{"id":98532,"date":"2024-04-12T11:18:01","date_gmt":"2024-04-12T03:18:01","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/98532.html"},"modified":"2024-04-12T11:18:03","modified_gmt":"2024-04-12T03:18:03","slug":"%e8%a7%a3%e6%9e%90xml%e5%93%8d%e5%ba%94%e5%9c%a8python%e4%b8%ad%e7%9a%84%e6%96%b9%e6%b3%95","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/98532.html","title":{"rendered":"\u89e3\u6790XML\u54cd\u5e94\u5728Python\u4e2d\u7684\u65b9\u6cd5"},"content":{"rendered":"<p style=\"text-align:center\"><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/02153449\/270e4363-57bc-4985-8d12-4a9e70a90ad0.webp\" alt=\"\u89e3\u6790XML\u54cd\u5e94\u5728Python\u4e2d\u7684\u65b9\u6cd5\" \/><\/p>\n<p><p>\u89e3\u6790XML\u54cd\u5e94\u5728Python\u4e2d\u7684\u65b9\u6cd5\u4e3b\u8981\u4f9d\u8d56\u4e8e\u51e0\u4e2a\u6838\u5fc3\u7684\u5e93\uff0c\u8fd9\u4e9b\u5e93\u5305\u62ec<strong>ElementTree\u3001Minidom\u3001lxml\u3001\u548cBeautifulSoup<\/strong>\u3002\u6bcf\u79cd\u65b9\u6cd5\u90fd\u6709\u5176\u7279\u70b9\u548c\u9002\u7528\u573a\u666f\uff0c\u4f46\u5728\u4f17\u591a\u9009\u9879\u4e2d\uff0c<strong>ElementTree<\/strong>\u56e0\u5176\u7b80\u6d01\u6027\u548c\u6613\u7528\u6027\u800c\u5e7f\u53d7\u6b22\u8fce\u3002ElementTree \u662f Python \u6807\u51c6\u5e93\u7684\u4e00\u90e8\u5206\uff0c\u63d0\u4f9b\u4e86\u8f7b\u91cf\u7ea7\u7684Python\u5f0f\u7684API\u6765\u5904\u7406XML\u6570\u636e\u3002\u5b83\u5141\u8bb8\u5f00\u53d1\u8005\u7528\u4e00\u4e2a\u7b80\u5355\u800c\u6709\u6548\u7684\u65b9\u5f0f\u6765\u521b\u5efa\u548c\u89e3\u6790XML\u6587\u6863\uff0c\u56e0\u6b64\u5bf9\u4e8e\u591a\u6570\u9700\u6c42\u800c\u8a00\uff0cElementTree\u662f\u4e00\u4e2a\u975e\u5e38\u597d\u7684\u9009\u62e9\u3002\u6b64\u5916\uff0c\u5b83\u8fd8\u652f\u6301XPath\u9009\u62e9\u5668\uff0c\u8ba9\u5bfb\u627e\u7279\u5b9a\u5143\u7d20\u53d8\u5f97\u66f4\u52a0\u4fbf\u6377\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u4f7f\u7528ELEMENTTREE\u89e3\u6790XML<\/h3>\n<\/p>\n<p><p>ElementTree\u7b80\u5316\u4e86XML\u6587\u6863\u7684\u5904\u7406\u6d41\u7a0b\u3002\u901a\u8fc7ElementTree\uff0c\u5f00\u53d1\u8005\u53ef\u4ee5\u8f7b\u677e\u5730\u8bfb\u53d6XML\u6587\u4ef6\u3001\u4fee\u6539\u6587\u6863\u3001\u521b\u5efa\u65b0\u7684XML\u6587\u6863\u4ee5\u53ca\u641c\u7d22\u6587\u6863\u4e2d\u7684\u5143\u7d20\u3002<\/p>\n<\/p>\n<p><h4>\u521b\u5efaElementTree\u5bf9\u8c61<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u9700\u8981\u4ecexml.etree.ElementTree\u6a21\u5757\u4e2d\u5bfc\u5165ElementTree\u7c7b\uff0c\u7136\u540e\u52a0\u8f7dXML\u6587\u6863\u521b\u5efaElementTree\u5bf9\u8c61\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import xml.etree.ElementTree as ET<\/p>\n<p>tree = ET.parse(&#039;example.xml&#039;)<\/p>\n<p>root = tree.getroot()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u6b64\u8fc7\u7a0b\u4e2d\uff0c<code>parse<\/code>\u51fd\u6570\u8bfb\u53d6\u6587\u4ef6\u5e76\u89e3\u6790XML\u6587\u6863\uff0c\u800c<code>getroot<\/code>\u65b9\u6cd5\u5219\u8fd4\u56de\u6587\u6863\u7684\u6839\u5143\u7d20\u3002<\/p>\n<\/p>\n<p><h4>\u904d\u5386XML\u6587\u6863<\/h4>\n<\/p>\n<p><p>ElementTree\u5bf9\u8c61\u53ef\u4ee5\u901a\u8fc7\u76f4\u63a5\u904d\u5386\u6765\u5904\u7406XML\u6587\u6863\u7684\u5143\u7d20\u3002\u5f00\u53d1\u8005\u53ef\u4ee5\u4f7f\u7528<code>for<\/code>\u5faa\u73af\u904d\u5386\u5b50\u5143\u7d20\uff0c\u4e5f\u53ef\u4ee5\u4f7f\u7528<code>.find()<\/code>\u3001<code>.findall()<\/code> \u6216 <code>.iter()<\/code> \u65b9\u6cd5\u6765\u641c\u7d22\u7279\u5b9a\u7684\u5143\u7d20\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for child in root:<\/p>\n<p>    print(child.tag, child.attrib)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u79cd\u65b9\u5f0f\uff0c\u60a8\u53ef\u4ee5\u6253\u5370\u51fa\u6839\u5143\u7d20\u4e0b\u6240\u6709\u5b50\u5143\u7d20\u7684\u6807\u7b7e\u548c\u5c5e\u6027\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001\u4f7f\u7528MINIDOM\u89e3\u6790XML<\/h3>\n<\/p>\n<p><p>Minidom\u662f\u4e00\u4e2a\u7b80\u5355\u7684DOM API\uff0c\u63d0\u4f9b\u4e86\u53e6\u4e00\u79cd\u89e3\u6790XML\u6587\u6863\u7684\u65b9\u6cd5\u3002\u5b83\u9002\u7528\u4e8e\u9700\u8981\u8bbf\u95eeXML\u6587\u6863\u7ed3\u6784\u7684\u5e94\u7528\uff0c\u6bd4\u5982\u904d\u5386\u6587\u6863\u6216\u4fee\u6539\u5176\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h4>\u52a0\u8f7dXML\u6587\u6863<\/h4>\n<\/p>\n<p><p>\u8981\u4f7f\u7528minidom\uff0c\u9996\u5148\u9700\u8981\u4ecexml.dom.minidom\u6a21\u5757\u5bfc\u5165parse\u65b9\u6cd5\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from xml.dom.minidom import parse<\/p>\n<p>dom = parse(&#039;example.xml&#039;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>parse\u51fd\u6570\u4f1a\u8bfb\u53d6\u5e76\u89e3\u6790XML\u6587\u6863\uff0c\u8fd4\u56de\u4e00\u4e2aDocument\u5bf9\u8c61\uff0c\u4ee3\u8868\u6574\u4e2aXML\u6587\u6863\u3002<\/p>\n<\/p>\n<p><h4>\u904d\u5386\u548c\u641c\u7d22\u5143\u7d20<\/h4>\n<\/p>\n<p><p>minidom\u63d0\u4f9b\u4e86\u83b7\u53d6\u5143\u7d20\u548c\u5c5e\u6027\u7684\u65b9\u6cd5\uff0c\u5982getElementsByTagName()\u53ef\u4ee5\u7528\u6765\u641c\u7d22\u5177\u6709\u7279\u5b9a\u6807\u7b7e\u7684\u6240\u6709\u5143\u7d20\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">items = dom.getElementsByTagName(&#039;item&#039;)<\/p>\n<p>for item in items:<\/p>\n<p>    print(item.getAttribute(&#039;name&#039;))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u4f7f\u7528LXML\u89e3\u6790XML<\/h3>\n<\/p>\n<p><p>lxml\u662f\u4e00\u4e2a\u975e\u5e38\u5f3a\u5927\u7684\u5e93\uff0c\u63d0\u4f9b\u4e86\u5168\u9762\u7684XML\/HTML\u5904\u7406\u529f\u80fd\u3002\u5b83\u6bd4\u6807\u51c6\u5e93\u4e2d\u7684ElementTree\u548cMinidom\u901f\u5ea6\u66f4\u5feb\uff0c\u800c\u4e14\u652f\u6301XPath\u548cXSLT\u3002<\/p>\n<\/p>\n<p><h4>\u89e3\u6790XML\u6587\u6863<\/h4>\n<\/p>\n<p><p>\u4ecelxml\u4e2d\u5bfc\u5165etree\uff0c\u7136\u540e\u4f7f\u7528<code>etree.parse()<\/code>\u51fd\u6570\u6765\u52a0\u8f7d\u548c\u89e3\u6790XML\u6587\u4ef6\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from