{"id":175356,"date":"2024-05-08T18:50:12","date_gmt":"2024-05-08T10:50:12","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/175356.html"},"modified":"2024-05-08T18:50:17","modified_gmt":"2024-05-08T10:50:17","slug":"python%e8%a7%a3%e6%9e%90xml%e6%96%87%e4%bb%b6%e5%a6%82%e4%bd%95%e8%af%bb%e5%8f%96%e6%a0%87%e7%ad%be%e7%9a%84%e5%86%85%e5%ae%b9","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/175356.html","title":{"rendered":"python\u89e3\u6790xml\u6587\u4ef6\u5982\u4f55\u8bfb\u53d6\u6807\u7b7e\u7684\u5185\u5bb9"},"content":{"rendered":"<p style=\"text-align:center\">&lt;img src=&quot;https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/27053242\/c4238b6c-a06f-4748-af84-5d1c6007476f.webp&quot; alt=&quot;python\u89e3\u6790xml\u6587\u4ef6\u5982\u4f55\u8bfb\u53d6<br \/>\u6807\u7b7e\u7684\u5185\u5bb9&#8221; \/&gt;<\/p>\n<p><p><strong>Python \u89e3\u6790 XML \u6587\u4ef6\u4ee5\u8bfb\u53d6 <code>&amp;lt;br \/&amp;gt;<\/code> \u6807\u7b7e\u7684\u5185\u5bb9\u901a\u5e38\u6d89\u53ca\u5230\u4f7f\u7528 XML \u89e3\u6790\u5e93\u3001\u8bfb\u53d6\u548c\u5904\u7406\u6807\u7b7e\u5c5e\u6027\u3001\u4ee5\u53ca\u6b63\u786e\u5904\u7406\u81ea\u95ed\u5408\u6807\u7b7e<\/strong>\u3002\u5bf9\u4e8e <code>&amp;lt;br \/&amp;gt;<\/code> \u8fd9\u7c7b\u81ea\u95ed\u5408\u6807\u7b7e\uff0c\u5176\u4e2d\u6ca1\u6709\u6587\u672c\u5185\u5bb9\uff0c\u4f46\u53ef\u4ee5\u8bfb\u53d6\u548c\u64cd\u4f5c\u5176\u5c5e\u6027\u3002\u5728Python\u4e2d\uff0c\u5e38\u7528\u7684\u5e93\u6709 <code>xml.etree.ElementTree<\/code> \u548c <code>lxml<\/code>\u3002<\/p>\n<\/p>\n<p><p>Python\u7684<code>xml.etree.ElementTree<\/code>\u6a21\u5757\u63d0\u4f9b\u4e86\u7b80\u5355\u6613\u7528\u7684API\u6765\u5904\u7406XML\u3002\u5b83\u65e2\u80fd\u591f\u89e3\u6790\u548c\u6784\u5efaXML\u6587\u6863\uff0c\u4e5f\u652f\u6301XPath\u9009\u62e9\u5668\u4ee5\u65b9\u4fbf\u7684\u8fdb\u884c\u5143\u7d20\u7684\u67e5\u627e\u3002\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0c<code>&amp;lt;br \/&amp;gt;<\/code> \u6807\u7b7e\u901a\u5e38\u5728HTML\u4e2d\u7528\u6765\u8868\u793a\u6362\u884c\uff0c\u800c\u5728\u7eafXML\u4e2d\uff0c\u5176\u8868\u73b0\u53ef\u80fd\u4ec5\u4e3a\u4e00\u4e2a\u81ea\u95ed\u5408\u7684\u5143\u7d20\uff0c\u6ca1\u6709\u7279\u5b9a\u7684\u683c\u5f0f\u5316\u610f\u4e49\u3002<\/p>\n<\/p>\n<p><p>\u5728\u4f7f\u7528<code>xml.etree.ElementTree<\/code>\u65f6\uff0c\u53ef\u4ee5\u901a\u8fc7\u5143\u7d20\u7684<code>.tag<\/code>\u5c5e\u6027\u6765\u8bbf\u95ee\u6807\u