{"id":22,"date":"2022-06-23T02:05:16","date_gmt":"2022-06-22T18:05:16","guid":{"rendered":"http:\/\/vigeek.cn\/?p=22"},"modified":"2025-04-26T21:23:23","modified_gmt":"2025-04-26T13:23:23","slug":"python-shi-xian-docx-wen-ben-ti-huan","status":"publish","type":"post","link":"https:\/\/www.vigeek.cn\/index.php\/2022\/06\/23\/python-shi-xian-docx-wen-ben-ti-huan\/","title":{"rendered":"python \u5b9e\u73b0 docx \u6587\u672c\u66ff\u6362"},"content":{"rendered":"<h2 id=\"title-0\">\u76ee\u7684<\/h2>\n<p>\u7531\u4e8e\u5546\u4e1a\u539f\u56e0\uff0c\u6700\u8fd1\u8981\u5b9e\u73b0\u4e00\u4e2a\u529f\u80fd\uff0c\u5c31\u662fword\u6587\u6863 \uff08docx\u683c\u5f0f\uff09\u7684\u6279\u91cf\u6587\u672c\u66ff\u6362\uff0c\u628adocx\u4e2d\u7684\u5546\u6807\u540d\u6362\u6210\u81ea\u5df1\u7684\uff0c\u66ff\u6362\u8fc7\u7a0b\u4e2d\u8981\u4fdd\u7559word\u6587\u6863\u7684\u6837\u5f0f\u3002<br \/>\n\u5728\u7f51\u4e0a\u641c\u5bfb\u591a\u79cd\u65b9\u6848\uff0c\u6709 python-docx, \u6709 apache poi, \u5747\u4e0d\u7b26\u5408\u6211\u7684\u8981\u6c42\uff0c\u4e3b\u8981\u662f \u8fd9\u4e9b\u5e93 \u89e3\u6790docx\u6587\u6863 \u80fd\u529b\u6709\u9650\uff0c\u6587\u6863\u4e0d\u5168\uff0c\u800c\u4e14\u6709\u7684\u5185\u5bb9\u65e0\u6cd5\u8bc6\u522b\u5230\uff0c<br \/>\n\u6709\u7684\u5373\u4f7f\u66ff\u6362\u4e86\uff0c\u6837\u5f0f\u4e5f\u4e71\u4e86\uff0c\u4e0b\u9762\u662f\u6211\u81ea\u5df1\u7684\u65b9\u6848\uff0c\u6548\u679c\u582a\u79f0\u5b8c\u7f8e\u3002<\/p>\n<h2 id=\"title-1\">\u601d\u8def<\/h2>\n<p>docx \u6587\u4ef6\u5176\u5b9e\u662fzip\u6587\u4ef6\uff0c\u5728windows\u4e0a\uff0c\u6211\u4eec\u5c06docx\u6587\u4ef6\u91cd\u547d\u540d\u4e3azip\u6587\u4ef6\uff0c\u89e3\u538b\uff0c\u5373\u53ef\u5f97\u5230\u4e0b\u9762\u7684\u6587\u4ef6\uff1a<\/p>\n<div class=\"post-image\"><a class=\"fancybox\" title=\"\" href=\"https:\/\/xiaxudong.com\/wp-content\/uploads\/2022\/03\/202203151607338.png\" rel=\"box\" class=\"fancybox\" rel=\"box\" data-original-title=\"\"><img decoding=\"async\" class=\"aligncenter size-full wp-image-152\" src=\"https:\/\/xiaxudong.com\/wp-content\/uploads\/2022\/03\/202203151607338.png\" alt=\"docx\u6587\u4ef6\u89e3\u538b\u540e\u7684\u5185\u5bb9\" \/><\/a><\/div>\n<p>\u53ef\u4ee5\u770b\u5230 docx\u6587\u4ef6\u672c\u8d28\u662f \u8d44\u6e90\u6587\u4ef6 + xml \u6587\u4ef6\u7684\u96c6\u5408\uff0c\u800c word\u6587\u6863\u4e2d\u7684\u6587\u5b57 \u90fd\u5728 word\/document.xml \u4e2d\u3002<br \/>\n\u6211\u4eec\u53ea\u8981\u66ff\u6362\u8fd9\u4e2a\u6587\u4ef6\uff0c\u518d\u91cd\u65b0\u538b\u7f29\u4e3azip,\u518d\u6539\u6210.docx\u683c\u5f0f \uff0c\u5373\u53ef\u5b9e\u73b0\u66ff\u6362\u3002<\/p>\n<h2 id=\"title-2\">\u4ee3\u7801\u5b9e\u73b0<\/h2>\n<ol class=\"linenums\">\n<li class=\"L0\"><span class=\"kwd\">import<\/span><span class=\"pln\"> zipfile<\/span><\/li>\n<li class=\"L1\"><span class=\"kwd\">import<\/span><span class=\"pln\"> shutil<\/span><\/li>\n<li class=\"L2\"><span class=\"kwd\">import<\/span><span class=\"pln\"> os<\/span><\/li>\n<li