML\u6216JSON\u3002\u6709\u65f6\u60a8\u8fd8\u9700\u8981\u5904\u7406\u4e00\u4e9b\u9700\u8981\u7279\u5b9a\u8bbe\u7f6e\u548c\u8bbf\u95ee\u6a21\u5f0f\u7684\u7f51\u7ad9\u3002<\/p>\n<p>\u5982\u679c\u4f60\u5728\u73b0\u6709\u5904\u7406\u8fd9\u4e9b\u95ee\u9898\u7684\u5e93\u7684\u57fa\u7840\u4e0a\u6784\u5efa\u4f60\u7684\u722c\u866b\uff0c\u4f60\u4f1a\u66f4\u987a\u5229\u3002\u5728\u672c\u6559\u7a0b\u4e2d\uff0c\u6211\u4eec\u5c06\u4f7f\u7528Python\u548cScrapy\u6765\u6784\u5efa\u6211\u4eec\u7684\u722c\u866b\u3002<\/p>\n<p>Scrapy\u662f\u6700\u53d7\u6b22\u8fce\u3001\u529f\u80fd\u5f3a\u5927\u7684Python\u722c\u866b\u5e93\u4e4b\u4e00\uff1b\u5b83\u91c7\u7528\u201c\u7535\u6c60\u5df2\u88c5\u5165\u201d\u7684\u65b9\u5f0f\u6765\u8fdb\u884c\u722c\u866b\uff0c\u8fd9\u610f\u5473\u7740\u5b83\u5904\u7406\u4e86\u5927\u90e8\u5206\u5e38\u89c1\u7684\u529f\u80fd\uff0c\u907f\u514d\u4e86\u5f00\u53d1\u8005\u5728\u6bcf\u6b21\u5f00\u53d1\u4e2d\u91cd\u590d\u9020\u8f6e\u5b50\u3002<\/p>\n<p>Scrapy\u548c\u5927\u591a\u6570Python\u5305\u4e00\u6837\uff0c\u53ef\u4ee5\u5728PyPI\uff08\u4e5f\u79f0\u4e3apip\uff09\u4e0a\u627e\u5230\u3002PyPI\u662fPython\u8f6f\u4ef6\u7684\u793e\u533a\u7ef4\u62a4\u4ed3\u5e93\uff0c\u6536\u5f55\u4e86\u6240\u6709\u5df2\u53d1\u5e03\u7684Python\u8f6f\u4ef6\u3002<\/p>\n<p>\u5982\u679c\u60a8\u5df2\u7ecf\u6309\u7167\u672c\u6559\u7a0b\u5148\u51b3\u6761\u4ef6\u4e2d\u6240\u6982\u8ff0\u7684\u65b9\u5f0f\u5b89\u88c5\u4e86Python\uff0c\u90a3\u4e48\u60a8\u7684\u7535\u8111\u4e0a\u5df2\u7ecf\u5b89\u88c5\u4e86pip\uff0c\u56e0\u6b64\u60a8\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5Scrapy\uff1a<\/p>\n<pre class=\"post-pre\"><code><ol><li data-prefix=\"$\">pip <span class=\"token function\">install<\/span> scrapy<\/li><\/ol><\/code><\/pre>\n<p>\u5982\u679c\u60a8\u5728\u5b89\u88c5\u4e2d\u9047\u5230\u4efb\u4f55\u95ee\u9898\uff0c\u6216\u8005\u60f3\u8981\u5728\u4e0d\u4f7f\u7528pip\u7684\u60c5\u51b5\u4e0b\u5b89\u88c5Scrapy\uff0c\u8bf7\u67e5\u9605\u5b98\u65b9\u7684\u5b89\u88c5\u6587\u6863\u3002<\/p>\n<p>\u5728\u5b89\u88c5\u4e86Scrapy\u540e\uff0c\u4e3a\u6211\u4eec\u7684\u9879\u76ee\u521b\u5efa\u4e00\u4e2a\u65b0\u7684\u6587\u4ef6\u5939\u3002\u4f60\u53ef\u4ee5\u901a\u8fc7\u5728\u7ec8\u7aef\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4\u6765\u5b9e\u73b0\uff1a<\/p>\n<pre class=\"post-pre\"><code><ol><li data-prefix=\"$\"><span class=\"token function\">mkdir<\/span> quote-scraper<\/li><\/ol><\/code><\/pre>\n<p>\u73b0\u5728\uff0c\u5bfc\u822a\u8fdb\u5165\u4f60\u521a\u521a\u521b\u5efa\u7684\u65b0\u76ee\u5f55\uff1a<\/p>\n<pre class=\"post-pre\"><code><ol><li data-prefix=\"$\"><span class=\"token builtin class-name\">cd<\/span> quote-scraper<\/li><\/ol><\/code><\/pre>\n<p>\u7136\u540e\uff0c\u5728\u6211\u4eec\u7684\u722c\u866b\u4e2d\u521b\u5efa\u4e00\u4e2a\u540d\u4e3a<code>scraper.py<\/code>\u7684\u65b0Python\u6587\u4ef6\u3002\u5728\u672c\u6559\u7a0b\u4e2d\uff0c\u6211\u4eec\u5c06\u628a\u6240\u6709\u7684\u4ee3\u7801\u90fd\u653e\u5728\u8fd9\u4e2a\u6587\u4ef6\u4e2d\u3002\u60a8\u53ef\u4ee5\u4f7f\u7528\u60a8\u9009\u62e9\u7684\u7f16\u8f91\u8f6f\u4ef6\u521b\u5efa\u6b64\u6587\u4ef6\u3002<\/p>\n<p>\u901a\u8fc7\u4f7f\u7528Scrapy\u4f5c\u4e3a\u57fa\u7840\uff0c\u5f00\u59cb\u9879\u76ee\u7684\u8fc7\u7a0b\u3002\u8981\u505a\u5230\u8fd9\u4e00\u70b9\uff0c\u60a8\u9700\u8981\u521b\u5efa\u4e00\u4e2aPython\u7c7b\uff0c\u8be5\u7c7b\u4ee5<code>scrapy.Spider<\/code>\u4e3a\u57fa\u7c7b\uff0c\u5e76\u7531Scrapy\u63d0\u4f9b\u7684\u57fa\u672c\u722c\u866b\u7c7b\u3002\u8fd9\u4e2a\u7c7b\u5c06\u6709\u4e24\u4e2a\u5fc5\u9700\u7684\u5c5e\u6027\uff1a<\/p>\n<ul class=\"post-ul\">\n<li><code>name<\/code> \u2014 \u722c\u866b\u7684\u540d\u79f0\u3002<\/li>\n<li><code>start_urls<\/code> \u2014 \u4f60\u5f00\u59cb\u6293\u53d6\u7684URL\u5217\u8868\u3002\u6211\u4eec\u5c06\u4ece\u4e00\u4e2aURL\u5f00\u59cb\u3002<\/li>\n<\/ul>\n<p>\u5728\u6587\u672c\u7f16\u8f91\u5668\u4e2d\u6253\u5f00<code>scraper.py<\/code>\u6587\u4ef6\uff0c\u5e76\u6dfb\u52a0\u4ee5\u4e0b\u4ee3\u7801\u6765\u521b\u5efa\u57fa\u672c\u7684\u722c\u866b\uff1a<\/p>\n<div>\u722c\u866b.py<\/p>\n<pre class=\"post-pre\"><code><span class=\"token keyword\">import<\/span> scrapy<span class=\"token keyword\">class<\/span> <span class=\"token class-name\">QuoteSpider<\/span><span class=\"token punctuation\">(<\/span>scrapy<span class=\"token punctuation\">.<\/span>Spider<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>    name <span class=\"token operator\">=<\/span> <span class=\"token string\">'quote-spider'<\/span>    start_urls <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">'https:\/\/quotes.toscrape.com'<\/span><span class=\"token punctuation\">]<\/span><\/code><\/pre>\n<p>\u8ba9\u6211\u4eec\u9010\u884c\u5206\u6790\u8fd9\u6bb5\u4ee3\u7801\uff1a<\/p>\n<p>\u9996\u5148\uff0c\u6211\u4eec\u5bfc\u5165Scrapy\u4ee5\u4fbf\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u8be5\u8f6f\u4ef6\u5305\u63d0\u4f9b\u7684\u7c7b\u3002<\/p>\n<p>\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u4f7f\u7528Scrapy\u63d0\u4f9b\u7684<code>Spider<\/code>\u7c7b\uff0c\u5e76\u4ee5\u5176\u4e3a\u57fa\u7c7b\u521b\u5efa\u4e00\u4e2a\u540d\u4e3a<code>QuoteSpider<\/code>\u7684\u5b50\u7c7b\u3002\u5c06\u5b50\u7c7b\u89c6\u4e3a\u5176\u7236\u7c7b\u7684\u66f4\u4e13\u4e1a\u5f62\u5f0f\u3002<code>Spider<\/code>\u7c7b\u5177\u6709\u5b9a\u4e49\u5982\u4f55\u8ddf\u968fURL\u548c\u4ece\u627e\u5230\u7684\u9875\u9762\u63d0\u53d6\u6570\u636e\u7684\u65b9\u6cd5\u548c\u884c\u4e3a\uff0c\u4f46\u5b83\u4e0d\u77e5\u9053\u8981\u67e5\u627e\u7684\u4f4d\u7f6e\u548c\u8981\u67e5\u627e\u7684\u6570\u636e\u3002\u901a\u8fc7\u521b\u5efa\u4e00\u4e2a\u5b50\u7c7b\uff0c\u6211\u4eec\u53ef\u4ee5\u63d0\u4f9b\u8fd9\u4e9b\u4fe1\u606f\u7ed9\u5b83\u3002<\/p>\n<p>\u6700\u540e\uff0c\u6211\u4eec\u547d\u540d\u8fd9\u4e2a\u7c7b\u4e3a<code>quote-spider<\/code>\uff0c\u5e76\u7ed9\u6211\u4eec\u7684\u722c\u866b\u4e00\u4e2a\u8d77\u59cbURL\uff1a<code>https:\/\/quotes.toscrape.com<\/code>\u3002\u5982\u679c\u4f60\u5728\u6d4f\u89c8\u5668\u4e2d\u6253\u5f00\u8fd9\u4e2aURL\uff0c\u5b83\u4f1a\u5e26\u4f60\u8fdb\u5165\u4e00\u4e2a\u641c\u7d22\u7ed3\u679c\u9875\u9762\uff0c\u5c55\u793a\u4e86\u8bb8\u591a\u8457\u540d\u5f15\u8bed\u7684\u7b2c\u4e00\u9875\u3002<\/p>\n<p>\u73b0\u5728\uff0c\u6d4b\u8bd5\u4e00\u4e0b\u722c\u866b\u3002\u901a\u5e38\uff0cPython\u6587\u4ef6\u4f1a\u901a\u8fc7\u7c7b\u4f3c<code>python path\/to\/file.py<\/code>\u8fd9\u6837\u7684\u547d\u4ee4\u6765\u8fd0\u884c\u3002\u7136\u800c\uff0cScrapy\u81ea\u5e26\u4e86\u81ea\u5df1\u7684\u547d\u4ee4\u884c\u754c\u9762\uff0c\u4ee5\u7b80\u5316\u542f\u52a8\u722c\u866b\u7684\u8fc7\u7a0b\u3002\u8bf7\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u5f00\u59cb\u4f60\u7684\u722c\u866b\uff1a<\/p>\n<pre class=\"post-pre\"><code><ol><li data-prefix=\"$\">scrapy runspider <mark>scraper.py<\/mark><\/li><\/ol><\/code><\/pre>\n<p>\u8be5\u547d\u4ee4\u5c06\u4f1a\u8f93\u51fa\u7c7b\u4f3c\u4ee5\u4e0b\u5185\u5bb9\u7684\u7ed3\u679c\uff1a<\/p>\n<pre class=\"post-pre\"><code><div class=\"secondary-code-label\" title=\"Output\">\u8f93\u51fa<\/div>2022-12-02 10:30:08 [scrapy.utils.log] DEBUG: Using reactor: twisted.internet.epollreactor.EPollReactor<br>2022-12-02 10:30:08 [scrapy.extensions.telnet] INFO: Telnet Password: b4d94e3a8d22ede1<br>2022-12-02 10:30:08 [scrapy.middleware] INFO: Enabled extensions:<br>['scrapy.extensions.corestats.CoreStats',<br> ...