7b7e\u540d\u79f0\uff0c<code>.attrib<\/code>\u6765\u8bbf\u95ee\u5b83\u7684\u5c5e\u6027\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u5f15\u5165XML\u5904\u7406\u6a21\u5757<\/h3>\n<\/p>\n<p><p>\u5728\u5f00\u59cb\u7f16\u7a0b\u524d\uff0c\u9700\u8981\u5148\u5bfc\u5165Python\u4e2d\u5904\u7406XML\u7684\u76f8\u5173\u6a21\u5757\u3002\u4e00\u822c\u4f1a\u4f7f\u7528<code>xml.etree.ElementTree<\/code>\uff0c\u8be5\u6a21\u5757\u5185\u7f6e\u4e8ePython\u6807\u51c6\u5e93\u4e2d\uff0c\u65e0\u9700\u5355\u72ec\u5b89\u88c5\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import xml.etree.ElementTree as ET<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001\u89e3\u6790XML\u6587\u4ef6<\/h3>\n<\/p>\n<p><p>\u9996\u5148\u9700\u8981\u5bf9XML\u6587\u4ef6\u8fdb\u884c\u89e3\u6790\uff0c\u5c06\u5176\u52a0\u8f7d\u5230\u5185\u5b58\u4e2d\uff0c\u5f62\u6210\u4e00\u4e2a\u53ef\u65b9\u4fbf\u64cd\u4f5c\u5904\u7406\u7684\u6811\u578b\u7ed3\u6784\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u52a0\u8f7dXML\u6587\u4ef6<\/p>\n<p>tree = ET.parse(&#039;example.xml&#039;)<\/p>\n<h2><strong>\u83b7\u53d6\u6839\u8282\u70b9<\/strong><\/h2>\n<p>root = tree.getroot()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u8bfb\u53d6<code>&amp;lt;br \/&amp;gt;<\/code>\u6807\u7b7e\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u5bf9\u4e8e<code>&amp;lt;br \/&amp;gt;<\/code>\u6807\u7b7e\uff0c\u7531\u4e8e\u5b83\u662f\u81ea\u95ed\u548c\u6807\u7b7e\uff0c\u901a\u5e38\u6211\u4eec\u5173\u6ce8\u7684\u662f\u8fd9\u4e2a\u6807\u7b7e\u672c\u8eab\u7684\u5b58\u5728\u4ee5\u53ca\u5b83\u7684\u5c5e\u6027\uff0c\u800c\u975e\u5176\u4e2d\u7684\u6587\u672c\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u904d\u5386\u6587\u6863\u4e2d\u7684\u6240\u6709`br`\u6807\u7b7e<\/p>\n<p>for br in root.iter(&#039;br&#039;):<\/p>\n<p>    # \u8f93\u51fa\u6807\u7b7e\u7684\u5c5e\u6027<\/p>\n<p>    print(br.attrib)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u56db\u3001\u5904\u7406XML\u4e2d\u7684\u81ea\u95ed\u5408\u6807\u7b7e<\/h3>\n<\/p>\n<p><p>\u5728\u5904\u7406\u50cf<code>&amp;lt;br \/&amp;gt;<\/code>\u8fd9\u6837\u7684\u81ea\u95ed\u5408\u6807\u7b7e\u65f6\uff0c\u53ef\u80fd\u9700\u8981\u6309\u7167\u7279\u5b9a\u903b\u8f91\u6765\u5bf9\u5b83\u4eec\u8fdb\u884c\u5904\u7406\uff0c\u4f8b\u5982\u5728\u89e3\u6790XML\u4e3aHTML\u65f6\uff0c\u5b83\u4ee3\u8868\u4e00\u4e2a\u6362\u884c\u7b26\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u5047\u8bbe\u6211\u4eec\u9700\u8981\u5c06XML\u8f6c\u6362\u4e3aHTML<\/p>\n<p>html_output = &quot;&quot;<\/p>\n<p>for element in root.iter():<\/p>\n<p>    if element.tag == &#039;br&#039;:<\/p>\n<p>        html_output += &quot;&lt;br \/&gt;&quot;<\/p>\n<p>    else:<\/p>\n<p>        # \u5904\u7406\u5176\u4ed6\u6807\u7b7e\u548c\u6587\u672c<\/p>\n<p>        pass  # \u8fd9\u91cc\u7701\u7565\u5177\u4f53\u5904\u7406\u903b\u8f91<\/p>\n<h2><strong>\u4f8b\u5982\uff0c\u53ef\u4ee5\u5c06\u8f6c\u6362\u540e\u7684HTML\u5185\u5bb9\u4fdd\u5b58\u5230\u6587\u4ef6\u4e2d<\/strong><\/h2>\n<p>with open(&#039;output.html&#039;, &#039;w&#039;) as f:<\/p>\n<p>    f.write(html_output)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u4f7f\u7528\u7b2c\u4e09\u65b9\u5e93\u5904\u7406\u590d\u6742XML<\/h3>\n<\/p>\n<p><p>\u5bf9\u4e8e\u66f4\u52a0\u590d\u6742\u7684XML\u6587\u4ef6\u5904\u7406\uff0c\u6216\u9700\u8981\u66f4\u5f3a\u5927\u7684XPath\u652f\u6301\uff0c\u53ef\u4ee5\u4f7f\u7528\u7b2c\u4e09\u65b9\u5e93\uff0c\u4f8b\u5982<code>lxml<\/code>\u3002\u8be5\u5e93\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684API\u548c\u66f4\u5feb\u7684\u6027\u80fd\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from lxml import etree<\/p>\n<h2><strong>\u4f7f\u7528lxml\u52a0\u8f7dXML<\/strong><\/h2>\n<p>tree = etree.parse(&#039;example.xml&#039;)<\/p>\n<p>root = tree.getroot()<\/p>\n<h2><strong>\u4f7f\u7528XPath\u67e5\u627e\u6240\u6709\u7684`br`\u6807\u7b7e<\/strong><\/h2>\n<p>breaks = root.xpath(&#039;\/\/br&#039;)<\/p>\n<h2><strong>\u8fdb\u884c\u76f8\u5173\u5904\u7406<\/strong><\/h2>\n<p>for br in breaks:<\/p>\n<p>    print(br.attrib)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5f53\u5904\u7406XML\u6587\u4ef6\u65f6\uff0c\u9664\u4e86\u4e0a\u8ff0\u65b9\u6cd5\uff0c\u53ef\u80fd\u8fd8\u9700\u8981\u5904\u7406\u7f16\u7801\u95ee\u9898\u3001\u547d\u540d\u7a7a\u95f4\u3001\u89e3\u6790\u9519\u8bef\u4ee5\u53caXML\u5b89\u5168\u95ee\u9898\u7b49\u3002\u5c24\u5176\u5f53\u5904\u7406\u6765\u81ea\u4e0d\u53ef\u4fe1\u6765\u6e90\u7684XML\u65f6\uff0c\u6ce8\u610f\u9632\u8303XML\u5916\u90e8\u5b9e\u4f53\u6ce8\u5165\u653b\u51fb\uff08XXE\u653b\u51fb\uff09\u7b49\u5b89\u5168\u9690\u60a3\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p><strong>1. \u5982\u4f55\u4f7f\u7528Python\u89e3\u6790XML\u6587\u4ef6\u5e76\u8bfb\u53d6\u6807\u7b7e\u7684\u5185\u5bb9\uff1f<\/strong><\/p>\n<p>XML\u662f\u4e00\u79cd\u7528\u4e8e\u5b58\u50a8\u548c\u4f20\u8f93\u6570\u636e\u7684\u6807\u8bb0\u8