class=\"L3\"><span class=\"pln\">\u00a0<\/span><\/li>\n<li class=\"L4\"><span class=\"kwd\">import<\/span><span class=\"pln\"> file_util<\/span><\/li>\n<li class=\"L5\"><span class=\"pln\">\u00a0<\/span><\/li>\n<li class=\"L6\"><span class=\"str\">'''<\/span><\/li>\n<li class=\"L7\"><span class=\"str\">input_f \u8f93\u5165\u6587\u4ef6\u8def\u5f84<\/span><\/li>\n<li class=\"L8\"><span class=\"str\">out_f \u8f93\u51fa\u6587\u4ef6\u8def\u5f84<\/span><\/li>\n<li class=\"L9\"><span class=\"str\">'''<\/span><\/li>\n<li class=\"L0\"><span class=\"pln\">\u00a0<\/span><\/li>\n<li class=\"L1\"><span class=\"pln\">\u00a0<\/span><\/li>\n<li class=\"L2\"><span class=\"kwd\">def<\/span><span class=\"pln\"> replace_text<\/span><span class=\"pun\">(<\/span><span class=\"pln\">input_f<\/span><span class=\"pun\">,<\/span><span class=\"pln\"> out_f<\/span><span class=\"pun\">):<\/span><\/li>\n<li class=\"L3\"><span class=\"pln\"> owd <\/span><span class=\"pun\">=<\/span><span class=\"pln\"> os<\/span><span class=\"pun\">.<\/span><span class=\"pln\">getcwd<\/span><span class=\"pun\">()<\/span><\/li>\n<li class=\"L4\"><span class=\"com\"># \u5c06\u6dd8\u5b9d\u66ff\u6362\u4e3a\u4eac\u4e1c<\/span><\/li>\n<li class=\"L5\"><span class=\"pln\"> replacements <\/span><span class=\"pun\">=<\/span> <span class=\"pun\">{<\/span><\/li>\n<li class=\"L6\"><span class=\"str\">'\u6dd8\u5b9d'<\/span><span class=\"pun\">:<\/span> <span class=\"str\">'\u4eac\u4e1c'<\/span><span class=\"pun\">,<\/span><\/li>\n<li class=\"L7\"><span class=\"pun\">}<\/span><\/li>\n<li class=\"L8\"><span class=\"pln\"> tmp_dir <\/span><span class=\"pun\">=<\/span> <span class=\"str\">\"D:\\\\BaiduNetdiskDownload\\\\tmp\\\\\"<\/span><\/li>\n<li class=\"L9\"><span class=\"kwd\">try<\/span><span class=\"pun\">:<\/span><\/li>\n<li class=\"L0\"><span class=\"pln\"> filename <\/span><span class=\"pun\">=<\/span><span class=\"pln\"> input_f<\/span><span class=\"pun\">.<\/span><span class=\"pln\">split<\/span><span class=\"pun\">(<\/span><span class=\"str\">\"\\\\\"<\/span><span class=\"pun\">)[-<\/span><span class=\"lit\">1<\/span><span class=\"pun\">]<\/span><\/li>\n<li class=\"L1\"><span class=\"pln\"> os<\/span><span class=\"pun\">.<\/span><span class=\"pln\">chdir<\/span><span class=\"pun\">(<\/span><span class=\"pln\">tmp_dir<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L2\"><span class=\"pln\"> shutil<\/span><span class=\"pun\">.<\/span><span class=\"pln\">copy<\/span><span class=\"pun\">(<\/span><span class=\"pln\">input_f<\/span><span class=\"pun\">,<\/span><span class=\"pln\"> tmp_dir<\/span><span class=\"pun\">)<\/span> <span class=\"com\"># \u590d\u5236\u5230\u4e34\u65f6\u76ee\u5f55<\/span><\/li>\n<li class=\"L3\"><span class=\"pln\"> copy_file <\/span><span class=\"pun\">=<\/span><span class=\"pln\"> os<\/span><span class=\"pun\">.<\/span><span class=\"pln\">path<\/span><span class=\"pun\">.