<br> 'scrapy.extensions.logstats.LogStats']<br>2022-12-02 10:30:08 [scrapy.middleware] INFO: Enabled downloader middlewares:<br>['scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',<br> ...<br> 'scrapy.downloadermiddlewares.stats.DownloaderStats']<br>2022-12-02 10:30:08 [scrapy.middleware] INFO: Enabled spider middlewares:<br>['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',<br> ...<br> 'scrapy.spidermiddlewares.depth.DepthMiddleware']<br>2022-12-02 10:30:08 [scrapy.middleware] INFO: Enabled item pipelines:<br>[]<br>2022-12-02 10:30:08 [scrapy.core.engine] INFO: Spider opened<br>2022-12-02 10:30:08 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages\/min), scraped 0 items (at 0 items\/min)<br>2022-12-02 10:30:08 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023<br>2022-12-02 10:49:32 [scrapy.core.engine] DEBUG: Crawled (200) &lt;GET https:\/\/quotes.toscrape.com&gt; (referer: None)<br>2022-12-02 10:30:08 [scrapy.core.engine] INFO: Closing spider (finished)<br>2022-12-02 10:30:08 [scrapy.statscollectors] INFO: Dumping Scrapy stats:<br>{'downloader\/request_bytes': 226,<br> ...<br> 'start_time': datetime.datetime(2022, 12, 2, 18, 30, 8, 492403)}<br>2022-12-02 10:30:08 [scrapy.core.engine] INFO: Spider closed (finished)<\/code><\/pre>\n<p>\u8fd9\u662f\u5927\u91cf\u7684\u8f93\u51fa\uff0c\u6240\u4ee5\u8ba9\u6211\u4eec\u5206\u5f00\u6765\u770b\u770b\u3002<\/p>\n<p>\u8fd9\u662f\u6587\u7ae0\u300a\u5982\u4f55\u4f7f\u7528Scrapy\u548cPython 3\u6293\u53d6\u7f51\u9875\u300b\u7684\u7b2c2\u90e8\u5206\uff08\u51719\u90e8\u5206\uff09\u3002<\/p>\n<ul class=\"post-ul\">\n<li>\u722c\u866b\u521d\u59cb\u5316\u5e76\u52a0\u8f7d\u4e86\u5904\u7406URL\u6570\u636e\u8bfb\u53d6\u6240\u9700\u7684\u989d\u5916\u7ec4\u4ef6\u548c\u6269\u5c55\u3002<\/li>\n<li>\u5b83\u4f7f\u7528\u4e86\u6211\u4eec\u5728<code>start_urls<\/code>\u5217\u8868\u4e2d\u63d0\u4f9b\u7684URL\uff0c\u5e76\u6293\u53d6\u4e86HTML\uff0c\u5c31\u50cf\u4f60\u7684\u7f51\u7edc\u6d4f\u89c8\u5668\u6240\u505a\u7684\u90a3\u6837\u3002<\/li>\n<li>\u5b83\u5c06\u8be5HTML\u4f20\u9012\u7ed9<code>parse<\/code>\u65b9\u6cd5\uff0c\u8be5\u65b9\u6cd5\u9ed8\u8ba4\u60c5\u51b5\u4e0b\u4e0d\u6267\u884c\u4efb\u4f55\u64cd\u4f5c\u3002\u7531\u4e8e\u6211\u4eec\u4ece\u672a\u7f16\u5199\u81ea\u5df1\u7684<code>parse<\/code>\u65b9\u6cd5\uff0c\u56e0\u6b64\u722c\u866b\u5728\u672a\u6267\u884c\u4efb\u4f55\u5de5\u4f5c\u7684\u60c5\u51b5\u4e0b\u5c31\u7ed3\u675f\u4e86\u3002<\/li>\n<\/ul>\n<p>\u73b0\u5728\uff0c\u8ba9\u6211\u4eec\u4ece\u9875\u9762\u4e2d\u63d0\u53d6\u4e00\u4e9b\u6570\u636e\u3002<\/p>\n<h2>\u7b2c\u4e8c\u6b65 &#8211; \u4ece\u9875\u9762\u4e2d\u63d0\u53d6\u6570\u636e<\/h2>\n<p>\u6211\u4eec\u5df2\u7ecf\u521b\u5efa\u4e86\u4e00\u4e2a\u975e\u5e38\u57fa\u7840\u7684\u7a0b\u5e8f\uff0c\u5b83\u53ef\u4ee5\u4e0b\u8f7d\u4e00\u4e2a\u9875\u9762\uff0c\u4f46\u76ee\u524d\u8fd8\u6ca1\u6709\u8fdb\u884c\u4efb\u4f55\u6570\u636e\u83b7\u53d6\u6216\u722c\u53d6\u64cd\u4f5c\u3002\u8ba9\u6211\u4eec\u7ed9\u5b83\u4e00\u4e9b\u9700\u8981\u63d0\u53d6\u7684\u6570\u636e\u3002<\/p>\n<p>\u5982\u679c\u4f60\u770b\u4e00\u4e0b\u6211\u4eec\u60f3\u8981\u6293\u53d6\u7684\u9875\u9762\uff0c\u4f60\u4f1a\u770b\u5230\u5b83\u5177\u6709\u4ee5\u4e0b\u7684\u7ed3\u6784\uff1a<\/p>\n<ul class=\"post-ul\">\n<li>\u6709\u4e00\u4e2a\u5728\u6bcf\u4e2a\u9875\u9762\u4e0a\u90fd\u5b58\u5728\u7684\u9875\u7709\u3002<\/li>\n<li>\u6709\u4e00\u4e2a\u767b\u5f55\u94fe\u63a5\u3002<\/li>\n<li>\u7136\u540e\u662f\u5f15\u8a00\u672c\u8eab\uff0c\u4ee5\u8868\u683c\u6216\u6709\u5e8f\u5217\u8868\u7684\u5f62\u5f0f\u663e\u793a\u3002\u6bcf\u4e2a\u5f15\u8a00\u90fd\u5177\u6709\u76f8\u4f3c\u7684\u683c\u5f0f\u3002<\/li>\n<\/ul>\n<p>\u5f53\u64b0\u5199\u7f51\u7edc\u722c\u866b\u65f6\uff0c\u4f60\u5c06\u9700\u8981\u67e5\u770bHTML\u6587\u4ef6\u7684\u6e90\u4ee3\u7801\u5e76\u719f\u6089\u5176\u7ed3\u6784\u3002\u8fd9\u662f\u7b80\u5316\u7248\u7684\u6e90\u4ee3\u7801\uff0c\u4e3a\u4e86\u4fbf\u4e8e\u9605\u8bfb\u5df2\u7ecf\u79fb\u9664\u4e86\u4e0e\u6211\u4eec\u76ee\u6807\u65e0\u5173\u7684\u6807\u7b7e\u3002<\/p>\n<pre class=\"post-pre\"><code><div class=\"secondary-code-label\" title=\"quotes.toscrape.com\">quotes.toscrape.com\r\n<pre><code class=\"language-html\"><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>body<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n...\r\n    <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>div<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>quote<span class=\"token punctuation\">\"<\/span><\/span> <span class=\"token attr-name\">itemscope<\/span> <span class=\"token attr-name\">itemtype<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>http:\/\/schema.org\/CreativeWork<span class=\"token punctuation\">\"<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n        <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>span<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>text<span class=\"token punctuation\">\"<\/span><\/span> <span class=\"token attr-name\">itemprop<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>text<span class=\"token punctuation\">\"<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u201c\u6211\u6ca1\u6709\u5931\u8d25\u3002\u6211\u53ea\u662f\u53d1\u73b0\u4e86\u4e00\u4e07\u79cd\u884c\u4e0d\u901a\u7684\u65b9\u6cd5\u3002\u201d<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n        <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u4f5c\u8005\uff1a<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>small<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>author<span class=\"token punctuation\">\"<\/span><\/span> <span class=\"token attr-name\">itemprop<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>author<span class=\"token punctuation\">\"<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u6258\u9a6c\u65af\u00b7A\u00b7\u7231\u8fea\u751f<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>small<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n        <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>a<\/span> <span class=\"token attr-name\">href<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>\/author\/Thomas-A-Edison<span class=\"token punctuation\">\"<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>(\u5173\u4e8e)<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>a<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n        <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n        <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>div<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>tags<span class=\"token punctuation\">\"<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n            \u6807\u7b7e\uff1a\r\n            <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>meta<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>keywords<span class=\"token punctuation\">\"<\/span><\/span> <span class=\"token attr-name\">itemprop<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>keywords<span class=\"token punctuation\">\"<\/span><\/span> <span class=\"token attr-name\">content<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>\u7231\u8fea\u751f,\u5931\u8d25,\u52b1\u5fd7,\u8f6c\u8ff0<span class=\"token punctuation\">\"<\/span><\/span> <span class=\"token punctuation\">\/&gt;<\/span><\/span> \r\n            \r\n            <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>a<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>tag<span class=\"token punctuation\">\"<\/span><\/span> <span class=\"token attr-name\">href<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>\/tag\/edison\/page\/1\/<span class=\"token punctuation\">\"<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u7231\u8fea\u751f<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>a<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n            \r\n            <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>a<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>tag<span class=\"token punctuation\">\"<\/span><\/span> <span class=\"token attr-name\">href<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>\/tag\/failure\/page\/1\/<span class=\"token punctuation\">\"<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u5931\u8d25<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>a<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n            \r\n            <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>a<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>tag<span class=\"token punctuation\">\"<\/span><\/span> <span class=\"token attr-name\">href<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>\/tag\/inspirational\/page\/1\/<span class=\"token punctuation\">\"<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u52b1\u5fd7<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>a<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n            \r\n            <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>a<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>tag<span class=\"token punctuation\">\"<\/span><\/span> <span class=\"token attr-name\">href<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>\/tag\/paraphrased\/page\/1\/<span class=\"token punctuation\">\"<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u8f6c\u8ff0<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>a<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n            \r\n        <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>div<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n    <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>div<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n...\r\n<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>body<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n<\/code><\/pre>\n<p>\u722c\u53d6\u8fd9\u4e2a\u9875\u9762\u662f\u4e00\u4e2a\u4e24\u6b65\u8fc7\u7a0b\u3002<\/p>\n<p>\u8fd9\u662f\u6587\u7ae0\u300a\u5982\u4f55\u4f7f\u7528Scrapy\u548cPython 3\u6293\u53d6\u7f51\u9875\u300b\u7684\u7b2c4\u90e8\u5206\uff08\u51719\u90e8\u5206\uff09\u3002<\/p>\n<ol>\n<li>\u9996\u5148\uff0c\u901a\u8fc7\u67e5\u627e\u9875\u9762\u4e0a\u6211\u4eec\u60f3\u8981\u7684\u6570\u636e\u90e8\u5206\uff0c\u83b7\u53d6\u6bcf\u4e2a\u5f15\u7528\u3002<\/li>\n<li>\u7136\u540e\uff0c\u9488\u5bf9\u6bcf\u4e2a\u5f15\u7528\uff0c\u901a\u8fc7\u4eceHTML\u6807\u7b7e\u4e2d\u63d0\u53d6\u6570\u636e\u6765\u83b7\u53d6\u6211\u4eec\u60f3\u8981\u7684\u6570\u636e\u3002<\/li>\n<\/ol>\n<p>Scrapy\u6839\u636e\u60a8\u63d0\u4f9b\u7684\u9009\u62e9\u5668\u6765\u83b7\u53d6\u6570\u636e\u3002\u9009\u62e9\u5668\u662f\u6211\u4eec\u7528\u6765\u5728\u9875\u9762\u4e0a\u67e5\u627e\u4e00\u4e2a\u6216\u591a\u4e2a\u5143\u7d20\u7684\u6a21\u5f0f\uff0c\u4ee5\u4fbf\u6211\u4eec\u53ef\u4ee5\u5bf9\u5143\u7d20\u5185\u7684\u6570\u636e\u8fdb\u884c\u64cd\u4f5c\u3002Scrapy\u652f\u6301\u4f7f\u7528CSS\u9009\u62e9\u5668\u6216XPath\u9009\u62e9\u5668\u3002<\/p>\n<p>\u6211\u4eec\u73b0\u5728\u5c06\u4f7f\u7528CSS\u9009\u62e9\u5668\uff0c\u56e0\u4e3aCSS\u975e\u5e38\u9002\u5408\u7528\u4e8e\u67e5\u627e\u9875\u9762\u4e0a\u7684\u6240\u6709\u96c6\u5408\u3002\u5982\u679c\u60a8\u67e5\u770bHTML\uff0c\u60a8\u4f1a\u770b\u5230\u6bcf\u4e2a\u5f15\u7528\u90fd\u4f7f\u7528<code>class=\"quote\"<\/code>\u8fdb\u884c\u4e86\u6307\u5b9a\u3002\u56e0\u4e3a\u6211\u4eec\u6b63\u5728\u5bfb\u627e\u4e00\u4e2a\u7c7b\uff0c\u6240\u4ee5\u6211\u4eec\u4f1a\u4f7f\u7528<code>.quote<\/code>\u4f5c\u4e3a\u6211\u4eec\u7684CSS\u9009\u62e9\u5668\u3002\u9009\u62e9\u5668\u4e2d\u7684<code>.<\/code>\u90e8\u5206\u4f1a\u5728\u5143\u7d20\u7684<code>class<\/code>\u5c5e\u6027\u4e0a\u8fdb\u884c\u641c\u7d22\u3002\u6211\u4eec\u53ea\u9700\u8981\u5728\u7c7b\u4e2d\u521b\u5efa\u4e00\u4e2a\u540d\u4e3a<code>parse<\/code>\u7684\u65b0\u65b9\u6cd5\uff0c\u5e76\u5c06\u8be5\u9009\u62e9\u5668\u4f20\u9012\u7ed9\u54cd\u5e94\u5bf9\u8c61\uff0c\u5c31\u50cf\u8fd9\u6837\uff1a<\/p>\n<div>\n<p>\u722c\u866b.py<\/p>\n<pre class=\"post-pre\"><code><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">QuoteSpider<\/span><span class=\"token punctuation\">(<\/span>scrapy<span class=\"token punctuation\">.<\/span>Spider<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n    name <span class=\"token operator\">=<\/span> <span class=\"token string\">'quote-spdier'<\/span>\r\n    start_urls <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">'https:\/\/quotes.toscrape.com'<\/span><span class=\"token punctuation\">]<\/span>\r\n\r\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">parse<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> response<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n        <mark>QUOTE_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.quote'<\/span><\/mark>\r\n        <mark>TEXT_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.text::text'<\/span><\/mark>\r\n        <mark>AUTHOR_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.author::text'<\/span><\/mark>\r\n        \r\n        <mark><span class=\"token keyword\">for<\/span> quote <span class=\"token keyword\">in<\/span> response<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>QUOTE_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><\/mark>\r\n            <mark><span class=\"token keyword\">pass<\/span><\/mark>\r\n<\/code><\/pre>\n<\/div>\n<p>\u8fd9\u6bb5\u4ee3\u7801\u83b7\u53d6\u9875\u9762\u4e0a\u7684\u6240\u6709\u96c6\u5408\uff0c\u5e76\u5bf9\u5b83\u4eec\u8fdb\u884c\u5faa\u73af\u4ee5\u63d0\u53d6\u6570\u636e\u3002\u73b0\u5728\u8ba9\u6211\u4eec\u4ece\u8fd9\u4e9b\u5f15\u6587\u4e2d\u63d0\u53d6\u6570\u636e\uff0c\u4ee5\u4fbf\u6211\u4eec\u80fd\u591f\u663e\u793a\u5b83\u3002<\/p>\n<p>\u518d\u770b\u4e00\u4e0b\u6211\u4eec\u89e3\u6790\u7684\u9875\u9762\u7684\u6e90\u4ee3\u7801\uff0c\u5b83\u544a\u8bc9\u6211\u4eec\u6bcf\u4e2a\u5f15\u7528\u7684\u6587\u672c\u90fd\u5b58\u50a8\u5728\u4e00\u4e2a\u5e26\u6709<code>text<\/code>\u7c7b\u7684<code>&lt;span&gt;<\/code>\u6807\u7b7e\u5185\uff0c\u800c\u5f15\u7528\u7684\u4f5c\u8005\u5219\u5728\u4e00\u4e2a\u5e26\u6709<code>author<\/code>\u7c7b\u7684<code>&lt;small&gt;<\/code>\u6807\u7b7e\u5185\u3002<\/p>\n<pre class=\"post-pre\"><code><div class=\"secondary-code-label\" title=\"quotes.toscrape.com\">quotes.toscrape.com...