{"id":1071053,"date":"2025-01-08T11:03:47","date_gmt":"2025-01-08T03:03:47","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1071053.html"},"modified":"2025-01-08T11:03:50","modified_gmt":"2025-01-08T03:03:50","slug":"python%e5%a6%82%e4%bd%95%e6%8a%8axml%e5%8f%98%e6%88%90gb2312-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1071053.html","title":{"rendered":"python\u5982\u4f55\u628axml\u53d8\u6210gb2312"},"content":{"rendered":"

\"python\u5982\u4f55\u628axml\u53d8\u6210gb2312\"<\/p>\n

\u4f7f\u7528Python\u5c06XML\u6587\u4ef6\u8f6c\u6362\u4e3aGB2312\u7f16\u7801\u7684\u6b65\u9aa4\u5305\u62ec\uff1a\u8bfb\u53d6XML\u6587\u4ef6\u3001\u8fdb\u884c\u5185\u5bb9\u89e3\u6790\u3001\u5c06\u89e3\u6790\u540e\u7684\u5185\u5bb9\u8fdb\u884c\u7f16\u7801\u8f6c\u6362\u3001\u5e76\u5c06\u8f6c\u6362\u540e\u7684\u5185\u5bb9\u4fdd\u5b58\u5230\u65b0\u7684XML\u6587\u4ef6\u4e2d\u3002<\/strong><\/p>\n<\/p>\n

\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u7684\u5185\u7f6e\u6a21\u5757\u548c\u5e93\u5982xml.etree.ElementTree<\/code>\u3001io<\/code>\u3001codecs<\/code>\u6765\u5b9e\u73b0\u8fd9\u4e2a\u8fc7\u7a0b\u3002\u63a5\u4e0b\u6765\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u8fdb\u884c\u8fd9\u4e9b\u64cd\u4f5c\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u8bfb\u53d6\u548c\u89e3\u6790XML\u6587\u4ef6<\/h3>\n<\/p>\n

\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u8bfb\u53d6\u5e76\u89e3\u6790XML\u6587\u4ef6\u3002Python\u7684xml.etree.ElementTree<\/code>\u6a21\u5757\u662f\u4e00\u4e2a\u8f7b\u91cf\u7ea7\u7684\u5e93\uff0c\u9002\u7528\u4e8e\u5904\u7406XML\u6587\u4ef6\u3002<\/p>\n<\/p>\n

import xml.etree.ElementTree as ET<\/p>\n
\u8bfb\u53d6XML\u6587\u4ef6<\/strong><\/h2>\n
tree = ET.parse('input.xml')<\/p>\n
root = tree.getroot()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u91cc\uff0c\u6211\u4eec\u4f7f\u7528ET.parse<\/code>\u65b9\u6cd5\u8bfb\u53d6XML\u6587\u4ef6\uff0c\u5e76\u4f7f\u7528getroot<\/code>\u65b9\u6cd5\u83b7\u53d6XML\u7684\u6839\u5143\u7d20\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u5c06\u89e3\u6790\u540e\u7684\u5185\u5bb9\u7f16\u7801\u8f6c\u6362\u4e3aGB2312<\/h3>\n<\/p>\n
\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u9700\u8981\u5c06\u89e3\u6790\u540e\u7684\u5185\u5bb9\u8f6c\u6362\u4e3aGB2312\u7f16\u7801\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u7684codecs<\/code>\u6a21\u5757\u6765\u5b9e\u73b0\u8fd9\u4e00\u70b9\u3002<\/p>\n<\/p>\n
import codecs<\/p>\n
\u5c06XML\u5185\u5bb9\u8f6c\u6362\u4e3a\u5b57\u7b26\u4e32<\/strong><\/h2>\n
xml_str = ET.tostring(root, encoding='utf-8').decode('utf-8')<\/p>\n
\u5c06\u5b57\u7b26\u4e32\u8f6c\u6362\u4e3aGB2312\u7f16\u7801<\/strong><\/h2>\n
xml_gb2312 = xml_str.encode('gb2312')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u91cc\uff0c\u6211\u4eec\u9996\u5148\u5c06XML\u5185\u5bb9\u8f6c\u6362\u4e3a\u5b57\u7b26\u4e32\uff0c\u7136\u540e\u5c06\u5b57\u7b26\u4e32\u7f16\u7801\u4e3aGB2312\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u5c06\u8f6c\u6362\u540e\u7684\u5185\u5bb9\u4fdd\u5b58\u5230\u65b0\u7684XML\u6587\u4ef6\u4e2d<\/h3>\n<\/p>\n
