{"id":1011990,"date":"2024-12-27T11:34:53","date_gmt":"2024-12-27T03:34:53","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1011990.html"},"modified":"2024-12-27T11:34:57","modified_gmt":"2024-12-27T03:34:57","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e8%8e%b7%e5%8f%96xml","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1011990.html","title":{"rendered":"\u5982\u4f55\u7528python\u83b7\u53d6xml"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25085928\/03e6f767-226f-49ff-8233-764fc56f268f.webp\" alt=\"\u5982\u4f55\u7528python\u83b7\u53d6xml\" \/><\/p>\n<p><p> <strong>\u4f7f\u7528Python\u83b7\u53d6XML\u6587\u4ef6\u7684\u5173\u952e\u6b65\u9aa4\u5305\u62ec\uff1a\u89e3\u6790XML\u6587\u4ef6\u3001\u4f7f\u7528\u5408\u9002\u7684\u5e93\u5982ElementTree\u6216lxml\u6765\u5904\u7406XML\u6570\u636e\u3001\u904d\u5386\u548c\u67e5\u8be2XML\u5143\u7d20\u3002\u8fd9\u4e9b\u6b65\u9aa4\u4e2d\u7684\u6bcf\u4e00\u4e2a\u90fd\u81f3\u5173\u91cd\u8981\uff0c\u4e0b\u9762\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528ElementTree\u5e93\u83b7\u53d6\u548c\u89e3\u6790XML\u6587\u4ef6\u3002<\/strong><\/p>\n<\/p>\n<p><p>Python\u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u5f0f\u6765\u5904\u7406XML\u6587\u4ef6\uff0c\u5176\u4e2d\u6700\u5e38\u7528\u7684\u662fElementTree\u548clxml\u5e93\u3002ElementTree\u662fPython\u6807\u51c6\u5e93\u7684\u4e00\u90e8\u5206\uff0c\u63d0\u4f9b\u4e86\u7b80\u5355\u6613\u7528\u7684API\u6765\u89e3\u6790\u548c\u521b\u5efaXML\u6587\u4ef6\u3002\u5b83\u9002\u5408\u5904\u7406\u7ed3\u6784\u7b80\u5355\u7684XML\u6587\u4ef6\u3002\u800clxml\u5e93\u5219\u662f\u4e00\u4e2a\u529f\u80fd\u66f4\u52a0\u5f3a\u5927\u7684\u7b2c\u4e09\u65b9\u5e93\uff0c\u652f\u6301XPath\u548cXSLT\uff0c\u53ef\u4ee5\u5904\u7406\u66f4\u590d\u6742\u7684XML\u4efb\u52a1\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u89e3\u6790XML\u6587\u4ef6<\/h3>\n<\/p>\n<p><p>\u89e3\u6790XML\u6587\u4ef6\u662f\u83b7\u53d6\u6570\u636e\u7684\u7b2c\u4e00\u6b65\u3002ElementTree\u5e93\u63d0\u4f9b\u4e86<code>parse()<\/code>\u51fd\u6570\uff0c\u53ef\u4ee5\u5c06XML\u6587\u4ef6\u8bfb\u5165\u5e76\u8f6c\u6362\u4e3a\u6811\u7ed3\u6784\uff0c\u65b9\u4fbf\u540e\u7eed\u64cd\u4f5c\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import xml.etree.ElementTree as ET<\/p>\n<p>tree = ET.parse(&#39;file.xml&#39;)<\/p>\n<p>root = tree.getroot()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c<code>parse()<\/code>\u51fd\u6570\u7528\u4e8e\u8bfb\u53d6XML\u6587\u4ef6\uff0c\u5e76\u8fd4\u56de\u4e00\u4e2aElementTree\u5bf9\u8c61\u3002<code>getroot()<\/code>\u65b9\u6cd5\u7528\u4e8e\u83b7\u53d6XML\u7684\u6839\u5143\u7d20\uff0c\u4e4b\u540e\u4fbf\u53ef\u4ee5\u901a\u8fc7\u904d\u5386\u83b7\u53d6\u5404\u4e2a\u5b50\u5143\u7d20\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001\u904d\u5386\u548c\u67e5\u8be2XML\u5143\u7d20<\/h3>\n<\/p>\n<p><p>\u5728\u83b7\u53d6\u4e86XML\u7684\u6839\u5143\u7d20\u540e\uff0c\u53ef\u4ee5\u901a\u8fc7\u904d\u5386\u7684\u65b9\u6cd5\u83b7\u53d6\u5404\u4e2a\u8282\u70b9\u7684\u6570\u636e\u3002ElementTree\u5e93\u63d0\u4f9b\u4e86\u591a\u79cd\u904d\u5386\u65b9\u6cd5\uff0c\u5982<code>iter()<\/code>\u548c<code>findall()<\/code>\u7b49\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>\u4e0a\u8ff0\u4ee3\u7801\u901a\u8fc7\u904d\u5386\u6839\u8282\u70b9\u7684\u6240\u6709\u5b50\u8282\u70b9\uff0c\u6253\u5370\u51fa\u6bcf\u4e2a\u8282\u70b9\u7684\u6807\u7b7e\u548c\u5c5e\u6027\u3002\u9664\u6b64\u4e4b\u5916\uff0c\u8fd8\u53ef\u4ee5\u4f7f\u7528<code>findall()<\/code>\u65b9\u6cd5\u6765\u67e5\u627e\u7279\u5b9a\u6807\u7b7e\u7684\u8282\u70b9\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for