\r\n        <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>span<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>text<span class=\"token punctuation\">\"<\/span><\/span> <span class=\"token attr-name\">itemprop<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>text<span class=\"token punctuation\">\"<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\u201cI have not failed. I<span class=\"token entity\" title=\"'\">&amp;#39;<\/span>ve just found 10,000 ways that won<span class=\"token entity\" title=\"'\">&amp;#39;<\/span>t work.\u201d<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n        <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>span<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>by <span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>small<\/span> <span class=\"token attr-name\">class<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>author<span class=\"token punctuation\">\"<\/span><\/span> <span class=\"token attr-name\">itemprop<\/span><span class=\"token attr-value\"><span class=\"token punctuation attr-equals\">=<\/span><span class=\"token punctuation\">\"<\/span>author<span class=\"token punctuation\">\"<\/span><\/span><span class=\"token punctuation\">&gt;<\/span><\/span>Thomas A. Edison<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;\/<\/span>small<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n        ...\r\n<\/code><\/pre>\n<p>\u6211\u4eec\u6b63\u5728\u5faa\u73af\u904d\u5386\u7684\u5f15\u7528\u5bf9\u8c61\u5177\u6709\u81ea\u5df1\u7684<code>css<\/code>\u65b9\u6cd5\uff0c\u56e0\u6b64\u6211\u4eec\u53ef\u4ee5\u4f20\u5165\u4e00\u4e2a\u9009\u62e9\u5668\u6765\u5b9a\u4f4d\u5b50\u5143\u7d20\u3002\u8bf7\u6309\u7167\u4ee5\u4e0b\u65b9\u5f0f\u4fee\u6539\u60a8\u7684\u4ee3\u7801\uff0c\u4ee5\u627e\u5230\u96c6\u5408\u7684\u540d\u79f0\u5e76\u663e\u793a\u51fa\u6765\u3002<\/p>\n<div>\u522e\u522e\u5668.py<\/div>\n<pre class=\"post-pre\"><code><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">QuoteSpider<\/span><span class=\"token punctuation\">(<\/span>scrapy<span class=\"token punctuation\">.<\/span>Spider<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n    name <span class=\"token operator\">=<\/span> <span class=\"token string\">'quote-spdier'<\/span>\r\n    start_urls <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">'https:\/\/quotes.toscrape.com'<\/span><span class=\"token punctuation\">]<\/span>\r\n\r\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">parse<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> response<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n        QUOTE_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.quote'<\/span>\r\n        TEXT_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.text::text'<\/span>\r\n        AUTHOR_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.author::text'<\/span>\r\n        \r\n        <span class=\"token keyword\">for<\/span> quote <span class=\"token keyword\">in<\/span> response<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>QUOTE_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n            <mark><span class=\"token keyword\">yield<\/span> <span class=\"token punctuation\">{<\/span><\/mark>\r\n                <mark><span class=\"token string\">'text'<\/span><span class=\"token punctuation\">:<\/span> quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>TEXT_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract_first<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><\/mark>\r\n                <mark><span class=\"token string\">'author'<\/span><span class=\"token punctuation\">:<\/span> quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>AUTHOR_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract_first<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><\/mark>\r\n            <mark><span class=\"token punctuation\">}<\/span><\/mark>\r\n<\/code><\/pre>\n<div class=\"post-conf-note\">\n<p class=\"post-note\">\n<p class=\"post-conf-desc\">\u6ce8\u610f\uff1a<code>extract_first()<\/code> \u540e\u9762\u7684\u9017\u53f7\u4e0d\u662f\u62fc\u5199\u9519\u8bef\u3002\u5728 Python \u4e2d\uff0c\u5b57\u5178\u5bf9\u8c61\u540e\u9762\u7684\u9017\u53f7\u662f\u6709\u6548\u8bed\u6cd5\uff0c\u4e5f\u662f\u4e3a\u4e86\u7ed9\u6dfb\u52a0\u66f4\u591a\u5143\u7d20\u7559\u51fa\u7a7a\u95f4\uff0c\u5728\u540e\u9762\u6211\u4eec\u4f1a\u770b\u5230\u3002<\/p>\n<p>\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u4f60\u4f1a\u6ce8\u610f\u5230\u4e24\u4ef6\u4e8b\uff1a<\/p>\n<ul class=\"post-ul\">\n<li>\u6211\u4eec\u4e3a\u5f15\u7528\u548c\u4f5c\u8005\u7684\u9009\u62e9\u5668\u6dfb\u52a0\u4e86 <code>::text<\/code>\u3002\u8fd9\u662f\u4e00\u4e2a CSS \u4f2a\u9009\u62e9\u5668\uff0c\u7528\u4e8e\u83b7\u53d6\u6807\u7b7e\u5185\u90e8\u7684\u6587\u672c\uff0c\u800c\u4e0d\u662f\u6807\u7b7e\u672c\u8eab\u3002<\/li>\n<li>\u6211\u4eec\u5bf9 <code>quote.css(TEXT_SELECTOR)<\/code> \u8fd4\u56de\u7684\u5bf9\u8c61\u8c03\u7528\u4e86 <code>extract_first()<\/code>\uff0c\u56e0\u4e3a\u6211\u4eec\u53ea\u9700\u8981\u5339\u914d\u9009\u62e9\u5668\u7684\u7b2c\u4e00\u4e2a\u5143\u7d20\u3002\u8fd9\u4f1a\u8fd4\u56de\u4e00\u4e2a\u5b57\u7b26\u4e32\uff0c\u800c\u4e0d\u662f\u4e00\u4e2a\u5143\u7d20\u5217\u8868\u3002<\/li>\n<\/ul>\n<p>\u4fdd\u5b58\u6587\u4ef6\u5e76\u518d\u6b21\u8fd0\u884c\u722c\u866b\u7a0b\u5e8f\u3002<\/p>\n<pre class=\"post-pre\"><code><ol><li data-prefix=\"$\">scrapy runspider <mark>scraper.py<\/mark>\r\n<\/li><\/ol>\r\n<\/code><\/pre>\n<p>\u8fd9\u6b21\u7684\u8f93\u51fa\u5c06\u5305\u62ec\u5f15\u7528\u53ca\u5176\u4f5c\u8005\u3002<\/p>\n<pre class=\"post-pre\"><code><div class=\"secondary-code-label\" title=\"Output\">\u8f93\u51fa<\/div>\r\n2022-12-02 11:00:53 [scrapy.core.scraper] DEBUG: \u4ece &lt;200 https:\/\/quotes.toscrape.com&gt; \u6293\u53d6\r\n{'text': '\u201cThere are only two ways to live your life. One is as though nothing is a miracle. The other is as though everything is a miracle.