{"id":175193,"date":"2024-05-08T18:46:40","date_gmt":"2024-05-08T10:46:40","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/175193.html"},"modified":"2024-05-08T18:46:46","modified_gmt":"2024-05-08T10:46:46","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e8%af%bb%e5%8f%96%e6%8e%a5%e5%8f%a3%e8%bf%94%e5%9b%9e%e7%9a%84xml-%e4%b8%ad%e7%9a%84%e6%95%b0%e6%8d%ae","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/175193.html","title":{"rendered":"\u5982\u4f55\u7528python\u8bfb\u53d6\u63a5\u53e3\u8fd4\u56de\u7684xml \u4e2d\u7684\u6570\u636e"},"content":{"rendered":"<p style=\"text-align:center\"><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/27053038\/6c9f43c6-e8c5-4a81-b5a7-4cb90b640cec.webp\" alt=\"\u5982\u4f55\u7528python\u8bfb\u53d6\u63a5\u53e3\u8fd4\u56de\u7684xml \u4e2d\u7684\u6570\u636e\" \/><\/p>\n<p><p><strong>Python\u8bfb\u53d6\u63a5\u53e3\u8fd4\u56de\u7684XML\u6570\u636e<\/strong>\u53ef\u5206\u4e3a\u4ee5\u4e0b\u6b65\u9aa4\uff1a<strong>\u5b89\u88c5\u5e76\u5bfc\u5165\u5fc5\u8981\u7684\u5e93\u3001\u53d1\u8d77HTTP\u8bf7\u6c42\u83b7\u53d6XML\u6570\u636e\u3001\u89e3\u6790XML\u6570\u636e\u3001\u8bbf\u95ee\u7279\u5b9a\u7684XML\u8282\u70b9\u3001\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e<\/strong>\u3002\u5728\u8be6\u7ec6\u63cf\u8ff0\u524d\uff0c\u9996\u5148\u8981\u4e86\u89e3\u7684\u662f\uff0c\u89e3\u6790XML\u6570\u636e\u4e00\u822c\u4f7f\u7528<code>xml.etree.ElementTree<\/code>\u6a21\u5757\uff0c\u5b83\u662fPython\u7684\u5185\u7f6e\u5e93\uff0c\u65e0\u9700\u989d\u5916\u5b89\u88c5\uff0c\u5e76\u4e14\u63d0\u4f9b\u4e86\u7075\u6d3b\u7684\u8282\u70b9\u904d\u5386\u65b9\u5f0f\uff0c\u5982<code>find<\/code>\u3001<code>findall<\/code>\u548c<code>iter<\/code>\u7b49\u65b9\u6cd5\uff0c\u7528\u4e8e\u67e5\u627e\u548c\u8bbf\u95ee\u8282\u70b9\u5143\u7d20\u3002<\/p>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u901a\u8fc7\u7b2c\u4e09\u65b9\u5e93\u5982<code>requests<\/code>\u53d1\u8d77HTTP\u8bf7\u6c42\uff0c\u5047\u8bbe\u63a5\u53e3\u4ee5GET\u65b9\u6cd5\u63d0\u4f9b\u6570\u636e\uff0c\u5219\u4ee3\u7801\u7c7b\u4f3c\u4e8e\uff1a<code>response = requests.get(&#039;\u63a5\u53e3URL&#039;)<\/code>\u3002\u83b7\u53d6\u5230\u7684response\u5bf9\u8c61\u5305\u542b\u4e86\u670d\u52a1\u5668\u8fd4\u56de\u7684XML\u683c\u5f0f\u7684\u5185\u5bb9\uff0c\u53ef\u4ee5\u901a\u8fc7<code>response.content<\/code>\u8bbf\u95ee\u539f\u59cb\u7684\u5b57\u8282\u6570\u636e\uff0c\u6216\u662f\u901a\u8fc7<code>response.text<\/code>\u4ee5\u5b57\u7b26\u4e32\u5f62\u5f0f\u8bbf\u95ee\u3002<\/p>\n<\/p>\n<p><p>\u4e00\u65e6\u83b7\u53d6\u4e86XML\u6570\u636e\uff0c\u5c31\u53ef\u4ee5\u4f7f\u7528<code>xml.etree.ElementTree<\/code>\u6a21\u5757\u8fdb\u884c\u89e3\u6790\u3002\u901a\u5e38\u53ef\u4ee5\u901a\u8fc7<code>ElementTree.XML()<\/code>\u65b9\u6cd5\u5c06\u5b57\u7b26\u4e32\u89e3\u6790\u4e3aXML\u7684\u5143\u7d20\u6811\uff0c\u5f97\u5230\u7684\u6811\u5bf9\u8c61\u53ef\u7528\u4e8e\u8fdb\u4e00\u6b65\u7684\u5904\u7406\u3002\u4f8b\u5982\uff0c<code>tree = ElementTree.XML(response.text)<\/code>\u3002<\/p>\n<\/p>\n<p><p>\u63a5\u4e0b\u6765\u7684\u6b65\u9aa4\u662f\u6839\u636eXML\u7684\u7ed3\u6784\uff0c\u4f7f\u7528<code>find<\/code>\u3001<code>findall<\/code>\u7b49\u65b9\u6cd5\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u4f8b\u5982\uff0c\u82e5\u60f3\u8981\u83b7\u53d6XML\u4e2d\u7684\u6240\u6709<code>item<\/code>\u8282\u70b9\uff0c\u53ef\u4ee5\u4f7f\u7528<code>items = tree.findall(&#039;.\/\/item&#039;)<\/code>\u3002<\/p>\n<\/p>\n<p><p>\u63a5\u4e0b\u6765\uff0c\u4e3e\u4f8b\u8be6\u7ec6\u8bf4\u660e\u6574\u4e2a\u5904\u7406\u8fc7\u7a0b\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u5b89\u88c5\u5e76\u5bfc\u5165\u5fc5\u8981\u7684\u5e93<\/h3>\n<\/p>\n<p><p>\u5728Python\u4e2d\uff0c\u9996\u5148\u9700\u8981\u5b89\u88c5<code>requests<\/code>\u5e93\uff08\u5982\u679c\u5c1a\u672a\u5b89\u88c5\u7684\u8bdd\uff09\uff0c\u53ef\u4ee5\u901a\u8fc7\u4e0b\u9762\u7684\u547d\u4ee4\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code>pip install requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u7136\u540e\u5728\u4ee3\u7801\u4e2d\uff0c\u5bfc\u5165<code>requests<\/code>\u5e93\u548c<code>xml.etree.ElementTree<\/code>\u6a21\u5757\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>import xml.etree.ElementTree as ET<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001\u53d1\u8d77HTTP\u8bf7\u6c42\u83b7\u53d6XML\u6570\u636e<\/h3>\n<\/p>\n<p><p>\u63a5\u4e0b\u6765\uff0c\u4f7f\u7528<code>requests<\/code>\u53d1\u9001HTTP\u8bf7\u6c42\u5230\u6307\u5b9a\u7684\u63a5\u53e3URL\uff0c\u83b7\u53d6\u8fd4\u56de\u7684XML\u6570\u636e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">url = &#039;\u63a5\u53e3URL&#039;<\/p>\n<p>response = requests.get(url)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u786e\u4fdd\u8bf7\u6c42\u6210\u529f\u540e\uff0c\u7ee7\u7eed\u5904\u7406\u54cd\u5e94\u4e2d\u7684XML\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">xml_data = response.text<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u89e3\u6790XML\u6570\u636e<\/h3>\n<\/p>\n<p><p>\u5229\u7528<code>xml.etree.ElementTree<\/code>\u4e2d\u7684<code>XML()<\/code>\u65b9\u6cd5\uff0c\u53ef\u4ee5\u5c06\u5b57\u7b26\u4e32\u683c\u5f0f\u7684XML\u6570\u636e\u8f6c\u6362\u4e3a\u4e00\u4e2a\u89e3\u6790\u540e\u7684XML\u5143\u7d20\u6811\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">root = ET.XML(xml_data)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p><code>root<\/code>\u53d8\u91cf\u73b0\u5728\u5c31\u4ee3\u8868\u4e86XML\u7684\u6839\u8282\u70b9\uff0c\u53ef\u4ee5\u4ece\u8fd9\u91cc\u5f00\u59cb\u904d\u5386\u548c\u67e5\u8be2\u3002<\/p>\n<\/p>\n<p><h3>\u56db\u3001\u8bbf\u95ee\u7279\u5b9a\u7684XML\u8282\u70b9<\/h3>\n<\/p>\n<p><p>\u5047\u8bbe\u4f60\u9700\u8981\u8bbf\u95ee\u6240\u6709\u540d\u4e3a<code>data<\/code>\u7684\u8282\u70b9\uff0c\u53ef\u4ee5\u4f7f\u7528<code>findall<\/code>\u65b9\u6cd5\u3002\u5982\u679cXML\u7ed3\u6784\u8f83\u4e3a\u590d\u6742\uff0c\u53ef\u80fd\u9700\u8981\u4f7f\u7528XPath\u8868\u8fbe\u5f0f\u6765\u5b9a\u4f4d\u8fd9\u4e9b\u8282\u70b9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">data_elements = root.findall(&#039;.\/\/data&#039;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e<\/h3>\n<\/p>\n<p><p>\u5bf9\u627e\u5230\u7684\u6bcf\u4e2a\u8282\u70b9\uff0c\u53ef\u4ee5\u4f7f\u7528<code>find<\/code>\u65b9\u6cd5\u6765\u83b7\u53d6\u5b50\u8282\u70b9\uff0c\u6216\u8005<code>attrib<\/code>\u5c5e\u6027\u6765\u83b7\u53d6\u8282\u70b9\u7684\u5c5e\u6027\u503c\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for elem in data_elements:<\/p>\n<p>    child = elem.find(&#039;child&#039;) # \u6539\u4e3a\u4f60\u9700\u8981\u67e5\u627e\u7684\u5b50\u8282\u70b9\u6807\u7b7e\u540d<\/p>\n<p>    attribute = elem.attrib.get(&#039;attribute_name&#039;) # \u6539\u4e3a\u4f60\u9700\u8981\u7684\u5c5e\u6027\u540d<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u6700\u540e\uff0c\u5bf9\u83b7\u53d6\u5230\u7684\u6570\u636e\u8fdb\u884c\u5904\u7406\u3001\u5b58\u50a8\u6216\u8f93\u51fa\uff0c\u6839\u636e\u5b9e\u9645\u9700\u6c42\u5b8c\u6210\u7279\u5b9a\u4efb\u52a1\u3002<\/p>\n<\/p>\n<p><h3>\u516d\u3001\u603b\u7ed3\u4e0e\u5b9e\u8df5<\/h3>\n<\/p>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u4f60\u53ef\u4ee5\u8bfb\u53d6\u5e76\u5904\u7406\u4efb\u4f55\u901a\u8fc7HTTP\u63a5\u53e3\u8fd4\u56de\u7684XML\u6570\u636e\u3002\u91cd\u8981\u7684\u662f\u8981\u7406\u89e3XML\u7684\u7ed3\u6784\u4ee5\u53ca\u5982\u4f55\u4f7f\u7528<code>ElementTree<\/code>\u6a21\u5757\u4e2d\u7684\u65b9\u6cd5\u6765\u67e5\u8be2\u548c\u64cd\u4f5cXML\u8282\u70b9\u3002\u968f\u7740\u7ecf\u9a8c\u7684\u79ef\u7d2f\uff0c\u4f60\u5c06\u80fd\u591f\u5feb\u901f\u5730\u4ece\u590d\u6742\u7684XML\u4e2d\u63d0\u53d6\u6240\u9700\u6570\u636e\uff0c\u5e76\u5c06\u8fd9\u4e9b\u6570\u636e\u5e94\u7528\u4e8e\u6570\u636e\u5206\u6790\u3001\u8f6c\u6362\u4e3a\u5176\u4ed6\u683c\u5f0f\u6216\u8fdb\u884c\u6570\u636e\u5e93\u5b58\u50a8\u7b49\u4efb\u52a1\u3002<\/p>\n<\/p>\n<p><p>\u5728\u5b9e\u8df5\u4e2d\uff0c\u8bf7\u8bb0\u4f4f\u68c0\u67e5\u63a5\u53e3\u7684\u8fd4\u56de\u72b6\u6001\u548c\u9519\u8bef\u5904\u7406\uff0c\u540c\u65f6\u4e5f\u8981\u6ce8\u610f\u5904\u7406\u5927\u578bXML\u6587\u4ef6\u65f6\u7684\u5185\u5b58\u4f7f\u7528\u95ee\u9898\u3002\u8fd9\u4e9b\u90fd\u662f\u5b9e\u73b0\u9ad8\u6548\u4e14\u5065\u58ee\u7684XML\u6570\u636e\u5904