elem in root.findall(&#39;tag_name&#39;):<\/p>\n<p>    print(elem.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u4f7f\u7528XPath\u8fdb\u884c\u9ad8\u7ea7\u67e5\u8be2<\/h3>\n<\/p>\n<p><p>\u5982\u679c\u9700\u8981\u8fdb\u884c\u66f4\u590d\u6742\u7684\u67e5\u8be2\uff0clxml\u5e93\u63d0\u4f9b\u4e86\u5bf9XPath\u7684\u652f\u6301\u3002XPath\u662f\u4e00\u79cd\u5728XML\u6587\u6863\u4e2d\u67e5\u627e\u4fe1\u606f\u7684\u8bed\u8a00\uff0c\u4f7f\u7528\u5b83\u53ef\u4ee5\u66f4\u7075\u6d3b\u5730\u8fdb\u884c\u67e5\u8be2\u3002<\/p>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5lxml\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install lxml<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u7136\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528\u5982\u4e0b\u4ee3\u7801\u8fdb\u884cXPath\u67e5\u8be2\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from lxml import etree<\/p>\n<p>tree = etree.parse(&#39;file.xml&#39;)<\/p>\n<p>result = tree.xpath(&#39;\/\/tag_name&#39;)<\/p>\n<p>for elem in result:<\/p>\n<p>    print(elem.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c<code>xpath()<\/code>\u65b9\u6cd5\u7528\u4e8e\u5728XML\u6587\u6863\u4e2d\u67e5\u627e\u6240\u6709\u7b26\u5408XPath\u8868\u8fbe\u5f0f\u7684\u5143\u7d20\u3002<\/p>\n<\/p>\n<p><h3>\u56db\u3001\u5904\u7406\u590d\u6742\u7684XML\u7ed3\u6784<\/h3>\n<\/p>\n<p><p>\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0cXML\u6587\u4ef6\u7684\u7ed3\u6784\u53ef\u80fd\u975e\u5e38\u590d\u6742\uff0c\u5305\u542b\u5d4c\u5957\u7684\u6807\u7b7e\u548c\u591a\u5c42\u6b21\u7684\u6570\u636e\u3002\u6b64\u65f6\uff0c\u53ef\u4ee5\u7ed3\u5408\u4f7f\u7528ElementTree\u548clxml\u5e93\u4e2d\u7684\u529f\u80fd\u6765\u89e3\u6790\u8fd9\u4e9b\u590d\u6742\u7684\u7ed3\u6784\u3002<\/p>\n<\/p>\n<p><p>\u4f8b\u5982\uff0c\u5904\u7406\u5d4c\u5957\u7ed3\u6784\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528\u9012\u5f52\u7684\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">def recursive_parse(element):<\/p>\n<p>    for child in element:<\/p>\n<p>        print(child.tag, child.attrib, child.text)<\/p>\n<p>        recursive_parse(child)<\/p>\n<p>recursive_parse(root)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u9012\u5f52\u65b9\u6cd5\u53ef\u4ee5\u6df1\u5165\u5230XML\u6811\u7684\u6bcf\u4e00\u5c42\uff0c\u83b7\u53d6\u6240\u6709\u8282\u70b9\u7684\u4fe1\u606f\u3002<\/p>\n<\/p>\n<p><h3>\u4e94\u3001\u4fee\u6539\u548c\u521b\u5efaXML\u6587\u4ef6<\/h3>\n<\/p>\n<p><p>\u9664\u4e86\u89e3\u6790\u548c\u67e5\u8be2XML\u6587\u4ef6\uff0cPython\u8fd8\u53ef\u4ee5\u7528\u4e8e\u4fee\u6539\u548c\u521b\u5efaXML\u6587\u4ef6\u3002ElementTree\u5e93\u63d0\u4f9b\u4e86\u7b80\u5355\u7684\u65b9\u6cd5\u6765\u5b9e\u73b0\u8fd9\u4e9b\u529f\u80fd\u3002<\/p>\n<\/p>\n<p><p><strong>\u4fee\u6539XML\u6587\u4ef6<\/strong><\/p>\n<\/p>\n<p><p>\u53ef\u4ee5\u76f4\u63a5\u4fee\u6539\u8282\u70b9\u7684\u5c5e\u6027\u6216\u6587\u672c\uff0c\u7136\u540e\u5c06\u4fee\u6539\u540e\u7684\u6811\u4fdd\u5b58\u56de\u6587\u4ef6\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for