bed\u8a00\uff0cPython\u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u6cd5\u7528\u4e8e\u89e3\u6790\u548c\u8bfb\u53d6XML\u6587\u4ef6\u4e2d\u7684\u5185\u5bb9\u3002\u4e00\u79cd\u5e38\u7528\u7684\u65b9\u6cd5\u662f\u4f7f\u7528Python\u5185\u7f6e\u7684xml.etree.ElementTree\u6a21\u5757\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u4f8b\u5b50\uff1a<\/p>\n<pre><code class=\"language-python\">import xml.etree.ElementTree as ET\n\n# \u8bfb\u53d6XML\u6587\u4ef6\ntree = ET.parse(&#039;example.xml&#039;)\nroot = tree.getroot()\n\n# \u904d\u5386XML\u6587\u6863\u5e76\u8bfb\u53d6\u6307\u5b9a\u6807\u7b7e\u7684\u5185\u5bb9\nfor element in root.iter(&#039;tag_name&#039;):\n    # \u83b7\u53d6\u6807\u7b7e\u7684\u5185\u5bb9\n    content = element.text\n    print(content)\n<\/code><\/pre>\n<p>\u5728\u4e0a\u8ff0\u793a\u4f8b\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u4f7f\u7528<code>ET.parse<\/code>\u65b9\u6cd5\u8bfb\u53d6XML\u6587\u4ef6\uff0c\u5e76\u4f7f\u7528<code>getroot<\/code>\u65b9\u6cd5\u83b7\u53d6\u6839\u5143\u7d20\u3002\u7136\u540e\uff0c\u6211\u4eec\u4f7f\u7528<code>iter<\/code>\u65b9\u6cd5\u904d\u5386XML\u6587\u6863\u4e2d\u6240\u6709\u6307\u5b9a\u540d\u79f0\u7684\u6807\u7b7e\uff0c\u5e76\u4f7f\u7528<code>text<\/code>\u5c5e\u6027\u83b7\u53d6\u6807\u7b7e\u7684\u5185\u5bb9\u3002<\/p>\n<p><strong>2. Python\u4e2d\u6709\u54ea\u4e9b\u5e93\u53ef\u4ee5\u7528\u4e8e\u89e3\u6790XML\u6587\u4ef6\u5e76\u8bfb\u53d6\u6807\u7b7e\u7684\u5185\u5bb9\uff1f<\/strong><\/p>\n<p>\u9664\u4e86\u4f7f\u7528Python\u5185\u7f6e\u7684xml.etree.ElementTree\u6a21\u5757\uff0c\u8fd8\u6709\u5176\u4ed6\u4e00\u4e9b\u7b2c\u4e09\u65b9\u5e93\u53ef\u4ee5\u7528\u4e8e\u89e3\u6790XML\u6587\u4ef6\u5e76\u8bfb\u53d6\u6807\u7b7e\u7684\u5185\u5bb9\u3002\u4f8b\u5982\uff1a<\/p>\n<ul>\n<li>lxml\uff1a\u5b83\u662f\u57fa\u4e8eC\u8bed\u8a00\u7684libxml2\u5e93\u7684Python\u7ed1\u5b9a\uff0c\u63d0\u4f9b\u4e86\u9ad8\u6027\u80fd\u7684XML\u89e3\u6790\u548c\u5904\u7406\u529f\u80fd\u3002<\/li>\n<li>xml.dom\uff1a\u8fd9\u4e2a\u6a21\u5757\u63d0\u4f9b\u4e86\u7528\u4e8e\u5904\u7406XML\u6587\u6863\u7684DOM\u5b9e\u73b0\uff0c\u53ef\u4ee5\u901a\u8fc7\u521b\u5efaDOM\u6811\u6765\u83b7\u53d6\u548c\u64cd\u4f5cXML\u6587\u6863\u4e2d\u7684\u5143\u7d20\u548c\u5c5e\u6027\u3002<\/li>\n<li>xmltodict\uff1a\u8fd9\u662f\u4e00\u4e2a\u5c06XML\u6587\u4ef6\u8f6c\u6362\u4e3aPython\u5b57\u5178\u7684\u5e93\uff0c\u53ef\u4ee5\u8f7b\u677e\u5730\u8bbf\u95ee\u548c\u64cd\u4f5cXML\u6587