\u201d', 'author': 'Albert Einstein'}\r\n2022-12-02 11:00:53 [scrapy.core.scraper] DEBUG: \u4ece &lt;200 https:\/\/quotes.toscrape.com&gt; \u6293\u53d6\r\n{'text': '\u201cThe person, be it gentleman or lady, who has not pleasure in a good novel, must be intolerably stupid.\u201d', 'author': 'Jane Austen'}\r\n2022-12-02 11:00:53 [scrapy.core.scraper] DEBUG: \u4ece &lt;200 https:\/\/quotes.toscrape.com&gt; \u6293\u53d6\r\n{'text': \"\u201cImperfection is beauty, madness is genius and it's better to be absolutely ridiculous than absolutely boring.\u201d\", 'author': 'Marilyn Monroe'}\r\n...\r\n\r\n<\/code><\/pre>\n<p>\u8ba9\u6211\u4eec\u7ee7\u7eed\u6269\u5c55\u8fd9\u4e2a\u529f\u80fd\uff0c\u5e76\u4e3a\u4f5c\u8005\u7684\u9875\u9762\u6dfb\u52a0\u65b0\u7684\u9009\u62e9\u5668\u548c\u6807\u7b7e\u6765\u5f15\u7528\u3002\u901a\u8fc7\u7814\u7a76\u6bcf\u4e2a\u5f15\u7528\u7684 HTML\uff0c\u6211\u4eec\u53d1\u73b0\uff1a<\/p>\n<ul class=\"post-ul\">\n<li>\u6307\u5411\u4f5c\u8005\u7b80\u4ecb\u9875\u9762\u7684\u94fe\u63a5\u5b58\u50a8\u5728\u7d27\u968f\u5176\u59d3\u540d\u4e4b\u540e\u7684\u94fe\u63a5\u4e2d\u3002<\/li>\n<li>\u6807\u7b7e\u5b58\u50a8\u4e3a <code>&lt;a&gt;<\/code> \u6807\u7b7e\u7684\u96c6\u5408\uff0c\u6bcf\u4e2a\u6807\u7b7e\u90fd\u5e26\u6709 <code>tag<\/code> \u7c7b\uff0c\u5b58\u50a8\u5728\u5e26\u6709 <code>tags<\/code> \u7c7b\u7684 <code>&lt;div&gt;<\/code> \u5143\u7d20\u4e2d\u3002<\/li>\n<\/ul>\n<p>\u90a3\u4e48\uff0c\u8ba9\u6211\u4eec\u4fee\u6539\u7f51\u9875\u6293\u53d6\u5de5\u5177\u6765\u83b7\u53d6\u8fd9\u4e9b\u65b0\u7684\u4fe1\u606f\u5427\u3002<\/p>\n<div>scraper.py<\/div>\n<\/div>\n<pre class=\"post-pre\"><code><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">QuoteSpider<\/span><span class=\"token punctuation\">(<\/span>scrapy<span class=\"token punctuation\">.<\/span>Spider<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n    name <span class=\"token operator\">=<\/span> <span class=\"token string\">'quote-spdier'<\/span>\r\n    start_urls <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">'https:\/\/quotes.toscrape.com'<\/span><span class=\"token punctuation\">]<\/span>\r\n\r\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">parse<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> response<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n        QUOTE_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.quote'<\/span>\r\n        TEXT_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.text::text'<\/span>\r\n        AUTHOR_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.author::text'<\/span>\r\n        <mark>ABOUT_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.author + a::attr(\"href\")'<\/span><\/mark>\r\n        <mark>TAGS_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.tags &gt; .tag::text'<\/span><\/mark>\r\n\r\n        <span class=\"token keyword\">for<\/span> quote <span class=\"token keyword\">in<\/span> response<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>QUOTE_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n            <span class=\"token keyword\">yield<\/span> <span class=\"token punctuation\">{<\/span>\r\n                <span class=\"token string\">'text'<\/span><span class=\"token punctuation\">:<\/span> quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>TEXT_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract_first<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n                <span class=\"token string\">'author'<\/span><span class=\"token punctuation\">:<\/span> quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>AUTHOR_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract_first<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n                <mark><span class=\"token string\">'about'<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">'https:\/\/quotes.toscrape.com'<\/span> <span class=\"token operator\">+<\/span> <\/mark>\r\n                        <mark>quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>ABOUT_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract_first<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><\/mark>\r\n                <mark><span class=\"token string\">'tags'<\/span><span class=\"token punctuation\">:<\/span> quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>TAGS_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><\/mark>\r\n            <span class=\"token punctuation\">}<\/span>\r\n\r\n<\/code><\/pre>\n<p>\u4fdd\u5b58\u60a8\u6240\u505a\u7684\u66f4\u6539\u5e76\u518d\u6b21\u8fd0\u884c\u6293\u53d6\u7a0b\u5e8f\u3002<\/p>\n<pre class=\"post-pre\"><code><ol><li data-prefix=\"$\">scrapy runspider <mark>scraper.py<\/mark>\r\n<\/li><\/ol>\r\n<\/code><\/pre>\n<p>\u73b0\u5728\u8f93\u51fa\u5c06\u5305\u542b\u65b0\u6570\u636e\u3002<\/p>\n<pre class=\"post-pre\"><code><div class=\"secondary-code-label\" title=\"Output\">Output\r\n<p>\u8fd9\u662f\u6587\u7ae0\u300a\u5982\u4f55\u4f7f\u7528Scrapy\u548cPython 3\u6293\u53d6\u7f51\u9875\u300b\u7684\u7b2c7\u90e8\u5206\uff08\u51719\u90e8\u5206\uff09\u3002<\/p>\r\n<p>\u5185\u5bb9\u7247\u6bb5:<\/p>\r\n<pre><code>2022-12-02 11:14:28 [scrapy.core.scraper] DEBUG: Scraped from &lt;200 https:\/\/quotes.toscrape.com&gt;\r\n{'text': '\u201cThere are only two ways to live your life. One is as though nothing is a miracle. The other is as though everything is a miracle.\u201d', 'author': 'Albert Einstein', 'about': 'https:\/\/quotes.toscrape.com\/author\/Albert-Einstein', 'tags': ['inspirational', 'life', 'live', 'miracle', 'miracles']}\r\n2022-12-02 11:14:28 [scrapy.core.scraper] DEBUG: Scraped from &lt;200 https:\/\/quotes.toscrape.com&gt;\r\n{'text': '\u201cThe person, be it gentleman or lady, who has not pleasure in a good novel, must be intolerably stupid.\u201d', 'author': 'Jane Austen', 'about': 'https:\/\/quotes.toscrape.com\/author\/Jane-Austen', 'tags': ['aliteracy', 'books', 'classic', 'humor']}\r\n2022-12-02 11:14:28 [scrapy.core.scraper] DEBUG: Scraped from &lt;200 https:\/\/quotes.toscrape.com&gt;\r\n{'text': \"\u201cImperfection is beauty, madness is genius and it's better to be absolutely ridiculous than absolutely boring.