\u6700\u540e\uff0c\u6211\u4eec\u9700\u8981\u5c06\u8f6c\u6362\u540e\u7684\u5185\u5bb9\u4fdd\u5b58\u5230\u65b0\u7684XML\u6587\u4ef6\u4e2d\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528codecs.open<\/code>\u65b9\u6cd5\u6765\u5b9e\u73b0\u8fd9\u4e00\u70b9\u3002<\/p>\n<\/p>\n
# \u5c06\u8f6c\u6362\u540e\u7684\u5185\u5bb9\u4fdd\u5b58\u5230\u65b0\u7684XML\u6587\u4ef6\u4e2d<\/p>\n
with codecs.open('output.xml', 'w', encoding='gb2312') as f:<\/p>\n
    f.write(xml_gb2312.decode('gb2312'))<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u91cc\uff0c\u6211\u4eec\u4f7f\u7528codecs.open<\/code>\u65b9\u6cd5\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\uff0c\u5e76\u5c06\u8f6c\u6362\u540e\u7684\u5185\u5bb9\u5199\u5165\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n
\u5b8c\u6574\u4ee3\u7801\u793a\u4f8b<\/h3>\n<\/p>\n
import xml.etree.ElementTree as ET<\/p>\n
import codecs<\/p>\n
\u8bfb\u53d6XML\u6587\u4ef6<\/strong><\/h2>\n
tree = ET.parse('input.xml')<\/p>\n
root = tree.getroot()<\/p>\n
\u5c06XML\u5185\u5bb9\u8f6c\u6362\u4e3a\u5b57\u7b26\u4e32<\/strong><\/h2>\n
xml_str = ET.tostring(root, encoding='utf-8').decode('utf-8')<\/p>\n
\u5c06\u5b57\u7b26\u4e32\u8f6c\u6362\u4e3aGB2312\u7f16\u7801<\/strong><\/h2>\n
xml_gb2312 = xml_str.encode('gb2312')<\/p>\n
\u5c06\u8f6c\u6362\u540e\u7684\u5185\u5bb9\u4fdd\u5b58\u5230\u65b0\u7684XML\u6587\u4ef6\u4e2d<\/strong><\/h2>\n
with codecs.open('output.xml', 'w', encoding='gb2312') as f:<\/p>\n
    f.write(xml_gb2312.decode('gb2312'))<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u5904\u7406XML\u6587\u4ef6\u4e2d\u7684\u7279\u6b8a\u5b57\u7b26<\/h3>\n<\/p>\n
\u5728\u5904\u7406XML\u6587\u4ef6\u65f6\uff0c\u6211\u4eec\u53ef\u80fd\u4f1a\u9047\u5230\u4e00\u4e9b\u7279\u6b8a\u5b57\u7b26\uff08\u5982&<\/code>\u3001<<\/code>\u3001><\/code>\u7b49\uff09\uff0c\u8fd9\u4e9b\u5b57\u7b26\u9700\u8981\u8fdb\u884c\u7279\u6b8a\u5904\u7406\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528xml.sax.saxutils<\/code>\u6a21\u5757\u4e2d\u7684escape<\/code>\u51fd\u6570\u6765\u8f6c\u4e49\u8fd9\u4e9b\u7279\u6b8a\u5b57\u7b26\u3002<\/p>\n<\/p>\n
from xml.sax.saxutils import escape<\/p>\n
\u5c06XML\u5185\u5bb9\u8f6c\u6362\u4e3a\u5b57\u7b26\u4e32\u5e76\u8f6c\u4e49\u7279\u6b8a\u5b57\u7b26<\/strong><\/h2>\n
xml_str = ET.tostring(root, encoding='utf-8').decode('utf-8')<\/p>\n
xml_str = escape(xml_str)<\/p>\n
\u5c06\u5b57\u7b26\u4e32\u8f6c\u6362\u4e3aGB2312\u7f16\u7801<\/strong><\/h2>\n
xml_gb2312 = xml_str.encode('gb2312')<\/p>\n
\u5c06\u8f6c\u6362\u540e\u7684\u5185\u5bb9\u4fdd\u5b58\u5230\u65b0\u7684XML\u6587\u4ef6\u4e2d<\/strong><\/h2>\n
with codecs.open('output.xml', 'w', encoding='gb2312') as f:<\/p>\n
    f.write(xml_gb2312.decode('gb2312'))<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u4f7f\u7528BeautifulSoup\u5904\u7406XML\u6587\u4ef6<\/h3>\n<\/p>\n
\u9664\u4e86xml.etree.ElementTree<\/code>\u6a21\u5757\uff0c\u6211\u4eec\u8fd8\u53ef\u4ee5\u4f7f\u7528BeautifulSoup<\/code>\u5e93\u6765\u5904\u7406XML\u6587\u4ef6\u3002BeautifulSoup<\/code>\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u5e93\uff0c\u9002\u7528\u4e8e\u5904\u7406\u590d\u6742\u7684XML\u6587\u4ef6\u3002<\/p>\n<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
import codecs<\/p>\n
