{"id":106,"date":"2026-08-06T00:30:17","date_gmt":"2026-08-05T16:30:17","guid":{"rendered":"https:\/\/ltrainyard.icu\/?p=106"},"modified":"2026-08-06T00:44:58","modified_gmt":"2026-08-05T16:44:58","slug":"day-20-%e7%ac%ac%e4%b8%89%e6%96%b9%e5%ba%93%ef%bc%9apip-venv-requests-beautifulsoup","status":"publish","type":"post","link":"https:\/\/ltrainyard.icu\/index.php\/2026\/08\/06\/day-20-%e7%ac%ac%e4%b8%89%e6%96%b9%e5%ba%93%ef%bc%9apip-venv-requests-beautifulsoup\/","title":{"rendered":"| Day 20 | \u7b2c\u4e09\u65b9\u5e93\uff1apip \/ venv \/ requests \/ BeautifulSoup |"},"content":{"rendered":"\n<h3 class=\"wp-block-heading\">1 pip \u2014\u2014 \u7b2c\u4e09\u65b9\u5e93\u7684\u300c\u5b89\u88c5\u7ba1\u5bb6\u300d<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u662f\u4ec0\u4e48\uff1f\u4e3a\u4ec0\u4e48\u5b66\uff1f<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>pip<\/strong> \u662f Python \u81ea\u5e26\u7684\u5305\u7ba1\u7406\u5de5\u5177\uff0c\u4ece <strong>PyPI<\/strong>\uff08Python Package Index\uff0cPython \u5b98\u65b9\u8f6f\u4ef6\u4ed3\u5e93\uff0c\u5168\u7403\u5f00\u53d1\u8005\u5171\u4eab\u4ee3\u7801\u7684\u5730\u65b9\uff09\u4e0b\u8f7d\u5e76\u5b89\u88c5\u7b2c\u4e09\u65b9\u5e93\u3002\u6807\u51c6\u5e93\u4e4b\u5916\u7684\u597d\u4e1c\u897f\u2014\u2014\u7f51\u9875\u8bf7\u6c42\u3001\u6570\u636e\u5206\u6790\u3001\u56fe\u50cf\u5904\u7406\u2014\u2014\u51e0\u4e4e\u90fd\u9760 <code>pip install<\/code> \u88c5\u8fdb\u73af\u5883\u3002\u6807\u51c6\u5e93\u662f\u300c\u81ea\u5e26\u5de5\u5177\u7bb1\u300d\uff0c\u800c<strong>\u7b2c\u4e09\u65b9\u5e93<\/strong>\u662f\u5168\u4e16\u754c\u5f00\u53d1\u8005\u5206\u4eab\u7684\u300c\u8d85\u7ea7\u5de5\u5177\u7bb1\u300d\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u5e95\u5c42\u539f\u7406<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><code>pip install requests<\/code> \u505a\u7684\u4e8b\u60c5\uff1a\u2460 \u5728 PyPI \u4ed3\u5e93\u91cc\u67e5\u627e\u540d\u4e3a <code>requests<\/code> \u7684\u5305\uff08\u540c\u65f6\u89e3\u6790\u5b83\u7684<strong>\u4f9d\u8d56<\/strong>\uff0c\u6bd4\u5982\u5b83\u4f9d\u8d56\u7684 <code>urllib3<\/code>\u3001<code>certifi<\/code>\uff09\uff1b\u2461 \u4e0b\u8f7d\u5bf9\u5e94\u4f60 Python \u7248\u672c\u7684\u6587\u4ef6\uff08\u901a\u5e38\u662f <code>.whl<\/code> \u8f6e\u5b50\u683c\u5f0f\uff0c\u5373\u9884\u7f16\u8bd1\u597d\u7684\u5b89\u88c5\u5305\uff09\uff1b\u2462 \u89e3\u538b\u5230\u5f53\u524d\u73af\u5883\u7684 <code>site-packages<\/code> \u76ee\u5f55\u3002<strong>\u5173\u952e\u70b9\uff1a<code>pip<\/code> \u88c5\u5230\u300c\u54ea\u4e2a\u73af\u5883\u300d\uff0c\u53d6\u51b3\u4e8e\u4f60\u7528\u54ea\u4e2a <code>python<\/code> \u547d\u4ee4<\/strong>\u2014\u2014\u6240\u4ee5\u7a33\u59a5\u5199\u6cd5\u662f <code>python -m pip<\/code>\uff08\u7528\u5f53\u524d python \u89e3\u91ca\u5668\u53bb\u8c03 pip\uff0c\u4fdd\u8bc1\u88c5\u8fdb\u540c\u4e00\u4e2a\u73af\u5883\uff09\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u751f\u6d3b\u7c7b\u6bd4<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">pip \u50cf<strong>\u624b\u673a\u5e94\u7528\u5546\u5e97<\/strong>\uff1aPyPI \u662f\u5546\u5e97\uff0c<code>pip install<\/code> \u662f\u300c\u70b9\u51fb\u5b89\u88c5\u300d\uff0c<code>pip list<\/code> \u662f\u300c\u5df2\u88c5\u5e94\u7528\u5217\u8868\u300d\uff0c<code>pip uninstall<\/code> \u662f\u300c\u5378\u8f7d\u300d\u3002<code>python -m pip<\/code> \u76f8\u5f53\u4e8e\u300c\u5148\u786e\u8ba4\u662f\u8fd9\u53f0\u624b\u673a\u518d\u5b89\u88c5\u300d\u2014\u2014\u907f\u514d\u88c5\u9519\u8bbe\u5907\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6ce8\u610f\u4e8b\u9879\u603b\u7ed3<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">1 <strong>\u67e5\u770b pip \u7248\u672c\u4e0e\u5df2\u5b89\u88c5\u5217\u8868<\/strong>\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>python -m pip --version\npython -m pip list\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u8fd0\u884c\u7ed3\u679c\uff08\u7248\u672c\u53f7\u4ee5\u5b9e\u9645\u4e3a\u51c6\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>pip 25.3 from C:\\...