\u201d\", 'author': 'Marilyn Monroe', 'about': 'https:\/\/quotes.toscrape.com\/author\/Marilyn-Monroe', 'tags': ['be-yourself', 'inspirational']}\r\n<\/code><\/pre>\n<p>\u73b0\u5728\uff0c\u8ba9\u6211\u4eec\u5c06\u8fd9\u4e2a\u6293\u53d6\u5668\uff08Scraper\uff09\u8f6c\u6362\u4e3a\u4e00\u4e2a\u80fd\u8ddf\u8e2a\u94fe\u63a5\u7684\u722c\u866b\uff08Spider\uff09\u3002<\/p>\n<h2>\u7b2c\u4e09\u6b65 \u2014 \u722c\u53d6\u591a\u4e2a\u9875\u9762<\/h2>\n<p>\u60a8\u5df2\u7ecf\u6210\u529f\u5730\u4ece\u521d\u59cb\u9875\u9762\u63d0\u53d6\u4e86\u6570\u636e\uff0c\u4f46\u6211\u4eec\u65e0\u6cd5\u8fdb\u4e00\u6b65\u67e5\u770b\u5176\u4f59\u7684\u7ed3\u679c\u3002\u722c\u866b\u7684\u6574\u4e2a\u76ee\u7684\u662f\u68c0\u6d4b\u5e76\u904d\u5386\u5176\u4ed6\u9875\u9762\u7684\u94fe\u63a5\uff0c\u5e76\u4ece\u8fd9\u4e9b\u9875\u9762\u4e2d\u83b7\u53d6\u6570\u636e\u3002<\/p>\n<p>\u60a8\u4f1a\u6ce8\u610f\u5230\u6bcf\u4e2a\u9875\u9762\u7684\u9876\u90e8\u548c\u5e95\u90e8\u90fd\u6709\u4e00\u4e2a\u5c0f\u7684\u53f3\u7bad\u5934\uff08&gt;\uff09\uff0c\u5b83\u94fe\u63a5\u5230\u4e0b\u4e00\u9875\u7684\u7ed3\u679c\u3002\u8fd9\u662f\u5b83\u7684HTML\u4ee3\u7801\uff1a<\/p>\n<pre class=\"post-pre\"><code>&lt;div class=\"secondary-code-label\" title=\"quotes.toscrape.com\"&gt;quotes.toscrape.com...\r\n    &lt;nav&gt;\r\n        &lt;ul class=\"pager\"&gt;\r\n            \r\n            \r\n            &lt;li class=\"next\"&gt;\r\n                &lt;a href=\"\/page\/2\/\"&gt;Next &lt;span aria-hidden=\"true\"&gt;&amp;rarr;&lt;\/span&gt;&lt;\/a&gt;\r\n            &lt;\/li&gt;\r\n            \r\n        &lt;\/ul&gt;\r\n    &lt;\/nav&gt;\r\n...\r\n<\/code><\/pre>\n<p>\u5728\u6e90\u4ee3\u7801\u4e2d\uff0c\u60a8\u4f1a\u627e\u5230\u4e00\u4e2a\u5e26\u6709\u201cnext\u201d\u7c7b\u7684<code>&lt;li&gt;<\/code>\u6807\u7b7e\uff0c\u5728\u8be5\u6807\u7b7e\u5185\u90e8\uff0c\u6709\u4e00\u4e2a\u6307\u5411\u4e0b\u4e00\u9875\u7684\u8d85\u94fe\u63a5<code>&lt;a&gt;<\/code>\u6807\u7b7e\u3002\u6211\u4eec\u552f\u4e00\u8981\u505a\u7684\u5c31\u662f\u544a\u8bc9\u722c\u866b\uff0c\u5982\u679c\u5b58\u5728\u8be5\u94fe\u63a5\uff0c\u5c31\u8ddf\u968f\u8fd9\u4e2a\u94fe\u63a5\u3002<\/p>\n<p>\u8bf7\u6309\u7167\u4ee5\u4e0b\u65b9\u5f0f\u4fee\u6539\u60a8\u7684\u4ee3\u7801\uff1a<\/p>\n<div>\u722c\u866b.py<\/div>\n<p>\u8fd9\u662f\u6587\u7ae0\u300a\u5982\u4f55\u4f7f\u7528Scrapy\u548cPython 3\u6293\u53d6\u7f51\u9875\u300b\u7684\u7b2c8\u90e8\u5206\uff08\u51719\u90e8\u5206\uff09\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">QuoteSpider<\/span><span class=\"token punctuation\">(<\/span>scrapy<span class=\"token punctuation\">.<\/span>Spider<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n    name <span class=\"token operator\">=<\/span> <span class=\"token string\">'quote-spdier'<\/span>\r\n    start_urls <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">'https:\/\/quotes.toscrape.com'<\/span><span class=\"token punctuation\">]<\/span>\r\n\r\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">parse<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> response<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n        QUOTE_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.quote'<\/span>\r\n        TEXT_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.text::text'<\/span>\r\n        AUTHOR_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.author::text'<\/span>\r\n        ABOUT_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.author + a::attr(\"href\")'<\/span>\r\n        TAGS_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.tags &gt; .tag::text'<\/span>\r\n        <mark>NEXT_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.next a::attr(\"href\")'<\/span><\/mark>\r\n\r\n        <span class=\"token keyword\">for<\/span> quote <span class=\"token keyword\">in<\/span> response<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>QUOTE_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n            <span class=\"token keyword\">yield<\/span> <span class=\"token punctuation\">{<\/span>\r\n                <span class=\"token string\">'text'<\/span><span class=\"token punctuation\">:<\/span> quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>TEXT_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract_first<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n                <span class=\"token string\">'author'<\/span><span class=\"token punctuation\">:<\/span> quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>AUTHOR_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract_first<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n                <span class=\"token string\">'about'<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">'https:\/\/quotes.toscrape.com'<\/span> <span class=\"token operator\">+<\/span> \r\n                        quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>ABOUT_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract_first<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n                <span class=\"token string\">'tags'<\/span><span class=\"token punctuation\">:<\/span> quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>TAGS_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n            <span class=\"token punctuation\">}<\/span>\r\n\r\n        <mark>next_page <span class=\"token operator\">=<\/span> response<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>NEXT_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract_first<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/mark>\r\n        <mark><span class=\"token keyword\">if<\/span> next_page<span class=\"token punctuation\">:<\/span><\/mark>\r\n            <mark><span class=\"token keyword\">yield<\/span> scrapy<span class=\"token punctuation\">.<\/span>Request<span class=\"token punctuation\">(<\/span>response<span class=\"token punctuation\">.<\/span>urljoin<span class=\"token punctuation\">(<\/span>next_page<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/mark>\r\n\r\n<\/code><\/pre>\n<p>\u9996\u5148\uff0c\u6211\u4eec\u4e3a\u201c\u4e0b\u4e00\u9875\u201d\u94fe\u63a5\u5b9a\u4e49\u4e00\u4e2a\u9009\u62e9\u5668\uff0c\u5e76\u63d0\u53d6\u7b2c\u4e00\u4e2a\u5339\u914d\u9879\uff0c\u7136\u540e\u68c0\u67e5\u5176\u662f\u5426\u5b58\u5728\u3002<code>scrapy.Request<\/code> \u662f\u4e00\u4e2a\u65b0\u7684\u8bf7\u6c42\u5bf9\u8c61\uff0cScrapy \u77e5\u9053\u5b83\u610f\u5473\u7740\u5e94\u8be5\u83b7\u53d6\u5e76\u89e3\u6790\u4e0b\u4e00\u9875\u3002<\/p>\n<p>\u8fd9\u610f\u5473\u7740\u4e00\u65e6\u6211\u4eec\u7ffb\u5230\u4e0b\u4e00\u9875\uff0c\u6211\u4eec\u4f1a\u5728\u90a3\u91cc\u5bfb\u627e\u4e0b\u4e00\u9875\u7684\u94fe\u63a5\uff0c\u7136\u540e\u5728\u90a3\u4e00\u9875\u4e0a\u518d\u627e\u5230\u4e0b\u4e00\u9875\u7684\u94fe\u63a5\uff0c\u76f4\u5230\u6211\u4eec\u627e\u4e0d\u5230\u4e0b\u4e00\u9875\u7684\u94fe\u63a5\u4e3a\u6b62\u3002\u8fd9\u662f\u7f51\u9875\u722c\u53d6\u7684\u5173\u952e\u90e8\u5206\uff1a\u627e\u5230\u5e76\u8ddf\u968f\u94fe\u63a5\u3002\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u5b83\u662f\u975e\u5e38\u7ebf\u6027\u7684\uff1b\u4e00\u4e2a\u9875\u9762\u6709\u4e00\u4e2a\u94fe\u63a5\u6307\u5411\u4e0b\u4e00\u9875\uff0c\u76f4\u5230\u6211\u4eec\u5230\u8fbe\u6700\u540e\u4e00\u9875\u3002\u4f46\u662f\u4f60\u4e5f\u53ef\u4ee5\u8ddf\u968f\u94fe\u63a5\u5230\u6807\u7b7e\u3001\u5176\u4ed6\u641c\u7d22\u7ed3\u679c\u6216\u4efb\u4f55\u4f60\u60f3\u8981\u7684 