<\/span><span class=\"pln\">join<\/span><span class=\"pun\">(<\/span><span class=\"pln\">tmp_dir<\/span><span class=\"pun\">,<\/span><span class=\"pln\"> filename<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L4\"><span class=\"pln\"> zip_file <\/span><span class=\"pun\">=<\/span><span class=\"pln\"> copy_file<\/span><span class=\"pun\">.<\/span><span class=\"pln\">replace<\/span><span class=\"pun\">(<\/span><span class=\"str\">\".docx\"<\/span><span class=\"pun\">,<\/span> <span class=\"str\">\".zip\"<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L5\"><span class=\"pln\"> os<\/span><span class=\"pun\">.<\/span><span class=\"pln\">rename<\/span><span class=\"pun\">(<\/span><span class=\"pln\">copy_file<\/span><span class=\"pun\">,<\/span><span class=\"pln\"> zip_file<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L6\"><span class=\"com\"># \u89e3\u538b\u6587\u4ef6<\/span><\/li>\n<li class=\"L7\"><span class=\"kwd\">with<\/span><span class=\"pln\"> zipfile<\/span><span class=\"pun\">.<\/span><span class=\"typ\">ZipFile<\/span><span class=\"pun\">(<\/span><span class=\"pln\">zip_file<\/span><span class=\"pun\">,<\/span> <span class=\"str\">\"r\"<\/span><span class=\"pun\">)<\/span> <span class=\"kwd\">as<\/span><span class=\"pln\"> zip_ref<\/span><span class=\"pun\">:<\/span><\/li>\n<li class=\"L8\"><span class=\"pln\"> zip_ref<\/span><span class=\"pun\">.<\/span><span class=\"pln\">extractall<\/span><span class=\"pun\">(<\/span><span class=\"pln\">tmp_dir<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L9\"><span class=\"pln\"> os<\/span><span class=\"pun\">.<\/span><span class=\"pln\">remove<\/span><span class=\"pun\">(<\/span><span class=\"pln\">zip_file<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L0\"><span class=\"com\"># \u66ff\u6362\u6587\u672c<\/span><\/li>\n<li class=\"L1\"><span class=\"kwd\">with<\/span><span class=\"pln\"> open<\/span><span class=\"pun\">(<\/span><span class=\"str\">'word\\\\document.xml'<\/span><span class=\"pun\">,<\/span> <span class=\"str\">'r'<\/span><span class=\"pun\">,<\/span><span class=\"pln\"> encoding<\/span><span class=\"pun\">=<\/span><span class=\"str\">\"utf8\"<\/span><span class=\"pun\">)<\/span> <span class=\"kwd\">as<\/span><span class=\"pln\"> file<\/span><span class=\"pun\">:<\/span><\/li>\n<li class=\"L2\"><span class=\"pln\"> str <\/span><span class=\"pun\">=<\/span><span class=\"pln\"> file<\/span><span class=\"pun\">.<\/span><span class=\"pln\">read<\/span><span class=\"pun\">()<\/span><\/li>\n<li class=\"L3\"><span class=\"kwd\">for<\/span><span class=\"pln\"> k<\/span><span class=\"pun\">,<\/span><span class=\"pln\"> v <\/span><span class=\"kwd\">in<\/span><span class=\"pln\"> replacements<\/span><span class=\"pun\">.<\/span><span class=\"pln\">items<\/span><span class=\"pun\">():<\/span><\/li>\n<li class=\"L4\"><span class=\"pln\"> str <\/span><span class=\"pun\">=<\/span><span class=\"pln\"> str<\/span><span class=\"pun\">.