\u8bfb\u53d6XML\u6587\u4ef6<\/strong><\/h2>\n
with open('input.xml', 'r', encoding='utf-8') as f:<\/p>\n
    xml_str = f.read()<\/p>\n
\u89e3\u6790XML\u6587\u4ef6<\/strong><\/h2>\n
soup = BeautifulSoup(xml_str, 'xml')<\/p>\n
\u5c06\u89e3\u6790\u540e\u7684\u5185\u5bb9\u8f6c\u6362\u4e3aGB2312\u7f16\u7801<\/strong><\/h2>\n
xml_gb2312 = soup.prettify().encode('gb2312')<\/p>\n
\u5c06\u8f6c\u6362\u540e\u7684\u5185\u5bb9\u4fdd\u5b58\u5230\u65b0\u7684XML\u6587\u4ef6\u4e2d<\/strong><\/h2>\n
with codecs.open('output.xml', 'w', encoding='gb2312') as f:<\/p>\n
    f.write(xml_gb2312.decode('gb2312'))<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u91cc\uff0c\u6211\u4eec\u9996\u5148\u4f7f\u7528BeautifulSoup<\/code>\u5e93\u89e3\u6790XML\u6587\u4ef6\uff0c\u7136\u540e\u5c06\u89e3\u6790\u540e\u7684\u5185\u5bb9\u8f6c\u6362\u4e3aGB2312\u7f16\u7801\uff0c\u6700\u540e\u5c06\u8f6c\u6362\u540e\u7684\u5185\u5bb9\u4fdd\u5b58\u5230\u65b0\u7684XML\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n
\u516d\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u4f7f\u7528Python\u5c06XML\u6587\u4ef6\u8f6c\u6362\u4e3aGB2312\u7f16\u7801\u7684\u8fc7\u7a0b\u5305\u62ec\uff1a\u8bfb\u53d6\u548c\u89e3\u6790XML\u6587\u4ef6\u3001\u5c06\u89e3\u6790\u540e\u7684\u5185\u5bb9\u8fdb\u884c\u7f16\u7801\u8f6c\u6362\u3001\u5e76\u5c06\u8f6c\u6362\u540e\u7684\u5185\u5bb9\u4fdd\u5b58\u5230\u65b0\u7684XML\u6587\u4ef6\u4e2d\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u7684\u5185\u7f6e\u6a21\u5757\u548c\u5e93\u5982xml.etree.ElementTree<\/code>\u3001BeautifulSoup<\/code>\u3001codecs<\/code>\u6765\u5b9e\u73b0\u8fd9\u4e2a\u8fc7\u7a0b\u3002\u5728\u5904\u7406XML\u6587\u4ef6\u4e2d\u7684\u7279\u6b8a\u5b57\u7b26\u65f6\uff0c\u6211\u4eec\u8fd8\u53ef\u4ee5\u4f7f\u7528xml.sax.saxutils<\/code>\u6a21\u5757\u4e2d\u7684escape<\/code>\u51fd\u6570\u8fdb\u884c\u5904\u7406\u3002\u901a\u8fc7\u8fd9\u4e9b\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u5730\u5c06XML\u6587\u4ef6\u8f6c\u6362\u4e3aGB2312\u7f16\u7801\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5728Python\u4e2d\u5c06XML\u6587\u4ef6\u8f6c\u6362\u4e3aGB2312\u7f16\u7801\uff1f<\/strong>
\u8981\u5c06XML\u6587\u4ef6\u8f6c\u6362\u4e3aGB2312\u7f16\u7801\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u7684\u6807\u51c6\u5e93xml.etree.ElementTree<\/code>\u6765\u89e3\u6790XML\u6587\u4ef6\uff0c\u7136\u540e\u4f7f\u7528open<\/code>\u51fd\u6570\u4ee5GB2312\u7f16\u7801\u91cd\u65b0\u5199\u5165\u6587\u4ef6\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\u4ee3\u7801\uff1a  <\/p>\n
import xml.etree.ElementTree as ET\n\n# \u89e3\u6790XML\u6587\u4ef6\ntree = ET.parse('input.xml')\nroot = tree.getroot()\n\n# \u5c06XML\u5185\u5bb9\u5199\u5165\u65b0\u7684GB2312\u7f16\u7801\u6587\u4ef6\nwith open('output.xml', 'w', encoding='gb2312') as f:\n    f.write(ET.tostring(root, encoding='unicode'))\n<\/code><\/pre>\n
\u8fd9\u4e2a\u793a\u4f8b\u5c06\u8bfb\u53d6\u4e00\u4e2a\u540d\u4e3ainput.xml<\/code>\u7684\u6587\u4ef6\uff0c\u5e76\u5c06\u5176\u8f6c\u6362\u4e3aGB2312\u7f16\u7801\u540e\u4fdd\u5b58\u4e3aoutput.xml<\/code>\u3002<\/p>\n
\u5728\u8f6c\u6362\u8fc7\u7a0b\u4e2d\u5982\u4f55\u5904\u7406XML\u4e2d\u7684\u7279\u6b8a\u5b57\u7b26\uff1f<\/strong>