lxml import etree<\/p>\n<p>tree = etree.parse(&#039;example.xml&#039;)<\/p>\n<p>root = tree.getroot()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>\u4f7f\u7528XPath\u9009\u62e9\u5143\u7d20<\/h4>\n<\/p>\n<p><p>lxml\u7684\u4e00\u4e2a\u7a81\u51fa\u7279\u70b9\u662f\u652f\u6301XPath\uff0c\u8fd9\u662f\u4e00\u4e2a\u7528\u4e8e\u5728XML\u6587\u6863\u4e2d\u5b9a\u4f4d\u5143\u7d20\u7684\u8bed\u8a00\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for element in root.xpath(&#039;\/\/item[@name=&quot;example&quot;]&#039;):<\/p>\n<p>    print(element.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u56db\u3001\u4f7f\u7528BEAUTIFULSOAP\u89e3\u6790XML<\/h3>\n<\/p>\n<p><p>BeautifulSoup\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u7684\u5e93\uff0c\u7279\u522b\u9002\u5408\u505a\u7f51\u9875\u6293\u53d6\u3002\u5b83\u63d0\u4f9b\u4e86Python\u98ce\u683c\u7684\u64cd\u4f5cAPI\u3002<\/p>\n<\/p>\n<p><h4>\u52a0\u8f7d\u548c\u89e3\u6790XML<\/h4>\n<\/p>\n<p><p>\u9996\u5148\u8981\u5b89\u88c5beautifulsoup4\u548clxml\u5e93\uff0c\u7136\u540e\u52a0\u8f7dXML\u6587\u6863\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>with open(&#039;example.xml&#039;, &#039;r&#039;) as file:<\/p>\n<p>    data = file.read()<\/p>\n<p>soup = BeautifulSoup(data, &#039;lxml&#039;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>\u641c\u7d22\u5143\u7d20<\/h4>\n<\/p>\n<p><p>BeautifulSoup\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u65b9\u6cd5\u6765\u641c\u7d22\u7279\u5b9a\u7684\u6807\u7b7e\u548c\u5c5e\u6027\uff0c\u4f8b\u5982<code>find_all()<\/code>\u65b9\u6cd5\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for item in soup.find_all(&#039;item&#039;):<\/p>\n<p>    print(item[&#039;name&#039;])<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u7efc\u4e0a\u6240\u8ff0\uff0cPython\u63d0\u4f9b\u4e86\u591a\u79cd\u89e3\u6790XML\u54cd\u5e94\u7684\u65b9\u6cd5\uff0c\u6bcf\u79cd\u65b9\u6cd5\u90fd\u6709\u5176\u4f18\u52bf\u548c\u7279\u70b9\u3002ElementTree\u56e0\u5176\u7b80\u6d01\u6027\u800c\u88ab\u5e7f\u6cdb\u5e94\u7528\uff0cMinidom\u548clxml\u63d0\u4f9b\u4e86\u66f4\u591a\u9ad8\u7ea7\u529f\u80fd\uff0c\u800cBeautifulSoup\u5219\u5728\u7f51\u9875\u6293\u53d6\u65b9\u9762\u8868\u73b0\u51fa\u8272\u3002\u5f00\u53d1\u8005\u53ef\u4ee5\u6839\u636e\u81ea\u5df1\u7684\u9700\u6c42\u548c\u573a\u666f\u9009\u62e9\u5408\u9002\u7684\u5e93\u6765\u5904\u7406XML\u6570\u636e\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p><strong>1. \u5728Python\u4e2d\u5982\u4f55\u89e3\u6790XML\u54cd\u5e94\uff1f<\/strong><br \/>\n\u8981\u89e3\u6790XML\u54cd\u5e94\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u7684\u5185\u7f6e\u5e93\uff0c\u4f8b\u5982xml.etree.ElementTree\u3002\u8fd9\u4e2a\u5e93\u63d0\u4f9b\u4e86\u4e00\u7ec4\u7b80\u5355\u800c\u5f3a\u5927\u7684\u5de5\u5177\uff0c\u7528\u4e8e\u89e3\u6790\u548c\u64cd\u4f5cXML\u6570\u636e\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528ElementTree\u7684parse\u51fd\u6570\u4eceXML\u6587\u4ef6\u6216\u5b57\u7b26\u4e32\u4e2d\u521b\u5efa\u4e00\u4e2aElement\u5bf9\u8c61\uff0c\u7136\u540e\u4f7f\u7528Element\u5bf9\u8c61\u7684\u65b9\u6cd5\u6765\u8bbf\u95ee\u548c\u5904\u7406XML\u6570\u636e\u3002<\/p>\n<p><strong>2. \u6211\u5e94\u8be5\u5982\u4f55\u5904\u7406XML\u54cd\u5e94\u4e2d\u7684\u547d\u540d\u7a7a\u95f4\uff1f<\/strong><br \/>\n\u5728\u5904\u7406XML\u54cd\u5e94\u65f6\uff0c\u547d\u540d\u7a7a\u95f4\u662f\u4e00\u4e2a\u91cd\u8981\u7684\u6982\u5ff5\u3002\u547d\u540d\u7a7a\u95f4\u5141\u8bb8\u6211\u4eec\u5728XML\u6587\u6863\u4e2d\u4f7f\u7528\u76f8\u540c\u540d\u79f0\u7684\u5143\u7d20\u548c\u5c5e\u6027\uff0c\u4f46\u5b83\u4eec\u5177\u6709\u4e0d\u540c\u7684\u542b\u4e49\u3002\u8981\u5904\u7406\u547d\u540d\u7a7a\u95f4\uff0c\u53ef\u4ee5\u4f7f\u7528Element\u5bf9\u8c61\u7684\u65b9\u6cd5\uff0c\u4f8b\u5982find\u548cfindall\u6765\u9009\u62e9\u5177\u6709\u7279\u5b9a\u547d\u540d\u7a7a\u95f4\u7684\u5143\u7d20\u3002\u8fd8\u53ef\u4ee5\u4f7f\u7528Element\u5bf9\u8c61\u7684get\u548cset\u65b9\u6cd5\u6765\u64cd\u4f5c\u5177\u6709\u547d\u540d\u7a7a\u95f4\u7684\u5c5e\u6027\u3002<\/p>\n<p><strong>3. \u6211\u53ef\u4ee5\u4f7f\u7528\u5176\u4ed6Python\u5e93\u6765\u89e3\u6790XML\u54cd\u5e94\u5417\uff1f<\/strong><br \/>\n\u9664\u4e86xml.etree.ElementTree\uff0cPython\u8fd8\u63d0\u4f9b\u4e86\u5176\u4ed6\u4e00\u4e9b\u5e93\u6765\u5904\u7406XML\u6570\u636e\uff0c\u4f8b\u5982lxml\u548cxml.dom\u3002lxml\u662f\u4e00\u4e2a\u975e\u5e38\u5feb\u901f\u548c\u6613\u4e8e\u4f7f\u7528\u7684XML\u548cHTML\u5904\u7406\u5e93\uff0c\u5b83\u5177\u6709\u4e0eElementTree\u7c7b\u4f3c\u7684API\uff0c\u4f46\u63d0\u4f9b\u4e86\u66f4\u9ad8\u7ea7\u7684\u529f\u80fd\u3002xml.dom\u662fPython\u7684\u6807\u51c6DOM\u5b9e\u73b0\uff0c\u5b83\u63d0\u4f9b\u4e86\u4e00\u7ec4\u5bf9\u8c61\u6765\u8868\u793aXML\u6587\u6863\uff0c\u5e76\u53ef\u4ee5\u901a\u8fc7\u904d\u5386\u6811\u72b6\u7ed3\u6784\u6765\u8bbf\u95ee\u548c\u64cd\u4f5cXML\u6570\u636e\u3002\u6839\u636e\u4f60\u7684\u9700\u6c42\u548c\u4e2a\u4eba\u504f\u597d\uff0c\u4f60\u53ef\u4ee5\u9009\u62e9\u4f7f\u7528\u5176\u4e2d\u4e4b\u4e00\u6765\u89e3\u6790XML\u54cd\u5e94\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u89e3\u6790XML\u54cd\u5e94\u5728Python\u4e2d\u7684\u65b9\u6cd5\u4e3b\u8981\u4f9d\u8d56\u4e8e\u51e0\u4e2a\u6838\u5fc3\u7684\u5e93\uff0c\u8fd9\u4e9b\u5e93\u5305\u62ecElementTree\u3001Minidom\u3001 [&hellip;]","protected":false},"author":3,"featured_media":98536,"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\/98532"}],"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=98532"}],"version-history":[{"count":0,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/98532\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/98536"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=98532"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=98532"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=98532"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}