elem in root.iter(&#39;tag_name&#39;):<\/p>\n<p>    elem.set(&#39;attribute_name&#39;, &#39;new_value&#39;)<\/p>\n<p>tree.write(&#39;modified_file.xml&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p><strong>\u521b\u5efaXML\u6587\u4ef6<\/strong><\/p>\n<\/p>\n<p><p>\u53ef\u4ee5\u4f7f\u7528ElementTree\u5e93\u521b\u5efa\u65b0\u7684XML\u6587\u4ef6\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">root = ET.Element(&#39;root&#39;)<\/p>\n<p>child = ET.SubElement(root, &#39;child&#39;)<\/p>\n<p>child.text = &#39;This is a child element&#39;<\/p>\n<p>tree = ET.ElementTree(root)<\/p>\n<p>tree.write(&#39;new_file.xml&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u516d\u3001\u5904\u7406\u5927\u89c4\u6a21XML\u6587\u4ef6<\/h3>\n<\/p>\n<p><p>\u5bf9\u4e8e\u975e\u5e38\u5927\u7684XML\u6587\u4ef6\uff0c\u9010\u884c\u89e3\u6790\u53ef\u80fd\u66f4\u4e3a\u9ad8\u6548\u3002ElementTree\u7684<code>iterparse()<\/code>\u65b9\u6cd5\u53ef\u4ee5\u5b9e\u73b0\u8fd9\u4e00\u70b9\uff0c\u5141\u8bb8\u5728\u89e3\u6790\u65f6\u9010\u6b65\u5904\u7406\u6587\u4ef6\u4e2d\u7684\u5143\u7d20\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for event, elem in ET.iterparse(&#39;large_file.xml&#39;, events=(&#39;start&#39;, &#39;end&#39;)):<\/p>\n<p>    if event == &#39;end&#39; and elem.tag == &#39;tag_name&#39;:<\/p>\n<p>        print(elem.text)<\/p>\n<p>        elem.clear()  # \u6e05\u9664\u5df2\u5904\u7406\u7684\u5143\u7d20\uff0c\u8282\u7701\u5185\u5b58<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u65b9\u6cd5\uff0c\u53ef\u4ee5\u6709\u6548\u5730\u5904\u7406\u5927\u89c4\u6a21\u7684XML\u6587\u4ef6\u800c\u4e0d\u5360\u7528\u8fc7\u591a\u5185\u5b58\u3002<\/p>\n<\/p>\n<p><h3>\u4e03\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>Python\u63d0\u4f9b\u4e86\u591a\u79cd\u5904\u7406XML\u6587\u4ef6\u7684\u5e93\uff0cElementTree\u548clxml\u662f\u5176\u4e2d\u6700\u5e38\u7528\u7684\u4e24\u4e2a\u3002\u901a\u8fc7\u8fd9\u4e9b\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u89e3\u6790\u3001\u67e5\u8be2\u3001\u4fee\u6539\u548c\u521b\u5efaXML\u6587\u4ef6\uff0c\u6ee1\u8db3\u4ece\u7b80\u5355\u5230\u590d\u6742\u7684\u5404\u79cd\u9700\u6c42\u3002\u5728\u5904\u7406\u5927\u89c4\u6a21XML\u6587\u4ef6\u65f6\uff0c\u9010\u884c\u89e3\u6790\u7684\u65b9\u6cd5\u80fd\u591f\u6709\u6548\u8282\u7701\u5185\u5b58\uff0c\u63d0\u9ad8\u6548\u7387\u3002\u65e0\u8bba\u662f\u6570\u636e\u7684\u63d0\u53d6\u8fd8\u662f\u6587\u4ef6\u7684\u5904\u7406\uff0c\u638c\u63e1\u8fd9\u4e9b\u6280\u5de7\u90fd\u80fd\u6781\u5927\u63d0\u9ad8\u5de5\u4f5c\u6548\u7387\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u7528Python\u89e3\u6790XML\u6587\u4ef6\uff1f<\/strong><br \/>\u5728Python\u4e2d\uff0c\u89e3\u6790XML\u6587\u4ef6\u53ef\u4ee5\u4f7f\u7528\u591a\u79cd\u5e93\uff0c\u6700\u5e38\u7528\u7684\u662f<code>xml.etree.ElementTree<\/code>\u548c<code>lxml<\/code>\u3002<code>ElementTree<\/code>\u662f\u6807\u51c6\u5e93\u7684\u4e00\u90e8\u5206\uff0c\u9002\u5408\u5904\u7406\u7b80\u5355\u7684XML\u7ed3\u6784\u3002\u4f7f\u7528<code>ElementTree<\/code>\u89e3\u6790XML\u6587\u4ef6\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u5bfc\u5165\u5e93\u3001\u52a0\u8f7dXML\u6587\u4ef6\u3001\u67e5\u627e\u8282\u70b9\u3001\u8bbf\u95ee\u8282\u70b9\u5c5e\u6027\u548c\u83b7\u53d6\u8282\u70b9\u6587\u672c\u5185\u5bb9\u3002\u5bf9\u4e8e\u590d\u6742\u7684XML\u6587\u4ef6\uff0c<code>lxml<\/code>\u5e93\u63d0\u4f9b\u4e86\u66f4\u5f3a\u5927\u7684\u529f\u80fd\uff0c\u5305\u62ecXPath\u652f\u6301\u3002<\/p>\n<p><strong>\u4f7f\u7528Python\u83b7\u53d6XML\u6570\u636e\u7684\u5e38\u89c1\u573a\u666f\u6709\u54ea\u4e9b\uff1f<\/strong><br \/>Python\u83b7\u53d6XML\u6570\u636e\u7684\u5e94\u7528\u573a\u666f\u5e7f\u6cdb\u3002\u4f8b\u5982\uff0c\u722c\u866b\u7a0b\u5e8f\u53ef\u4ee5\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6XML\u6570\u636e\uff0c\u8bb8\u591aAPI\u8fd4\u56de\u7684\u6570\u636e\u683c\u5f0f\u4e3aXML\uff0c\u5c24\u5176\u662f\u5728\u91d1\u878d\u3001\u6c14\u8c61\u548c\u5730\u7406\u4fe1\u606f\u7cfb\u7edf\u7b49\u9886\u57df\u3002\u6b64\u5916\uff0cXML\u6587\u4ef6\u5e38\u7528\u4e8e\u914d\u7f6e\u6587\u4ef6\u548c\u6570\u636e\u4ea4\u6362\uff0cPython\u80fd\u591f\u8f7b\u677e\u8bfb\u53d6\u548c\u5904\u7406\u8fd9\u4e9b\u6570\u636e\u3002<\/p>\n<p><strong>\u5982\u4f55\u5904\u7406XML\u4e2d\u7684\u547d\u540d\u7a7a\u95f4\uff1f<\/strong><br \/>\u5728\u5904\u7406XML\u6587\u4ef6\u65f6\uff0c\u547d\u540d\u7a7a\u95f4\u53ef\u80fd\u4f1a\u5f15\u53d1\u4e00\u4e9b\u590d\u6742\u6027\u3002\u4f7f\u7528<code>xml.etree.ElementTree<\/code>\u65f6\uff0c\u9700\u8981\u5728\u67e5\u627e\u5143\u7d20\u65f6\u6307\u5b9a\u547d\u540d\u7a7a\u95f4\u3002\u53ef\u4ee5\u901a\u8fc7\u521b\u5efa\u4e00\u4e2a\u547d\u540d\u7a7a\u95f4\u5b57\u5178\u6765\u7b80\u5316\u8fd9\u4e00\u8fc7\u7a0b\uff0c\u4ece\u800c\u5728\u89e3\u6790\u65f6\u6307\u660e\u6b63\u786e\u7684\u547d\u540d\u7a7a\u95f4\u3002\u8fd9\u5bf9\u4e8e\u786e\u4fdd\u6b63\u786e\u8bbf\u95ee\u5230\u6240\u9700\u7684\u8282\u70b9\u81f3\u5173\u91cd\u8981\uff0c\u7279\u522b\u662f\u5728\u5927\u578b\u6216\u590d\u6742\u7684XML\u6587\u6863\u4e2d\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4f7f\u7528Python\u83b7\u53d6XML\u6587\u4ef6\u7684\u5173\u952e\u6b65\u9aa4\u5305\u62ec\uff1a\u89e3\u6790XML\u6587\u4ef6\u3001\u4f7f\u7528\u5408\u9002\u7684\u5e93\u5982ElementTree\u6216lxml\u6765 [&hellip;]","protected":false},"author":3,"featured_media":1011998,"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\/1011990"}],"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=1011990"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1011990\/revisions"}],"predecessor-version":[{"id":1012002,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1011990\/revisions\/1012002"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1011998"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1011990"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1011990"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1011990"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}