\u7406\u6d41\u7a0b\u7684\u91cd\u8981\u7ec4\u6210\u90e8\u5206\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p><strong>1. \u5982\u4f55\u4f7f\u7528Python\u8bfb\u53d6\u63a5\u53e3\u8fd4\u56de\u7684XML\u6570\u636e\uff1f<\/strong><\/p>\n<p>Python\u63d0\u4f9b\u4e86\u591a\u79cd\u5904\u7406XML\u6570\u636e\u7684\u5e93\uff0c\u5176\u4e2d\u6700\u5e38\u7528\u7684\u662f<code>xml.etree.ElementTree<\/code>\u6a21\u5757\u3002\u901a\u8fc7\u8be5\u6a21\u5757\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u8bfb\u53d6\u63a5\u53e3\u8fd4\u56de\u7684XML\u6570\u636e\u3002\u4ee5\u4e0b\u662f\u8bfb\u53d6XML\u6570\u636e\u7684\u7b80\u5355\u793a\u4f8b\uff1a<\/p>\n<pre><code class=\"language-python\">import xml.etree.ElementTree as ET\n\n# \u89e3\u6790XML\u6570\u636e\nxml_data = &#039;&#039;&#039;&lt;data&gt;\n    &lt;name&gt;John&lt;\/name&gt;\n    &lt;age&gt;30&lt;\/age&gt;\n    &lt;gender&gt;Male&lt;\/gender&gt;\n&lt;\/data&gt;&#039;&#039;&#039;\n\nroot = ET.fromstring(xml_data)\n\n# \u8bfb\u53d6XML\u6570\u636e\nname = root.find(&#039;name&#039;).text\nage = int(root.find(&#039;age&#039;).text)\ngender = root.find(&#039;gender&#039;).text\n\n# \u6253\u5370\u8bfb\u53d6\u7ed3\u679c\nprint(f&quot;Name: {name}&quot;)\nprint(f&quot;Age: {age}&quot;)\nprint(f&quot;Gender: {gender}&quot;)\n<\/code><\/pre>\n<p>\u8fd9\u6837\u5c31\u53ef\u4ee5\u901a\u8fc7<code>root.find()<\/code>\u65b9\u6cd5\u627e\u5230\u5bf9\u5e94\u7684XML\u8282\u70b9\uff0c\u5e76\u4f7f\u7528<code>text<\/code>\u5c5e\u6027\u83b7\u53d6\u8282\u70b9\u7684\u6587\u672c\u5185\u5bb9\u3002<\/p>\n<p><strong>2. \u5982\u4f55\u5904\u7406\u63a5\u53e3\u8fd4\u56de\u7684\u5d4c\u5957XML\u6570\u636e\uff1f<\/strong><\/p>\n<p>\u5982\u679c\u63a5\u53e3\u8fd4\u56de\u7684XML\u6570\u636e\u5b58\u5728\u5d4c\u5957\u7ed3\u6784\uff0c\u5373\u6709\u5b50\u8282\u70b9\u548c\u7236\u8282\u70b9\u7684\u5173\u7cfb\uff0c\u53ef\u4ee5\u901a\u8fc7\u9012\u5f52\u904d\u5386\u7684\u65b9\u5f0f\u5904\u7406\u5d4c\u5957XML\u6570\u636e\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a<\/p>\n<pre><code class=\"language-python\">import xml.etree.ElementTree as ET\n\ndef process_node(node):\n    # \u5904\u7406\u8282\u70b9\u6570\u636e\n    print(f&quot;Node Name: {node.tag}&quot;)\n    print(f&quot;Node Text: {node.text}&quot;)\n    print(&quot;&quot;)\n\n    # \u9012\u5f52\u5904\u7406\u5b50\u8282\u70b9\n    for child in node:\n        process_node(child)\n\n# \u89e3\u6790XML\u6570\u636e\nxml_data = &#039;&#039;&#039;&lt;data&gt;\n    &lt;person&gt;\n        &lt;name&gt;John&lt;\/name&gt;\n        &lt;age&gt;30&lt;\/age&gt;\n    &lt;\/person&gt;\n    &lt;person&gt;\n        &lt;name&gt;Jane&lt;\/name&gt;\n        &lt;age&gt;25&lt;\/age&gt;\n    &lt;\/person&gt;\n&lt;\/data&gt;&#039;&#039;&#039;\n\nroot = ET.fromstring(xml_data)\n\n# \u5904\u7406\u6839\u8282\u70b9\u53ca\u5176\u5b50\u8282\u70b9\nprocess_node(root)\n<\/code><\/pre>\n<p>\u901a\u8fc7\u9012\u5f52\u904d\u5386\u6bcf\u4e2a\u8282\u70b9\uff0c\u53ef\u4ee5\u83b7\u53d6\u5230\u6240\u6709\u5d4c\u5957XML\u6570\u636e\u7684\u5185\u5bb9\u3002<\/p>\n<p><strong>3. \u5982\u4f55\u5904\u7406\u63a5\u53e3\u8fd4\u56de\u7684\u5e26\u6709\u5c5e\u6027\u7684XML\u6570\u636e\uff1f<\/strong><\/p>\n<p>\u6709\u4e9b\u63a5\u53e3\u8fd4\u56de\u7684XML\u6570\u636e\u53ef\u80fd\u5b58\u5728\u8282\u70b9\u5c5e\u6027\uff0c\u800c\u4e0d\u4ec5\u4ec5\u662f\u6587\u672c\u5185\u5bb9\u3002\u53ef\u4ee5\u4f7f\u7528<code>Element.attrib<\/code>\u5c5e\u6027\u83b7\u53d6\u8282\u70b9\u7684\u5c5e\u6027\u4fe1\u606f\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a<\/p>\n<pre><code class=\"language-python\">import xml.etree.ElementTree as ET\n\n# \u89e3\u6790XML\u6570\u636e\nxml_data = &#039;&#039;&#039;&lt;data&gt;\n    &lt;person id=&quot;1&quot;&gt;\n        &lt;name&gt;John&lt;\/name&gt;\n        &lt;age&gt;30&lt;\/age&gt;\n    &lt;\/person&gt;\n    &lt;person id=&quot;2&quot;&gt;\n        &lt;name&gt;Jane&lt;\/name&gt;\n        &lt;age&gt;25&lt;\/age&gt;\n    &lt;\/person&gt;\n&lt;\/data&gt;&#039;&#039;&#039;\n\nroot = ET.fromstring(xml_data)\n\n# \u8bfb\u53d6\u5e26\u6709\u5c5e\u6027\u7684XML\u6570\u636e\nfor person in root.findall(&#039;person&#039;):\n    person_id = person.attrib[&#039;id&#039;]\n    name = person.find(&#039;name&#039;).text\n    age = int(person.find(&#039;age&#039;).text)\n\n    print(f&quot;Person ID: {person_id}&quot;)\n    print(f&quot;Name: {name}&quot;)\n    print(f&quot;Age: {age}&quot;)\n<\/code><\/pre>\n<p>\u901a\u8fc7<code>Element.attrib<\/code>\u53ef\u4ee5\u83b7\u53d6\u5230\u8282\u70b9\u7684\u5c5e\u6027\u5b57\u5178\uff0c\u4ece\u800c\u8bfb\u53d6\u5e26\u6709\u5c5e\u6027\u7684XML\u6570\u636e\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u8bfb\u53d6\u63a5\u53e3\u8fd4\u56de\u7684XML\u6570\u636e\u53ef\u5206\u4e3a\u4ee5\u4e0b\u6b65\u9aa4\uff1a\u5b89\u88c5\u5e76\u5bfc\u5165\u5fc5\u8981\u7684\u5e93\u3001\u53d1\u8d77HTTP\u8bf7\u6c42\u83b7\u53d6XML\u6570\u636e\u3001\u89e3\u6790X [&hellip;]","protected":false},"author":3,"featured_media":175200,"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\/175193"}],"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=175193"}],"version-history":[{"count":0,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/175193\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/175200"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=175193"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=175193"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=175193"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}