\\site-packages\\pip (python 3.14)\nPackage        Version\n------------- ---------\nbeautifulsoup4 4.15.0 \/ requests 2.34.2\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><code>python -m pip --version<\/code> \u6253\u5370 pip \u7248\u672c\uff08**<code>python -m<\/code> \u4fdd\u8bc1\u7528\u7684\u662f\u5f53\u524d\u89e3\u91ca\u5668**\uff09\uff1b<code>pip list<\/code> \u5217\u51fa\u5f53\u524d\u73af\u5883\u6240\u6709\u5df2\u88c5\u5305\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">2 <strong>\u5b89\u88c5 \/ \u67e5\u770b\u8be6\u60c5 \/ \u5378\u8f7d<\/strong>\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>python -m pip install requests beautifulsoup4      # \u5b89\u88c5\npython -m pip show requests                        # \u67e5\u770b\u8be6\u60c5\npython -m pip uninstall requests                   # \u5378\u8f7d\uff08\u4f1a\u4e8c\u6b21\u786e\u8ba4\uff09\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u8fd0\u884c\u7ed3\u679c\uff08\u5b89\u88c5\u6210\u529f\u7684\u5178\u578b\u8f93\u51fa\u7247\u6bb5\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>Collecting requests ... Successfully installed requests-2.32.3\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">3 <strong>\u56fd\u5185\u7f51\u7edc\u6162\u52a0\u955c\u50cf\u6e90<\/strong>\uff1a<code>python -m pip install requests -i https:\/\/pypi.tuna.tsinghua.edu.cn\/simple<\/code>\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6613\u9519\u70b9<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u76f4\u63a5\u6572 <code>pip install requests<\/code> \u2192 \u95ee\u9898\uff1a\u591a\u4e2a Python \u65f6\u53ef\u80fd\u88c5\u8fdb\u522b\u7684\u7248\u672c\uff0c<code>import<\/code> \u4f9d\u7136\u62a5\u9519 \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u7528 <code>python -m pip install<\/code> \u7ed1\u5b9a\u5f53\u524d\u89e3\u91ca\u5668\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1a<code>import requests<\/code> \u62a5 <code>ModuleNotFoundError<\/code> \u5374\u4e0d\u53bb\u88c5 \u2192 \u95ee\u9898\uff1a\u7b2c\u4e09\u65b9\u5e93\u5fc5\u987b\u663e\u5f0f\u5b89\u88c5\uff0c\u4e0d\u50cf\u6807\u51c6\u5e93\u81ea\u5e26 \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u5148 <code>python -m pip install requests<\/code>\u3002<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u8bb0\u5fc6\u53e3\u8bc0<\/strong>\uff1apip \u662f\u7ba1\u5bb6\uff0cPyPI \u662f\u4ed3\u5e93\uff1bpython -m pip \u6700\u7a33\u59a5\uff0c\u88c5\u5b8c import \u624d\u4e0d\u614c\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">2 \u865a\u62df\u73af\u5883 venv \u2014\u2014 \u6bcf\u4e2a\u9879\u76ee\u4e00\u4e2a\u300c\u72ec\u7acb\u623f\u95f4\u300d<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u662f\u4ec0\u4e48\uff1f\u4e3a\u4ec0\u4e48\u5b66\uff1f<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u865a\u62df\u73af\u5883<\/strong>\uff08virtual environment\uff09\u662f Python \u4e3a\u6bcf\u4e2a\u9879\u76ee\u521b\u5efa\u7684\u4e00\u5957<strong>\u72ec\u7acb\u9694\u79bb<\/strong>\u7684\u89e3\u91ca\u5668 + \u5e93\u76ee\u5f55\u3002\u9879\u76ee A \u9700\u8981 <code>requests 2.x<\/code>\u3001\u9879\u76ee B \u9700\u8981 <code>requests 1.x<\/code>\uff0c\u5168\u88c5\u5168\u5c40\u4f1a\u4e92\u76f8\u6253\u67b6\uff1b\u865a\u62df\u73af\u5883\u8ba9\u6bcf\u4e2a\u9879\u76ee\u6709\u81ea\u5df1\u7684\u5e93\uff0c\u4e92\u4e0d\u5f71\u54cd\u3002\u56e2\u961f\u5f00\u53d1\u3001\u90e8\u7f72\u4e0a\u7ebf\u65f6\uff0c\u8fd9\u662f\u6807\u51c6\u64cd\u4f5c\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u5e95\u5c42\u539f\u7406<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><code>python -m venv venv<\/code> \u5728\u5f53\u524d\u76ee\u5f55\u751f\u6210 <code>venv<\/code> \u6587\u4ef6\u5939\uff1a<strong>\u4e00\u4efd\u89e3\u91ca\u5668\u5165\u53e3<\/strong>\uff08Windows \u662f <code>venv\\Scripts\\python.exe<\/code>\uff09+ \u72ec\u7acb\u7684 <code>site-packages<\/code> \u76ee\u5f55\u3002\u6fc0\u6d3b\uff08<code>venv\\Scripts\\activate<\/code>\uff09\u7684\u672c\u8d28\u662f<strong>\u4fee\u6539\u73af\u5883\u53d8\u91cf <code>PATH<\/code><strong>\uff0c\u8ba9 <code>python<\/code> \/ <code>pip<\/code> \u4f18\u5148\u6307\u5411\u8fd9\u4e2a\u6587\u4ef6\u5939\uff1b\u9000\u51fa\uff08<code>deactivate<\/code>\uff09\u5219\u6062\u590d PATH\u3002<\/strong>\u9694\u79bb\u7684\u771f\u76f8\uff1a\u8def\u5f84\u6307\u5411\u4e0d\u540c\uff0c\u88c5\u7684\u5e93\u5404\u5f52\u5404\u5bb6<\/strong>\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u751f\u6d3b\u7c7b\u6bd4<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u865a\u62df\u73af\u5883\u50cf<strong>\u9152\u5e97\u623f\u95f4<\/strong>\uff1a\u6bcf\u4e2a\u9879\u76ee\u4f4f\u4e00\u95f4\uff0c\u623f\u5185\u7269\u54c1\uff08\u4f9d\u8d56\u5e93\uff09\u53ea\u5c5e\u4e8e\u8fd9\u95f4\u623f\uff1b\u9000\u623f\uff08deactivate\uff09\u540e\u4e92\u4e0d\u5f71\u54cd\u3002\u5168\u5c40\u73af\u5883\u50cf<strong>\u5927\u5bbf\u820d<\/strong>\uff0c\u8c01\u90fd\u80fd\u5f80\u91cc\u653e\u4e1c\u897f\uff0c\u4e92\u76f8\u4e32\u5473\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6ce8\u610f\u4e8b\u9879\u603b\u7ed3<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">1 <strong>\u521b\u5efa + \u6fc0\u6d3b + \u9000\u51fa<\/strong>\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>python -m venv venv        # 1. \u521b\u5efa\u865a\u62df\u73af\u5883\uff08\u751f\u6210 venv \u6587\u4ef6\u5939\uff09\nvenv\\Scripts\\activate      # 2. \u6fc0\u6d3b\uff08Windows\uff1bmacOS\/Linux \u7528 source venv\/bin\/activate\uff09\npip list                   # 3. \u6fc0\u6d3b\u540e\u770b\u5230\u7684\u662f\u8fd9\u4e2a\u73af\u5883\u81ea\u5df1\u7684\u5305\ndeactivate                 # 4. \u9000\u51fa\u73af\u5883\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u8fd0\u884c\u6548\u679c\uff08\u6fc0\u6d3b\u540e\u63d0\u793a\u7b26\u524d\u51fa\u73b0 <code>(venv)<\/code>\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>(venv) C:\\project&gt; pip list\nPackage    Version\n--------- -------\npip        25.3\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><code>python -m venv venv<\/code> \u521b\u5efa\u9694\u79bb\u73af\u5883\uff08\u53ea\u9700\u4e00\u6b21\uff09\uff1b<code>venv\\Scripts\\activate<\/code> \u6fc0\u6d3b\u540e\uff0c**\u63d0\u793a\u7b26\u524d\u9762\u51fa\u73b0 <code>(venv)<\/code>**\uff0c\u6b64\u65f6 <code>pip install<\/code> \u88c5\u7684\u5e93\u53ea\u5c5e\u4e8e\u8fd9\u4e2a\u9879\u76ee\uff1b<code>deactivate<\/code> \u9000\u51fa\u56de\u5230\u5168\u5c40\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">2 <strong>\u4e0d\u6fc0\u6d3b\u4e5f\u80fd\u7528\u2014\u2014\u76f4\u63a5\u8c03 venv \u91cc\u7684 python<\/strong>\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>venv\\Scripts\\python.exe -m pip --version\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u8fd0\u884c\u7ed3\u679c\uff1a<code>pip 25.3 from C:\\project\\venv\\Lib\\site-packages\\pip (python 3.14)<\/code>\n\u6ce8\u610f\u8def\u5f84\u91cc\u7684 <code>venv\\Lib\\site-packages<\/code>\u2014\u2014\u8fd9\u4e2a pip \u5c5e\u4e8e venv \u81ea\u5df1\u7684\u76ee\u5f55\u3002<strong>\u4e0d\u6fc0\u6d3b\u65f6\uff0c\u76f4\u63a5\u7528 <code>venv\\Scripts\\python.exe<\/code> \u4e5f\u80fd\u4eab\u53d7\u9694\u79bb\u73af\u5883<\/strong>\uff0c\u811a\u672c\u81ea\u52a8\u5316\uff08\u5b9a\u65f6\u4efb\u52a1\uff09\u5e38\u7528\u8fd9\u62db\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6613\u9519\u70b9<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u5fd8\u6fc0\u6d3b\u5c31\u76f4\u63a5 <code>pip install<\/code> \u2192 \u95ee\u9898\uff1a\u88c5\u8fdb\u4e86\u5168\u5c40\u73af\u5883\uff0c\u9879\u76ee\u91cc import \u4e0d\u5230 \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u5148 <code>venv\\Scripts\\activate<\/code> \u770b\u5230 <code>(venv)<\/code> \u518d\u88c5\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u628a <code>venv<\/code> \u6587\u4ef6\u5939\u63d0\u4ea4\u5230 git \/ \u53d1\u7ed9\u522b\u4eba \u2192 \u95ee\u9898\uff1a\u4f53\u79ef\u5927\u4e14\u542b\u672c\u673a\u7edd\u5bf9\u8def\u5f84\uff0c\u6362\u7535\u8111\u5c31\u5e9f \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u53ea\u63d0\u4ea4 <code>requirements.txt<\/code>\uff0c\u522b\u4eba <code>pip install -r<\/code> \u91cd\u5efa\u3002<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u8bb0\u5fc6\u53e3\u8bc0<\/strong>\uff1a\u4e00\u4e2a\u9879\u76ee\u4e00\u95f4\u623f\uff0cvenv \u5efa\u597d\u518d\u88c5\u5e93\uff1b\u63d0\u793a\u7b26\u5e26 (venv)\uff0cdeactivate \u9000\u623f\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">3 requests \u2014\u2014 \u7528\u51e0\u884c\u4ee3\u7801\u300c\u8bbf\u95ee\u300d\u7f51\u9875<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u662f\u4ec0\u4e48\uff1f\u4e3a\u4ec0\u4e48\u5b66\uff1f<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>requests<\/strong> \u662f Python \u6700\u6d41\u884c\u7684 HTTP \u8bf7\u6c42\u5e93\uff0c\u5c01\u88c5\u4e86\u7f51\u7edc\u534f\u8bae\u7ec6\u8282\uff0c\u8ba9\u300c\u8bbf\u95ee\u4e00\u4e2a\u7f51\u5740\u300d\u53d8\u6210\u4e00\u884c <code>requests.get(url)<\/code>\u3002\u6293\u7f51\u9875\u3001\u8c03 API\uff08\u5929\u6c14\u3001\u5730\u56fe\u3001\u7ffb\u8bd1\u63a5\u53e3\uff09\u90fd\u662f\u53d1 HTTP \u8bf7\u6c42\uff0crequests \u662f\u6807\u914d\u3002\u81ea\u5df1\u7528\u6807\u51c6\u5e93 <code>urllib<\/code> \u5199\u8981\u5904\u7406\u7f16\u7801\u3001\u91cd\u5b9a\u5411\u3001\u8d85\u65f6\u7b49\u4e00\u5806\u7ec6\u8282\uff0crequests \u5168\u90e8\u4ee3\u52b3\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u5e95\u5c42\u539f\u7406<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><code>requests.get(url)<\/code> \u5185\u90e8\u53d1\u4e00\u6b21 <strong>HTTP GET \u8bf7\u6c42<\/strong>\uff1a\u5efa\u7acb\u8fde\u63a5\uff08\u57fa\u4e8e <code>urllib3<\/code>\uff09\u2192 \u53d1\u9001\u8bf7\u6c42\u5934 \u2192 \u670d\u52a1\u5668\u8fd4\u56de\u54cd\u5e94 \u2192 \u5c01\u88c5\u6210 <code>Response<\/code> \u5bf9\u8c61\u3002\u5bf9\u8c61\u91cc\u6709\uff1a<code>status_code<\/code>\uff08<code>200<\/code> \u6210\u529f\u3001<code>404<\/code> \u4e0d\u5b58\u5728\u3001<code>403<\/code> \u62d2\u7edd\uff09\u3001<code>text<\/code>\uff08\u7f51\u9875\u6587\u672c\uff09\u3001<code>headers<\/code>\uff08\u54cd\u5e94\u5934\uff09\u3001<code>encoding<\/code>\uff08\u7f16\u7801\uff09\u3002<strong>\u5173\u952e\u70b9\uff1a\u7f51\u7edc\u8bf7\u6c42\u53ef\u80fd\u5931\u8d25\uff08\u65ad\u7f51\u3001\u8d85\u65f6\u3001\u88ab\u53cd\u722c\uff09\uff0c\u8981\u7528 <code>try\/except<\/code> \u5305\u4f4f<\/strong>\uff0c\u522b\u8ba9\u7a0b\u5e8f\u56e0\u4e00\u6b21\u7f51\u7edc\u6296\u52a8\u5d29\u6e83\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u751f\u6d3b\u7c7b\u6bd4<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">requests \u50cf<strong>\u6253\u7535\u8bdd<\/strong>\uff1a<code>requests.get(url)<\/code> \u662f\u300c\u62e8\u53f7 + \u95ee\u4e00\u53e5\u8bdd\u300d\uff0c<code>Response<\/code> \u662f\u300c\u5bf9\u65b9\u7b54\u590d\u300d\u2014\u2014\u5148\u542c\u8bed\u6c14\uff08200 \u662f\u300c\u597d\u7684\u300d\uff0c404 \u662f\u300c\u6ca1\u8fd9\u4eba\u300d\uff09\uff0c\u518d\u542c\u5185\u5bb9\uff08<code>resp.text<\/code>\uff09\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6ce8\u610f\u4e8b\u9879\u603b\u7ed3<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">1 <strong>\u8bf7\u6c42\u7f51\u9875\uff0c\u770b\u72b6\u6001\u7801\u548c\u5185\u5bb9<\/strong>\uff08\u9700\u8981\u8054\u7f51\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>import requests\n\nresp = requests.get(\"https:\/\/example.com\")\nprint(\"\u72b6\u6001\u7801:\", resp.status_code)\nprint(\"\u7f16\u7801:\", resp.encoding)\nprint(\"\u7f51\u9875\u6587\u672c\u524d 120 \u5b57\u7b26:\")\nprint(resp.text&#91;:120])\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u793a\u4f8b\u8f93\u51fa\uff08\u8054\u7f51\u8fd0\u884c\u65f6\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>\u72b6\u6001\u7801: 200\n\u7f16\u7801: ISO-8859-1\n\u7f51\u9875\u6587\u672c\u524d 120 \u5b57\u7b26: &lt;!doctype html&gt;&lt;html lang=\"en\"&gt;&lt;head&gt;&lt;title&gt;Example Domain...\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><code>requests.get(...)<\/code> \u53d1\u8bf7\u6c42\u8fd4\u56de\u54cd\u5e94\u5bf9\u8c61\uff1b<code>resp.status_code<\/code> \u5224\u65ad\u6210\u529f\u4e0e\u5426\uff1b<code>resp.text[:120]<\/code> \u53d6\u7f51\u9875\u6e90\u7801\u524d 120 \u5b57\u7b26\u2014\u2014\u8fd9\u5c31\u662f HTML \u5b57\u7b26\u4e32\uff0c\u4e0b\u4e00\u6b65\u4ea4\u7ed9 BeautifulSoup \u89e3\u6790\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">2 <strong>\u5e26\u6d4f\u89c8\u5668\u6807\u8bc6 + \u5f02\u5e38\u5904\u7406\uff08\u65ad\u7f51\u4e5f\u4e0d\u5d29\u6e83\uff09<\/strong>\uff08\u9700\u8981\u8054\u7f51\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>import requests\n\nheaders = {\"User-Agent\": \"Mozilla\/5.0 (Windows NT 10.0; Win64; x64)\"}\ntry:\n    resp = requests.get(\"https:\/\/example.com\", headers=headers, timeout=10)\n    resp.raise_for_status()          # \u72b6\u6001\u7801\u975e 200 \u65f6\u629b\u51fa\u5f02\u5e38\n    print(\"\u8bf7\u6c42\u6210\u529f\uff0c\u72b6\u6001\u7801:\", resp.status_code)\nexcept requests.RequestException as e:\n    print(\"\u8bf7\u6c42\u5931\u8d25:\", e)\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><code>headers<\/code> \u5e26\u4e0a\u6d4f\u89c8\u5668\u6807\u8bc6\uff08User-Agent\uff09\u51cf\u5c11\u88ab\u62d2\u6982\u7387\uff1b<code>timeout=10<\/code> \u8bbe\u8d85\u65f6\u9632\u6b62\u65e0\u9650\u7b49\u5f85\uff1b<code>raise_for_status()<\/code> \u5728\u72b6\u6001\u7801\u975e 200 \u65f6\u629b\u5f02\u5e38\uff1b<code>except requests.RequestException<\/code> \u63a5\u4f4f\u6240\u6709\u8bf7\u6c42\u7c7b\u5f02\u5e38\uff08\u65ad\u7f51\u3001\u8d85\u65f6\u3001404 \u90fd\u7b97\uff09\u2014\u2014<strong>\u7f51\u7edc\u4e0d\u53ef\u63a7\uff0c\u5fc5\u987b\u515c\u5e95<\/strong>\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">3 <strong>\u4e2d\u6587\u4e71\u7801\u5148\u67e5\u7f16\u7801<\/strong>\uff1a<code>resp.encoding = \"utf-8\"<\/code> \u6216 <code>resp.encoding = resp.apparent_encoding<\/code>\uff08\u81ea\u52a8\u63a8\u65ad\uff09\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6613\u9519\u70b9<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u4e0d\u5199 <code>timeout<\/code> \u2192 \u95ee\u9898\uff1a\u670d\u52a1\u5668\u4e0d\u54cd\u5e94\u65f6\u7a0b\u5e8f\u65e0\u9650\u5361\u4f4f \u2192 \u6b63\u786e\u5199\u6cd5\uff1a<code>requests.get(url, timeout=10)<\/code>\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u4e0d\u5199 <code>try\/except<\/code> \u2192 \u95ee\u9898\uff1a\u65ad\u7f51\u6216\u8d85\u65f6\u76f4\u63a5\u629b\u5f02\u5e38\u5d29\u6e83 \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u7528 <code>except requests.RequestException<\/code> \u515c\u5e95\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1aURL \u5fd8\u4e86 <code>https:\/\/<\/code> \u2192 \u95ee\u9898\uff1a\u62a5 <code>InvalidURL<\/code> \/ <code>MissingSchema<\/code> \u2192 \u6b63\u786e\u5199\u6cd5\uff1aURL \u5199\u5168\uff1a<code>https:\/\/example.com<\/code>\u3002<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u8bb0\u5fc6\u53e3\u8bc0<\/strong>\uff1aget \u662f\u6253\u7535\u8bdd\uff0cresp \u662f\u7b54\u590d\uff1b200 \u662f\u6210\u529f\uff0c404 \u6ca1\u4eba\u63a5\uff1b\u8d85\u65f6\u515c\u5e95\u522b\u5fd8 try\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">4 BeautifulSoup \u2014\u2014 \u628a HTML \u53d8\u6210\u300c\u5bf9\u8c61\u6811\u300d<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u662f\u4ec0\u4e48\uff1f\u4e3a\u4ec0\u4e48\u5b66\uff1f<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>beautifulsoup4\uff08bs4\uff09<\/strong>\u662f\u89e3\u6790 HTML\/XML \u7684\u5e93\u3002\u7f51\u9875\u6e90\u7801\u662f\u4e00\u5927\u5768\u5b57\u7b26\u4e32\uff0c\u76f4\u63a5 <code>find<\/code> \/ \u5207\u7247\u63d0\u53d6\u975e\u5e38\u75db\u82e6\uff1bBeautifulSoup \u628a HTML <strong>\u89e3\u6790\u6210\u4e00\u68f5\u6811<\/strong>\uff08\u6807\u7b7e\u5d4c\u5957\u7ed3\u6784\uff09\uff0c\u7136\u540e\u5c31\u80fd\u7528\u300c\u627e\u6807\u7b7e\u300d\u7684\u65b9\u5f0f\u53d6\u5185\u5bb9\u3002\u914d\u5408 requests \u5c31\u662f\u5b8c\u6574\u7684\u300c\u6293\u53d6 + \u89e3\u6790\u300d\u94fe\u8def\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u5e95\u5c42\u539f\u7406<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><code>BeautifulSoup(html, \"html.parser\")<\/code> \u7528\u89e3\u6790\u5668\u628a HTML \u5b57\u7b26\u4e32\u53d8\u6210\u4e00\u68f5<strong>\u5bf9\u8c61\u6811<\/strong>\uff1a\u6bcf\u4e2a\u6807\u7b7e\u662f\u4e00\u4e2a <code>Tag<\/code> \u5bf9\u8c61\uff0c\u6807\u7b7e\u4e4b\u95f4\u662f\u7236\u5b50\/\u5144\u5f1f\u5173\u7cfb\u3002\u7136\u540e\uff1a<code>soup.h1<\/code> \u53d6\u7b2c\u4e00\u4e2a <code>h1<\/code>\u3001<code>soup.find(\"p\", class_=\"temp\")<\/code> \u6309\u6807\u7b7e + \u5c5e\u6027\u627e\u3001<code>soup.find_all(\"a\")<\/code> \u627e<strong>\u6240\u6709<\/strong> <code>a<\/code>\u3001<code>tag.text<\/code> \u53d6\u6587\u672c\u3001<code>tag[\"href\"]<\/code> \u53d6\u5c5e\u6027\u3001<code>soup.select(\".news h2\")<\/code> \u7528 CSS \u9009\u62e9\u5668\u3002**\u6ce8\u610f <code>class<\/code> \u662f Python \u5173\u952e\u5b57\uff0c\u6240\u4ee5\u7528 <code>class_<\/code>**\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u751f\u6d3b\u7c7b\u6bd4<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">BeautifulSoup \u50cf<strong>\u6863\u6848\u7ba1\u7406\u5458<\/strong>\uff1aHTML \u662f\u4e00\u5806\u6742\u4e71\u7684\u7eb8\uff08\u5b57\u7b26\u4e32\uff09\uff0c\u7ba1\u7406\u5458\u6309\u76ee\u5f55\u6574\u7406\u6210\u6863\u6848\u67dc\uff08\u5bf9\u8c61\u6811\uff09\u2014\u2014\u627e\u300c\u6240\u6709\u6807\u9898\u300d\u67e5 <code>find_all(\"h2\")<\/code>\uff0c\u627e\u300c\u6b63\u6587\u7b2c\u4e00\u6bb5\u300d\u67e5 <code>find(\"p\")<\/code>\uff0c\u51e0\u79d2\u641e\u5b9a\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6ce8\u610f\u4e8b\u9879\u603b\u7ed3<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">1 <strong>\u89e3\u6790\u672c\u5730 HTML \u5b57\u7b26\u4e32\uff0c\u63d0\u53d6\u6807\u9898\/\u6bb5\u843d\/\u94fe\u63a5<\/strong>\uff08\u79bb\u7ebf\u53ef\u8dd1\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from bs4 import BeautifulSoup\n\nhtml = \"\"\"\n&lt;html&gt;&lt;body&gt;\n&lt;h1&gt;\u4eca\u65e5\u5929\u6c14&lt;\/h1&gt;\n&lt;p class=\"temp\"&gt;28 \u5ea6&lt;\/p&gt;\n&lt;p class=\"desc\"&gt;\u591a\u4e91\u8f6c\u6674&lt;\/p&gt;\n&lt;a href=\"\/detail\"&gt;\u67e5\u770b\u8be6\u60c5&lt;\/a&gt;\n&lt;\/body&gt;&lt;\/html&gt;\n\"\"\"\n\nsoup = BeautifulSoup(html, \"html.parser\")\nprint(\"h1 \u6587\u672c:\", soup.h1.text)\nprint(\"temp:\", soup.find(\"p\", class_=\"temp\").text)\nprint(\"\u94fe\u63a5:\", soup.a&#91;\"href\"], \"|\", soup.a.text)\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u8fd0\u884c\u7ed3\u679c\uff08\u79bb\u7ebf\u53ef\u590d\u73b0\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>h1 \u6587\u672c: \u4eca\u65e5\u5929\u6c14\ntemp: 28 \u5ea6\n\u94fe\u63a5: \/detail | \u67e5\u770b\u8be6\u60c5\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><code>BeautifulSoup(html, \"html.parser\")<\/code> \u628a\u5b57\u7b26\u4e32\u89e3\u6790\u6210\u5bf9\u8c61\u6811\uff1b<code>soup.h1.text<\/code> \u53d6\u7b2c\u4e00\u4e2a <code>h1<\/code> \u7684\u6587\u672c\uff1b<code>soup.find(\"p\", class_=\"temp\")<\/code> \u6309\u6807\u7b7e\u548c class \u627e\uff08**<code>class_<\/code> \u5e26\u4e0b\u5212\u7ebf**\uff09\uff1b<code>soup.a[\"href\"]<\/code> \u53d6 <code>a<\/code> \u7684 <code>href<\/code> \u5c5e\u6027\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">2 <strong>find_all \u6279\u91cf\u63d0\u53d6 + CSS \u9009\u62e9\u5668 + \u5d4c\u5957\u8868\u683c<\/strong>\uff08\u79bb\u7ebf\u53ef\u8dd1\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from bs4 import BeautifulSoup\n\nhtml = \"\"\"\n&lt;ul&gt;\n  &lt;li&gt;\u82f9\u679c&lt;\/li&gt;\n  &lt;li&gt;\u9999\u8549&lt;\/li&gt;\n  &lt;li&gt;\u68a8&lt;\/li&gt;\n&lt;\/ul&gt;\n&lt;table&gt;\n  &lt;tr&gt;&lt;th&gt;\u6c34\u679c&lt;\/th&gt;&lt;th&gt;\u4ef7\u683c&lt;\/th&gt;&lt;\/tr&gt;\n  &lt;tr&gt;&lt;td&gt;\u82f9\u679c&lt;\/td&gt;&lt;td&gt;5.5&lt;\/td&gt;&lt;\/tr&gt;\n  &lt;tr&gt;&lt;td&gt;\u9999\u8549&lt;\/td&gt;&lt;td&gt;3.0&lt;\/td&gt;&lt;\/tr&gt;\n&lt;\/table&gt;\n\"\"\"\n\nsoup = BeautifulSoup(html, \"html.parser\")\nitems = &#91;li.text for li in soup.find_all(\"li\")]      # \u5217\u8868\u63a8\u5bfc\u5f0f\u6279\u91cf\u53d6\u6587\u672c\nprint(\"\u6c34\u679c:\", items)\n\nrows = &#91;]\nfor tr in soup.find_all(\"tr\")&#91;1:]:                   # \u8df3\u8fc7\u8868\u5934\u884c\n    rows.append(&#91;td.text for td in tr.find_all(\"td\")])\nprint(\"\u8868\u683c:\", rows)\nprint(\"CSS \u9009\u62e9\u5668:\", &#91;h.text for h in soup.select(\"th\")])\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u8fd0\u884c\u7ed3\u679c\uff08\u79bb\u7ebf\u53ef\u590d\u73b0\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>\u6c34\u679c: &#91;'\u82f9\u679c', '\u9999\u8549', '\u68a8']\n\u8868\u683c: &#91;&#91;'\u82f9\u679c', '5.5'], &#91;'\u9999\u8549', '3.0']]\nCSS \u9009\u62e9\u5668: &#91;'\u6c34\u679c', '\u4ef7\u683c']\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><code>soup.find_all(\"li\")<\/code> \u914d\u5408\u5217\u8868\u63a8\u5bfc\u5f0f\u4e00\u6b21\u53d6\u5168\u90e8\u6587\u672c\u2014\u2014<strong>\u300c\u6279\u91cf\u63d0\u53d6\u300d\u5c31\u662f find_all + \u63a8\u5bfc\u5f0f<\/strong>\uff1b<code>soup.find_all(\"tr\")[1:]<\/code> \u8df3\u8fc7\u8868\u5934\u518d\u9010\u884c\u53d6 <code>td<\/code>\uff0c\u8fd9\u662f\u89e3\u6790\u8868\u683c\u7684\u6807\u51c6\u5957\u8def\uff08\u5148\u53d6\u884c\u518d\u53d6\u683c\uff09\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">3 <strong>requests + bs4 \u7ec4\u5408\u2014\u2014\u5b8c\u6574\u300c\u6293\u53d6 + \u89e3\u6790\u300d\u94fe\u8def<\/strong>\uff08\u9700\u8981\u8054\u7f51\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>import requests\nfrom bs4 import BeautifulSoup\n\nresp = requests.get(\"https:\/\/example.com\")\nsoup = BeautifulSoup(resp.text, \"html.parser\")\n\nprint(\"\u9875\u9762\u6807\u9898:\", soup.title.string)\nfor a in soup.find_all(\"a\"):\n    print(\"  \", a.get(\"href\"), \"-&gt;\", a.text)\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6613\u9519\u70b9<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u9519\u8bef\u5199\u6cd5\uff1a<code>soup.find(\"p\", class=\"temp\")<\/code> \u2192 \u95ee\u9898\uff1a<code>class<\/code> \u662f Python \u5173\u952e\u5b57\uff0c\u8bed\u6cd5\u62a5\u9519 \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u7528 <code>class_=\"temp\"<\/code>\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1a<code>soup.find(...)