URL\u3002<\/p>\n<p>\u73b0\u5728\uff0c\u5982\u679c\u4f60\u4fdd\u5b58\u4ee3\u7801\u5e76\u518d\u6b21\u8fd0\u884c\u722c\u866b\uff0c\u4f60\u4f1a\u53d1\u73b0\u5b83\u4e0d\u4ec5\u4ec5\u5728\u904d\u5386\u7b2c\u4e00\u9875\u7684\u6570\u636e\u4e4b\u540e\u505c\u6b62\u3002\u5b83\u5c06\u7ee7\u7eed\u904d\u5386\u6240\u6709 10 \u9875\u4e2d\u7684 100 \u4e2a\u5f15\u7528\u3002\u5c31\u6574\u4f53\u800c\u8a00\uff0c\u8fd9\u4e0d\u662f\u5927\u91cf\u7684\u6570\u636e\uff0c\u4f46\u73b0\u5728\u4f60\u77e5\u9053\u4e86\u81ea\u52a8\u67e5\u627e\u65b0\u9875\u9762\u8fdb\u884c\u6570\u636e\u6293\u53d6\u7684\u8fc7\u7a0b\u3002<\/p>\n<p>\u8fd9\u662f\u6211\u4eec\u4e3a\u672c\u6559\u7a0b\u51c6\u5907\u7684\u5b8c\u6574\u4ee3\u7801\u3002<\/p>\n<div>\u722c\u866b.py<\/div>\n<pre class=\"post-pre\"><code><span class=\"token keyword\">import<\/span> scrapy\r\n\r\n\r\n<span class=\"token keyword\">class<\/span> <span class=\"token class-name\">QuoteSpider<\/span><span class=\"token punctuation\">(<\/span>scrapy<span class=\"token punctuation\">.<\/span>Spider<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n    name <span class=\"token operator\">=<\/span> <span class=\"token string\">'quote-spider'<\/span>\r\n    start_urls <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">'https:\/\/quotes.toscrape.com'<\/span><span class=\"token punctuation\">]<\/span>\r\n\r\n    <span class=\"token keyword\">def<\/span> <span class=\"token function\">parse<\/span><span class=\"token punctuation\">(<\/span>self<span class=\"token punctuation\">,<\/span> response<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n        QUOTE_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.quote'<\/span>\r\n        TEXT_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.text::text'<\/span>\r\n        AUTHOR_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.author::text'<\/span>\r\n        ABOUT_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.author + a::attr(\"href\")'<\/span>\r\n        TAGS_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.tags &gt; .tag::text'<\/span>\r\n        NEXT_SELECTOR <span class=\"token operator\">=<\/span> <span class=\"token string\">'.next a::attr(\"href\")'<\/span>\r\n\r\n        <span class=\"token keyword\">for<\/span> quote <span class=\"token keyword\">in<\/span> response<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>QUOTE_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n            <span class=\"token keyword\">yield<\/span> <span class=\"token punctuation\">{<\/span>\r\n                <span class=\"token string\">'text'<\/span><span class=\"token punctuation\">:<\/span> quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>TEXT_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract_first<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n                <span class=\"token string\">'author'<\/span><span class=\"token punctuation\">:<\/span> quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>AUTHOR_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract_first<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n                <span class=\"token string\">'about'<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">'https:\/\/quotes.toscrape.com'<\/span> <span class=\"token operator\">+<\/span> \r\n                        quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>ABOUT_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract_first<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n                <span class=\"token string\">'tags'<\/span><span class=\"token punctuation\">:<\/span> quote<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>TAGS_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n            <span class=\"token punctuation\">}<\/span>\r\n\r\n        next_page <span class=\"token operator\">=<\/span> response<span class=\"token punctuation\">.<\/span>css<span class=\"token punctuation\">(<\/span>NEXT_SELECTOR<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>extract_first<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n        <span class=\"token keyword\">if<\/span> next_page<span class=\"token punctuation\">:<\/span>\r\n            <span class=\"token keyword\">yield<\/span> scrapy<span class=\"token punctuation\">.<\/span>Request<span class=\"token punctuation\">(<\/span>\r\n                response<span class=\"token punctuation\">.<\/span>urljoin<span class=\"token punctuation\">(<\/span>next_page<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n            <span class=\"token punctuation\">)<\/span>\r\n\r\n<\/code><\/pre>\n<h2>\u7ed3\u8bba<\/h2>\n<p>\u5728\u672c\u6559\u7a0b\u4e2d\uff0c\u60a8\u6784\u5efa\u4e86\u4e00\u4e2a\u529f\u80fd\u5b8c\u6574\u7684\u722c\u866b\uff0c\u5b83\u80fd\u591f\u5728\u4e0d\u5230\u4e09\u5341\u884c\u4ee3\u7801\u4e2d\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u6570\u636e\u3002\u8fd9\u662f\u4e00\u4e2a\u5f88\u597d\u7684\u5f00\u59cb\uff0c\u4f46\u60a8\u53ef\u4ee5\u7528\u8fd9\u4e2a\u722c\u866b\u505a\u5f88\u591a\u6709\u8da3\u7684\u4e8b\u60c5\u3002\u8fd9\u8db3\u4ee5\u8ba9\u60a8\u8fdb\u884c\u601d\u8003\u548c\u5b9e\u9a8c\u3002\u5982\u679c\u60a8\u9700\u8981\u5173\u4e8eScrapy\u7684\u66f4\u591a\u4fe1\u606f\uff0c\u8bf7\u53c2\u8003Scrapy\u7684\u5b98\u65b9\u6587\u6863\u3002\u6709\u5173\u4ece\u7f51\u7edc\u4e2d\u63d0\u53d6\u6570\u636e\u7684\u66f4\u591a\u4fe1\u606f\uff0c\u8bf7\u53c2\u9605\u6211\u4eec\u5173\u4e8e\u201c\u5982\u4f55\u4f7f\u7528Beautiful Soup\u548cPython 3\u722c\u53d6\u7f51\u9875\u201d\u7684\u6559\u7a0b\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5f15\u8a00 \u7f51\u9875\u6293\u53d6\uff0c\u901a\u5e38\u88ab\u79f0\u4e3a\u7f51\u7edc\u722c\u866b\u6216\u7f51\u7edc\u8718\u86db\uff0c\u662f\u6307\u4ee5\u7a0b\u5e8f\u5316\u65b9\u5f0f\u6d4f\u89c8\u4e00\u7cfb\u5217\u7f51\u9875\u5e76\u4ece\u4e2d\u63d0\u53d6\u6570\u636e\u7684\u884c\u4e3a\u3002\u5b83\u662f\u5904\u7406\u7f51\u7edc [&hellip;]<\/p>\n","protected":false},"author":9,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[32,444,165,446,445],"class_list":["post-77","post","type-post","status-publish","format-standard","hentry","category-uncategorized","tag-python","tag-scrapy","tag-165","tag-446","tag-445"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.5 (Yoast SEO v21.