<\/span><span class=\"pln\">replace<\/span><span class=\"pun\">(<\/span><span class=\"pln\">k<\/span><span class=\"pun\">,<\/span><span class=\"pln\"> v<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L5\"><span class=\"pln\"> text_file <\/span><span class=\"pun\">=<\/span><span class=\"pln\"> open<\/span><span class=\"pun\">(<\/span><span class=\"str\">\"out.xml\"<\/span><span class=\"pun\">,<\/span> <span class=\"str\">\"w\"<\/span><span class=\"pun\">,<\/span><span class=\"pln\"> encoding<\/span><span class=\"pun\">=<\/span><span class=\"str\">\"utf8\"<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L6\"><span class=\"pln\"> n <\/span><span class=\"pun\">=<\/span><span class=\"pln\"> text_file<\/span><span class=\"pun\">.<\/span><span class=\"pln\">write<\/span><span class=\"pun\">(<\/span><span class=\"pln\">str<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L7\"><span class=\"pln\"> text_file<\/span><span class=\"pun\">.<\/span><span class=\"pln\">close<\/span><span class=\"pun\">()<\/span><\/li>\n<li class=\"L8\"><span class=\"pln\">\u00a0<\/span><\/li>\n<li class=\"L9\"><span class=\"com\"># close input and output files<\/span><\/li>\n<li class=\"L0\"><span class=\"pln\"> os<\/span><span class=\"pun\">.<\/span><span class=\"pln\">remove<\/span><span class=\"pun\">(<\/span><span class=\"str\">\"word\\\\document.xml\"<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L1\"><span class=\"pln\"> os<\/span><span class=\"pun\">.<\/span><span class=\"pln\">rename<\/span><span class=\"pun\">(<\/span><span class=\"str\">\"out.xml\"<\/span><span class=\"pun\">,<\/span> <span class=\"str\">\"word\\\\document.xml\"<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L2\"><span class=\"com\"># \u91cd\u547d\u540d\u6587\u4ef6<\/span><\/li>\n<li class=\"L3\"><span class=\"pln\"> dst_zip_file_name <\/span><span class=\"pun\">=<\/span><span class=\"pln\"> filename<\/span><span class=\"pun\">.<\/span><span class=\"pln\">replace<\/span><span class=\"pun\">(<\/span><span class=\"str\">\".docx\"<\/span><span class=\"pun\">,<\/span> <span class=\"str\">\".zip\"<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L4\"><span class=\"pln\"> shutil<\/span><span class=\"pun\">.<\/span><span class=\"pln\">make_archive<\/span><span class=\"pun\">(<\/span><span class=\"pln\">filename<\/span><span class=\"pun\">.<\/span><span class=\"pln\">replace<\/span><span class=\"pun\">(<\/span><span class=\"str\">\".docx\"<\/span><span class=\"pun\">,<\/span> <span class=\"str\">\"\"<\/span><span class=\"pun\">),<\/span> <span class=\"str\">'zip'<\/span><span class=\"pun\">,<\/span><span class=\"pln\"> tmp_dir<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L5\"><span class=\"pln\"> os<\/span><span class=\"pun\">.