<\/code> \u6ca1\u627e\u5230\u5c31\u76f4\u63a5 <code>.text<\/code> \u2192 \u95ee\u9898\uff1a\u8fd4\u56de <code>None<\/code>\uff0c<code>None.text<\/code> \u62a5 <code>AttributeError<\/code> \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u5148\u5224\u65ad <code>if tag is not None:<\/code>\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u5fd8\u4e86 <code>html.parser<\/code> \u53c2\u6570\uff1a<code>BeautifulSoup(html)<\/code> \u2192 \u95ee\u9898\uff1a\u544a\u8b66\u300c\u672a\u6307\u5b9a\u89e3\u6790\u5668\u300d\uff0c\u884c\u4e3a\u4e0d\u786e\u5b9a \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u663e\u5f0f\u5199 <code>BeautifulSoup(html, \"html.parser\")<\/code>\u3002<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u8bb0\u5fc6\u53e3\u8bc0<\/strong>\uff1aBeautifulSoup \u5efa\u6863\u6848\uff0cfind \u4e00\u4e2a find_all \u4e00\u5806\uff1bclass \u52a0\u4e0b\u5212\u7ebf\uff0ctext \u53d6\u6587\u672c\uff0cNone \u8981\u5148\u5224\u65ad\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">5 \u52a8\u624b\u5b9e\u8df5\uff1a\u8bf7\u6c42\u5e76\u89e3\u6790\u4e00\u4e2a\u7f51\u9875<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u505a\u4e00\u4e2a\u300c\u7f51\u9875\u4fe1\u606f\u63d0\u53d6\u5668\u300d\uff1a\u8bf7\u6c42 example.com\uff0c\u63d0\u53d6\u6807\u9898\u3001\u6b63\u6587\u7b2c\u4e00\u6bb5\u3001\u6240\u6709\u94fe\u63a5\uff0c\u5e76\u628a\u94fe\u63a5\u6574\u7406\u540e\u6253\u5370\u51fa\u6765\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># page_parser.py \u2014\u2014 \u8bf7\u6c42\u5e76\u89e3\u6790\u4e00\u4e2a\u7f51\u9875\nimport requests\nfrom bs4 import BeautifulSoup\n\n\ndef fetch_page(url):\n    \"\"\"\u8bf7\u6c42\u7f51\u9875\uff0c\u8fd4\u56de BeautifulSoup \u5bf9\u8c61\uff1b\u5931\u8d25\u8fd4\u56de None\"\"\"\n    try:\n        resp = requests.get(url, timeout=10)\n        resp.raise_for_status()     # \u72b6\u6001\u7801\u975e 200 \u65f6\u629b\u5f02\u5e38\n        resp.encoding = \"utf-8\"\n        return BeautifulSoup(resp.text, \"html.parser\")\n    except requests.RequestException as e:\n        print(\"\u8bf7\u6c42\u5931\u8d25:\", e)\n        return None\n\n\ndef show_page_info(url):\n    soup = fetch_page(url)\n    if soup is None:\n        return\n\n    print(\"=== \u9875\u9762\u6807\u9898 ===\")\n    print(soup.title.string if soup.title else \"\uff08\u65e0\u6807\u9898\uff09\")\n\n    print(\"\\n=== \u6b63\u6587\u7b2c\u4e00\u6bb5 ===\")\n    p = soup.find(\"p\")\n    print(p.text if p else \"\uff08\u65e0\u6bb5\u843d\uff09\")\n\n    print(\"\\n=== \u9875\u9762\u91cc\u7684\u94fe\u63a5 ===\")\n    links = soup.find_all(\"a\")\n    for i, a in enumerate(links, 1):\n        href = a.get(\"href\")\n        text = a.text.strip()\n        print(f\"{i}. {href} -&gt; {text}\")\n    print(f\"\\n\u5171\u627e\u5230 {len(links)} \u4e2a\u94fe\u63a5\")\n\n\nif __name__ == \"__main__\":\n    show_page_info(\"https:\/\/example.com\")\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u793a\u4f8b\u8f93\u51fa\uff08\u9700\u8981\u8054\u7f51\u8fd0\u884c\uff1b\u9875\u9762\u5185\u5bb9\u5982\u6709\u5fae\u8c03\u4e0d\u5f71\u54cd\u7406\u89e3\u7ed3\u6784\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>=== \u9875\u9762\u6807\u9898 ===\nExample Domain\n=== \u6b63\u6587\u7b2c\u4e00\u6bb5 ===\nThis domain is for use in documentation examples without needing permission.\n=== \u9875\u9762\u91cc\u7684\u94fe\u63a5 ===\n1. https:\/\/iana.org\/domains\/example -&gt; Learn more\n\u5171\u627e\u5230 1 \u4e2a\u94fe\u63a5\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">example.com \u662f IANA \u63d0\u4f9b\u7684\u7a33\u5b9a\u6d4b\u8bd5\u9875\u9762\uff0c\u5185\u5bb9\u51e0\u4e4e\u4e0d\u53d8\uff0c\u6700\u9002\u5408\u62ff\u6765\u7ec3\u4e60\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u5347\u7ea7\u6311\u6218<\/strong>\uff1a\u628a\u63d0\u53d6\u7ed3\u679c\u4fdd\u5b58\u5230 <code>page_info.txt<\/code> \u6587\u4ef6\uff08\u7528\u5230 Day 13 \u5b66\u7684\u6587\u4ef6\u5199\u5165\uff09\uff1b\u518d\u8bd5\u8bd5\u8bf7\u6c42\u4e00\u4e2a\u4f60\u5e38\u901b\u7684\u516c\u5f00\u7f51\u9875\uff0c\u628a\u6807\u9898\u548c\u6240\u6709\u94fe\u63a5\u63d0\u53d6\u51fa\u6765\u3002\u6ce8\u610f\u522b\u9891\u7e41\u8bf7\u6c42\u522b\u4eba\u7f51\u7ad9\uff0c\u7ec3\u4e60\u7528 example.com \u6700\u5408\u9002\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u4eca\u65e5\u603b\u7ed3<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><code>python -m pip install<\/code> \u88c5\u5e93\uff0c<code>pip