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Scrapy\u4e0ePython 3\u7f51\u9875\u6293\u53d6\u5b9e\u6218\uff1a\u4ece\u5165\u95e8\u5230\u7cbe\u901a - Blog - Silicon Cloud<\/title>\n<meta name=\"description\" content=\"\u5b66\u4e60\u5982\u4f55\u4f7f\u7528\u5f3a\u5927\u7684Scrapy\u6846\u67b6\u548cPython 3\u9ad8\u6548\u6293\u53d6\u7f51\u9875\u6570\u636e\u3002\u672c\u6559\u7a0b\u6db5\u76d6Scrapy\u5b89\u88c5\u3001\u9879\u76ee\u521b\u5efa\u3001\u9009\u62e9\u5668\u4f7f\u7528\u3001\u6570\u636e\u5b58\u50a8\u7b49\u6838\u5fc3\u77e5\u8bc6\uff0c\u52a9\u4f60\u5feb\u901f\u638c\u63e1\u7f51\u9875\u722c\u53d6\u6280\u672f\uff0c\u8f7b\u677e\u5b9e\u73b0\u6570\u636e\u81ea\u52a8\u5316\u91c7\u96c6\u3002\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.silicloud.com\/zh\/blog\/\u5982\u4f55\u4f7f\u7528scrapy\u548cpython-3\u6293\u53d6\u7f51\u9875\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Scrapy\u4e0ePython 3\u7f51\u9875\u6293\u53d6\u5b9e\u6218\uff1a\u4ece\u5165\u95e8\u5230\u7cbe\u901a\" \/>\n<meta property=\"og:description\" content=\"\u5b66\u4e60\u5982\u4f55\u4f7f\u7528\u5f3a\u5927\u7684Scrapy\u6846\u67b6\u548cPython 3\u9ad8\u6548\u6293\u53d6\u7f51\u9875\u6570\u636e\u3002\u672c\u6559\u7a0b\u6db5\u76d6Scrapy\u5b89\u88c5\u3001\u9879\u76ee\u521b\u5efa\u3001\u9009\u62e9\u5668\u4f7f\u7528\u3001\u6570\u636e\u5b58\u50a8\u7b49\u6838\u5fc3\u77e5\u8bc6\uff0c\u52a9\u4f60\u5feb\u901f\u638c\u63e1\u7f51\u9875\u722c\u53d6\u6280\u672f\uff0c\u8f7b\u677e\u5b9e\u73b0\u6570\u636e\u81ea\u52a8\u5316\u91c7\u96c6\u3002\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/\u5982\u4f55\u4f7f\u7528scrapy\u548cpython-3\u6293\u53d6\u7f51\u9875\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2023-11-10T13:21:46+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-07-31T14:30:33+00:00\" \/>\n<meta name=\"author\" content=\"\u6e05, \u626c\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u6e05, \u626c\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/\",\"name\":\"Scrapy\u4e0ePython 3\u7f51\u9875\u6293\u53d6\u5b9e\u6218\uff1a\u4ece\u5165\u95e8\u5230\u7cbe\u901a - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2023-11-10T13:21:46+00:00\",\"dateModified\":\"2025-07-31T14:30:33+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/cb5556d2501da73d864cac945e8d9461\"},\"description\":\"\u5b66\u4e60\u5982\u4f55\u4f7f\u7528\u5f3a\u5927\u7684Scrapy\u6846\u67b6\u548cPython 3\u9ad8\u6548\u6293\u53d6\u7f51\u9875\u6570\u636e\u3002\u672c\u6559\u7a0b\u6db5\u76d6Scrapy\u5b89\u88c5\u3001\u9879\u76ee\u521b\u5efa\u3001\u9009\u62e9\u5668\u4f7f\u7528\u3001\u6570\u636e\u5b58\u50a8\u7b49\u6838\u5fc3\u77e5\u8bc6\uff0c\u52a9\u4f60\u5feb\u901f\u638c\u63e1\u7f51\u9875\u722c\u53d6\u6280\u672f\uff0c\u8f7b\u677e\u5b9e\u73b0\u6570\u636e\u81ea\u52a8\u5316\u91c7\u96c6\u3002\",\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Scrapy\u4e0ePython 3\u7f51\u9875\u6293\u53d6\u5b9e\u6218\uff1a\u4ece\u5165\u95e8\u5230\u7cbe\u901a\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/\",\"name\":\"Blog - Silicon Cloud\",\"description\":\"\",\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/cb5556d2501da73d864cac945e8d9461\",\"name\":\"\u6e05, \u626c\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g\",\"caption\":\"\u6e05, \u626c\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/qingyang\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Scrapy\u4e0ePython 3\u7f51\u9875\u6293\u53d6\u5b9e\u6218\uff1a\u4ece\u5165\u95e8\u5230\u7cbe\u901a - Blog - Silicon Cloud","description":"\u5b66\u4e60\u5982\u4f55\u4f7f\u7528\u5f3a\u5927\u7684Scrapy\u6846\u67b6\u548cPython 3\u9ad8\u6548\u6293\u53d6\u7f51\u9875\u6570\u636e\u3002\u672c\u6559\u7a0b\u6db5\u76d6Scrapy\u5b89\u88c5\u3001\u9879\u76ee\u521b\u5efa\u3001\u9009\u62e9\u5668\u4f7f\u7528\u3001\u6570\u636e\u5b58\u50a8\u7b49\u6838\u5fc3\u77e5\u8bc6\uff0c\u52a9\u4f60\u5feb\u901f\u638c\u63e1\u7f51\u9875\u722c\u53d6\u6280\u672f\uff0c\u8f7b\u677e\u5b9e\u73b0\u6570\u636e\u81ea\u52a8\u5316\u91c7\u96c6\u3002","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.silicloud.com\/zh\/blog\/\u5982\u4f55\u4f7f\u7528scrapy\u548cpython-3\u6293\u53d6\u7f51\u9875\/","og_locale":"zh_CN","og_type":"article","og_title":"Scrapy\u4e0ePython 3\u7f51\u9875\u6293\u53d6\u5b9e\u6218\uff1a\u4ece\u5165\u95e8\u5230\u7cbe\u901a","og_description":"\u5b66\u4e60\u5982\u4f55\u4f7f\u7528\u5f3a\u5927\u7684Scrapy\u6846\u67b6\u548cPython 3\u9ad8\u6548\u6293\u53d6\u7f51\u9875\u6570\u636e\u3002\u672c\u6559\u7a0b\u6db5\u76d6Scrapy\u5b89\u88c5\u3001\u9879\u76ee\u521b\u5efa\u3001\u9009\u62e9\u5668\u4f7f\u7528\u3001\u6570\u636e\u5b58\u50a8\u7b49\u6838\u5fc3\u77e5\u8bc6\uff0c\u52a9\u4f60\u5feb\u901f\u638c\u63e1\u7f51\u9875\u722c\u53d6\u6280\u672f\uff0c\u8f7b\u677e\u5b9e\u73b0\u6570\u636e\u81ea\u52a8\u5316\u91c7\u96c6\u3002","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/\u5982\u4f55\u4f7f\u7528scrapy\u548cpython-3\u6293\u53d6\u7f51\u9875\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2023-11-10T13:21:46+00:00","article_modified_time":"2025-07-31T14:30:33+00:00","author":"\u6e05, \u626c","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u6e05, \u626c","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"2 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/","name":"Scrapy\u4e0ePython 3\u7f51\u9875\u6293\u53d6\u5b9e\u6218\uff1a\u4ece\u5165\u95e8\u5230\u7cbe\u901a - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2023-11-10T13:21:46+00:00","dateModified":"2025-07-31T14:30:33+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/cb5556d2501da73d864cac945e8d9461"},"description":"\u5b66\u4e60\u5982\u4f55\u4f7f\u7528\u5f3a\u5927\u7684Scrapy\u6846\u67b6\u548cPython 3\u9ad8\u6548\u6293\u53d6\u7f51\u9875\u6570\u636e\u3002\u672c\u6559\u7a0b\u6db5\u76d6Scrapy\u5b89\u88c5\u3001\u9879\u76ee\u521b\u5efa\u3001\u9009\u62e9\u5668\u4f7f\u7528\u3001\u6570\u636e\u5b58\u50a8\u7b49\u6838\u5fc3\u77e5\u8bc6\uff0c\u52a9\u4f60\u5feb\u901f\u638c\u63e1\u7f51\u9875\u722c\u53d6\u6280\u672f\uff0c\u8f7b\u677e\u5b9e\u73b0\u6570\u636e\u81ea\u52a8\u5316\u91c7\u96c6\u3002","breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"Scrapy\u4e0ePython 3\u7f51\u9875\u6293\u53d6\u5b9e\u6218\uff1a\u4ece\u5165\u95e8\u5230\u7cbe\u901a"}]},{"@type":"WebSite","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website","url":"https:\/\/www.silicloud.com\/zh\/blog\/","name":"Blog - Silicon Cloud","description":"","inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/cb5556d2501da73d864cac945e8d9461","name":"\u6e05, \u626c","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g","caption":"\u6e05, \u626c"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/qingyang\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8scrapy%e5%92%8cpython-3%e6%8a%93%e5%8f%96%e7%bd%91%e9%a1%b5\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/77","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/users\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=77"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/77\/revisions"}],"predecessor-version":[{"id":109540,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/77\/revisions\/109540"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=77"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=77"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=77"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}