<\/span><span class=\"pln\">rename<\/span><span class=\"pun\">(<\/span><span class=\"pln\">dst_zip_file_name<\/span><span class=\"pun\">,<\/span><span class=\"pln\"> out_f<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L6\"><span class=\"kwd\">except<\/span> <span class=\"typ\">Exception<\/span> <span class=\"kwd\">as<\/span><span class=\"pln\"> e<\/span><span class=\"pun\">:<\/span><\/li>\n<li class=\"L7\"><span class=\"kwd\">pass<\/span><\/li>\n<li class=\"L8\"><span class=\"kwd\">finally<\/span><span class=\"pun\">:<\/span><\/li>\n<li class=\"L9\"><span class=\"com\"># \u5c06\u4e34\u65f6\u76ee\u5f55\u6e05\u7a7a<\/span><\/li>\n<li class=\"L0\"><span class=\"pln\"> file_util<\/span><span class=\"pun\">.<\/span><span class=\"pln\">clean_dir<\/span><span class=\"pun\">(<\/span><span class=\"pln\">tmp_dir<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L1\"><span class=\"pln\"> os<\/span><span class=\"pun\">.<\/span><span class=\"pln\">chdir<\/span><span class=\"pun\">(<\/span><span class=\"pln\">owd<\/span><span class=\"pun\">)<\/span><\/li>\n<li class=\"L2\"><span class=\"pln\">\u00a0<\/span><\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>\u76ee\u7684 \u7531\u4e8e\u5546\u4e1a\u539f\u56e0\uff0c\u6700\u8fd1\u8981\u5b9e\u73b0\u4e00\u4e2a\u529f\u80fd\uff0c\u5c31\u662fword\u6587\u6863 \uff08docx\u683c\u5f0f\uff09\u7684\u6279\u91cf\u6587\u672c\u66ff\u6362\uff0c\u628adocx\u4e2d\u7684\u5546\u6807\u540d\u6362\u6210\u81ea\u5df1\u7684\uff0c\u66ff\u6362\u8fc7\u7a0b\u4e2d\u8981\u4fdd\u7559word\u6587\u6863\u7684\u6837\u5f0f\u3002 \u5728\u7f51\u4e0a\u641c\u5bfb\u591a\u79cd\u65b9\u6848\uff0c\u6709 python-docx, \u6709 apache poi, \u5747\u4e0d\u7b26\u5408\u6211\u7684\u8981\u6c42\uff0c\u4e3b\u8981\u662f \u8fd9\u4e9b\u5e93 \u89e3\u6790docx\u6587\u6863 \u80fd\u529b\u6709\u9650\uff0c...<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[],"special":[],"class_list":["post-22","post","type-post","status-publish","format-standard","hentry","category-hou-duan-ji-shu"],"_links":{"self":[{"href":"https:\/\/www.vigeek.cn\/index.php\/wp-json\/wp\/v2\/posts\/22","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.vigeek.cn\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.vigeek.cn\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.vigeek.cn\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.vigeek.cn\/index.php\/wp-json\/wp\/v2\/comments?post=22"}],"version-history":[{"count":1,"href":"https:\/\/www.vigeek.cn\/index.php\/wp-json\/wp\/v2\/posts\/22\/revisions"}],"predecessor-version":[{"id":40,"href":"https:\/\/www.vigeek.cn\/index.php\/wp-json\/wp\/v2\/posts\/22\/revisions\/40"}],"wp:attachment":[{"href":"https:\/\/www.vigeek.cn\/index.php\/wp-json\/wp\/v2\/media?parent=22"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.vigeek.cn\/index.php\/wp-json\/wp\/v2\/categories?post=22"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.vigeek.cn\/index.php\/wp-json\/wp\/v2\/tags?post=22"},{"taxonomy":"special","embeddable":true,"href":"https:\/\/www.vigeek.cn\/index.php\/wp-json\/wp\/v2\/special?post=22"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}