list<\/code> \/ <code>show<\/code> \/ <code>uninstall<\/code> \u7ba1\u7406\uff0c\u955c\u50cf\u6e90\u52a0\u901f\uff1b<code>python -m pip<\/code> \u6700\u7a33\u59a5\n\u865a\u62df\u73af\u5883\uff1a<code>python -m venv venv<\/code> + \u6fc0\u6d3b\uff08<code>(venv)<\/code> \u63d0\u793a\u7b26\uff09+ <code>deactivate<\/code>\uff0c\u9879\u76ee\u72ec\u7acb\u623f\u95f4\n<code>requests.get()<\/code> \u8fd4\u56de Response\uff1a<code>status_code<\/code> \/ <code>text<\/code> \/ <code>encoding<\/code> \/ <code>headers<\/code>\n\u7f51\u7edc\u4e09\u4ef6\u5957\uff1a<code>headers<\/code> \u5e26 User-Agent\u3001<code>timeout<\/code> \u8bbe\u8d85\u65f6\u3001<code>try\/except<\/code> \u515c\u5e95\nBeautifulSoup \u5bf9\u8c61\u6811\uff1a<code>soup.h1<\/code> \/ <code>find<\/code> \/ <code>find_all<\/code> \/ <code>tag.text<\/code> \/ <code>tag[\"href\"]<\/code> \/ <code>select<\/code>\n\u89e3\u6790\u5957\u8def\uff1a\u6279\u91cf\u63d0\u53d6 = <code>find_all<\/code> + \u63a8\u5bfc\u5f0f\uff1b\u8868\u683c = \u5148\u53d6\u884c\u518d\u53d6\u683c\uff1b\u5b8c\u6574\u94fe\u8def = requests \u6293 \u2192 bs4 \u89e3\u6790\n\u533a\u5206\u8054\u7f51\u793a\u4f8b\u4e0e\u79bb\u7ebf\u793a\u4f8b\uff1a\u89e3\u6790\u7c7b\u7528\u672c\u5730 HTML \u5b57\u7b26\u4e32\u79bb\u7ebf\u8dd1\uff0c\u6293\u53d6\u7c7b\u624d\u9700\u8054\u7f51<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><thead><tr><th>\u62a5\u9519<\/th><th>\u539f\u56e0<\/th><th>\u4fee\u590d<\/th><\/tr><\/thead><tbody><tr><td><code>ModuleNotFoundError: No module named 'requests'<\/code><\/td><td>\u5e93\u6ca1\u5b89\u88c5\uff0c\u6216\u88c5\u5230\u4e86\u522b\u7684\u73af\u5883<\/td><td>\u5148 <code>pip install requests beautifulsoup4<\/code>\uff0c\u5e76\u786e\u8ba4\u5728\u6b63\u786e\u7684\u865a\u62df\u73af\u5883\u91cc<\/td><\/tr><tr><td><code>requests.exceptions.ConnectionError<\/code><\/td><td>\u7f51\u7edc\u4e0d\u901a\u6216\u7f51\u5740\u62fc\u9519<\/td><td>\u68c0\u67e5\u7f51\u7edc\uff0c\u786e\u8ba4 URL \u5b8c\u6574\uff08\u542b <code>https:\/\/<\/code>\uff09<\/td><\/tr><tr><td><code>404 Client Error<\/code> \/ <code>403 Client Error<\/code><\/td><td>\u9875\u9762\u4e0d\u5b58\u5728\uff0c\u6216\u670d\u52a1\u5668\u62d2\u7edd\u8bbf\u95ee<\/td><td>\u68c0\u67e5 URL\uff1b\u52a0\u4e0a <code>headers={\"User-Agent\": \"Mozilla\/5.0 ...\"}<\/code> \u518d\u8bd5<\/td><\/tr><tr><td><code>ValueError: Invalid URL<\/code><\/td><td>URL \u5199\u9519\u4e86<\/td><td>\u8865\u5168\u534f\u8bae\u5934\uff0c\u5982 <code>https:\/\/example.com<\/code><\/td><\/tr><tr><td><code>AttributeError: 'NoneType' object has no attribute 'text'<\/code><\/td><td><code>find<\/code> \/ <code>soup.a<\/code> \u6ca1\u627e\u5230\u5143\u7d20\uff0c\u8fd4\u56de\u4e86 <code>None<\/code><\/td><td>\u5148\u5224\u65ad <code>if tag is not None<\/code>\uff0c\u6216\u6539\u7528 <code>find_all<\/code> \u786e\u8ba4\u9009\u62e9\u5668\u662f\u5426\u6b63\u786e<\/td><\/tr><tr><td>\u9875\u9762\u4e2d\u6587\u4e71\u7801<\/td><td>\u7f16\u7801\u5224\u65ad\u9519\u8bef<\/td><td>\u8bbe\u7f6e <code>resp.encoding = \"utf-8\"<\/code> \u6216 <code>resp.encoding = resp.apparent_encoding<\/code><\/td><\/tr><\/tbody><\/table><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>1 pip \u2014\u2014 \u7b2c\u4e09\u65b9\u5e93\u7684\u300c\u5b89\u88c5\u7ba1\u5bb6\u300d \u662f\u4ec0\u4e48\uff1f\u4e3a\u4ec0\u4e48\u5b66\uff1f pip \u662f Python \u81ea\u5e26\u7684\u5305\u7ba1\u7406\u5de5\u5177\uff0c\u4ece  [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_import_markdown_pro_load_document_selector":0,"_import_markdown_pro_submit_text_textarea":"","footnotes":""},"categories":[16,9],"tags":[17],"class_list":["post-106","post","type-post","status-publish","format-standard","hentry","category-python","category-code-dev","tag-python-day"],"_links":{"self":[{"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/posts\/106","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/comments?post=106"}],"version-history":[{"count":2,"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/posts\/106\/revisions"}],"predecessor-version":[{"id":149,"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/posts\/106\/revisions\/149"}],"wp:attachment":[{"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/media?parent=106"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/categories?post=106"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/tags?post=106"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}