\u5728\u5c06XML\u6587\u4ef6\u8f6c\u6362\u4e3aGB2312\u7f16\u7801\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u7279\u6b8a\u5b57\u7b26\uff08\u5982\u4e2d\u6587\u5b57\u7b26\uff09\u7684\u95ee\u9898\u3002\u8fd9\u4e9b\u5b57\u7b26\u53ef\u80fd\u65e0\u6cd5\u5728GB2312\u7f16\u7801\u4e2d\u6b63\u786e\u8868\u793a\u3002\u4e3a\u4e86\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\uff0c\u53ef\u4ee5\u5728\u8bfb\u53d6\u548c\u5199\u5165\u8fc7\u7a0b\u4e2d\u4f7f\u7528html<\/code>\u5e93\u7684escape<\/code>\u65b9\u6cd5\u6765\u8f6c\u4e49\u8fd9\u4e9b\u7279\u6b8a\u5b57\u7b26\u3002\u4f8b\u5982\uff1a  <\/p>\n
import xml.etree.ElementTree as ET\nimport html\n\n# \u89e3\u6790XML\u6587\u4ef6\ntree = ET.parse('input.xml')\nroot = tree.getroot()\n\n# \u8f6c\u4e49\u7279\u6b8a\u5b57\u7b26\u5e76\u5199\u5165GB2312\u7f16\u7801\u6587\u4ef6\nwith open('output.xml', 'w', encoding='gb2312') as f:\n    f.write(html.escape(ET.tostring(root, encoding='unicode')))\n<\/code><\/pre>\n
\u8fd9\u6837\u53ef\u4ee5\u786e\u4fdd\u5728\u8f6c\u6362\u8fc7\u7a0b\u4e2d\u4e0d\u4f1a\u4e22\u5931\u4efb\u4f55\u91cd\u8981\u4fe1\u606f\u3002<\/p>\n
\u4f7f\u7528Python\u7684\u5176\u4ed6\u5e93\u8f6c\u6362XML\u7f16\u7801\u6709\u4ec0\u4e48\u4f18\u52bf\uff1f<\/strong>
\u9664\u4e86xml.etree.ElementTree<\/code>\u5916\uff0c\u4f7f\u7528\u5176\u4ed6\u5e93\u5982lxml<\/code>\u6216BeautifulSoup<\/code>\u4e5f\u80fd\u8fdb\u884cXML\u7f16\u7801\u8f6c\u6362\u3002\u8fd9\u4e9b\u5e93\u901a\u5e38\u63d0\u4f9b\u66f4\u5f3a\u5927\u7684\u529f\u80fd\uff0c\u6bd4\u5982\u66f4\u597d\u7684\u89e3\u6790\u6027\u80fd\u548c\u66f4\u591a\u7684\u5904\u7406\u9009\u9879\u3002\u4f7f\u7528lxml<\/code>\u7684\u793a\u4f8b\u4ee3\u7801\u5982\u4e0b\uff1a  <\/p>\n
from lxml import etree\n\n# \u8bfb\u53d6XML\u6587\u4ef6\nwith open('input.xml', 'rb') as f:\n    content = f.read()\n\n# \u89e3\u6790\u5e76\u8f6c\u6362\u7f16\u7801\nroot = etree.fromstring(content)\nwith open('output.xml', 'wb') as f:\n    f.write(etree.tostring(root, encoding='gb2312', xml_declaration=True))\n<\/code><\/pre>\n
\u9009\u62e9\u5408\u9002\u7684\u5e93\u53ef\u4ee5\u63d0\u9ad8\u4ee3\u7801\u7684\u7075\u6d3b\u6027\u548c\u53ef\u7ef4\u62a4\u6027\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4f7f\u7528Python\u5c06XML\u6587\u4ef6\u8f6c\u6362\u4e3aGB2312\u7f16\u7801\u7684\u6b65\u9aa4\u5305\u62ec\uff1a\u8bfb\u53d6XML\u6587\u4ef6\u3001\u8fdb\u884c\u5185\u5bb9\u89e3\u6790\u3001\u5c06\u89e3\u6790\u540e\u7684\u5185\u5bb9\u8fdb\u884c […]","protected":false},"author":3,"featured_media":1071061,"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\/1071053"}],"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=1071053"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1071053\/revisions"}],"predecessor-version":[{"id":1071062,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1071053\/revisions\/1071062"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1071061"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1071053"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1071053"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1071053"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}