\u6863\u4e2d\u7684\u6570\u636e\u3002<\/li>\n<\/ul>\n<p>\u6839\u636e\u4f60\u7684\u5177\u4f53\u9700\u6c42\uff0c\u53ef\u4ee5\u9009\u62e9\u9002\u5408\u7684\u5e93\u6765\u89e3\u6790XML\u6587\u4ef6\u3002<\/p>\n<p><strong>3. \u5982\u4f55\u4f7f\u7528XPath\u8868\u8fbe\u5f0f\u6765\u89e3\u6790XML\u6587\u4ef6\u5e76\u8bfb\u53d6\u6807\u7b7e\u7684\u5185\u5bb9\uff1f<\/strong><\/p>\n<p>XPath\u662f\u4e00\u79cd\u7528\u4e8e\u5728XML\u6587\u6863\u4e2d\u5b9a\u4f4d\u5143\u7d20\u7684\u8bed\u8a00\uff0cPython\u4e2d\u7684\u4e00\u4e9b\u5e93\uff08\u5982lxml\u548cxml.etree.ElementTree\uff09\u652f\u6301\u4f7f\u7528XPath\u6765\u89e3\u6790XML\u6587\u4ef6\u5e76\u8bfb\u53d6\u6807\u7b7e\u7684\u5185\u5bb9\u3002\u4e0b\u9762\u662f\u4e00\u4e2a\u4f7f\u7528lxml\u5e93\u548cXPath\u8868\u8fbe\u5f0f\u7684\u4f8b\u5b50\uff1a<\/p>\n<pre><code class=\"language-python\">from lxml import etree\n\n# \u8bfb\u53d6XML\u6587\u4ef6\ntree = etree.parse(&#039;example.xml&#039;)\n\n# \u4f7f\u7528XPath\u8868\u8fbe\u5f0f\u6765\u83b7\u53d6\u6307\u5b9a\u6807\u7b7e\u7684\u5185\u5bb9\nresult = tree.xpath(&#039;\/\/tag_name\/text()&#039;)\nfor content in result:\n    print(content)\n<\/code><\/pre>\n<p>\u5728\u4e0a\u8ff0\u793a\u4f8b\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u4f7f\u7528<code>etree.parse<\/code>\u65b9\u6cd5\u8bfb\u53d6XML\u6587\u4ef6\u3002\u7136\u540e\uff0c\u4f7f\u7528<code>xpath<\/code>\u65b9\u6cd5\u5e76\u4f20\u5165XPath\u8868\u8fbe\u5f0f\u6765\u83b7\u53d6\u6307\u5b9a\u6807\u7b7e\u7684\u5185\u5bb9\u3002\u6700\u540e\uff0c\u6211\u4eec\u4f7f\u7528\u4e00\u4e2a\u5faa\u73af\u6765\u6253\u5370\u6240\u6709\u83b7\u53d6\u5230\u7684\u5185\u5bb9\u3002\u53ea\u9700\u4fee\u6539XPath\u8868\u8fbe\u5f0f\u5373\u53ef\u83b7\u53d6\u4e0d\u540c\u7684\u6807\u7b7e\u5185\u5bb9\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"&lt;img src=&quot;https:\/\/cdn-kb.worktile.com\/kb\/wp-con [&hellip;]","protected":false},"author":3,"featured_media":175368,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/175356"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=175356"}],"version-history":[{"count":0,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/175356\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/175368"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=175356"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=175356"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=175356"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}