Python根據指定文件生成XML的方法
因項目需要根據指定格式的文件生成XML標注文件,可以方便使用LabelImg打開進行編輯和查看。其原始文件默認使用逗號進行分隔,如下所示:
在生成XML文件時,需要對其進行匯總,即將屬于同一個原始文件的切圖小文件的標注匯總到一起,其實現代碼如下所示:
import osfrom Logger import MyLoggerfrom xml.dom.minidom import Documentfrom collections import defaultdictimport reclass OpeateXML: def __init__(self, srcPath: str, targetPath: str, srcFileName: str): self._srcPath = srcPath self._targetPath = targetPath self._srcFileName = srcFileName def readSrcFileName(self, fileEncoding='utf8') -> dict: data = defaultdict(list) s = re.compile('.AIpng_d{1,}', re.IGNORECASE) srcFileFullPath = os.path.join(self._srcPath, self._srcFileName) try: with open(srcFileFullPath, mode='r', encoding=fileEncoding, errors='ignore') as fr:for content in fr.readlines(): data[s.sub('.AIpng',content.strip().split(',')[0])].append(content.strip()) except Exception as ex: MyLogger().error(f'OperateXML:read file error:n{ex}') return {} else: # data.sort(key=lambda x: x.strip().split(',')[0]) return data def createXML(self, data: dict, fileEncoding='utf8'): if data: try:for k,v in data.items(): doc = Document() # 創建根節點 rootNode = doc.createElement('annotation') # 添加根節點 doc.appendChild(rootNode) folder = doc.createElement('folder') folderText = doc.createTextNode(self._targetPath) folder.appendChild(folderText) rootNode.appendChild(folder) filename = doc.createElement('filename') filenameText = doc.createTextNode(k) filename.appendChild(filenameText) rootNode.appendChild(filename) path = doc.createElement('path') pathText = doc.createTextNode(os.path.join(self._targetPath,k)) path.appendChild(pathText) rootNode.appendChild(path) for i in v: tmpData = i.strip().split(',') if len(tmpData) == 6: _, ymin, xmin, ymax, xmax, labelName = tmpData objectObj = doc.createElement('object') rootNode.appendChild(objectObj) objectName = doc.createElement('name') objectNameText = doc.createTextNode(labelName) objectName.appendChild(objectNameText) objectObj.appendChild(objectName) objectBndBox = doc.createElement('bndbox') objectObj.appendChild(objectBndBox) objectBndBoxXmin = doc.createElement('xmin') objectBndBoxYmin = doc.createElement('ymin') objectBndBoxXmax = doc.createElement('xmax') objectBndBoxYmax = doc.createElement('ymax') objectBndBoxXminText = doc.createTextNode(xmin) objectBndBoxYminText = doc.createTextNode(ymin) objectBndBoxXmaxText = doc.createTextNode(xmax) objectBndBoxYmaxText = doc.createTextNode(ymax) objectBndBox.appendChild(objectBndBoxXmin) objectBndBox.appendChild(objectBndBoxYmin) objectBndBox.appendChild(objectBndBoxXmax) objectBndBox.appendChild(objectBndBoxYmax) objectBndBoxXmin.appendChild(objectBndBoxXminText) objectBndBoxYmin.appendChild(objectBndBoxYminText) objectBndBoxXmax.appendChild(objectBndBoxXmaxText) objectBndBoxYmax.appendChild(objectBndBoxYmaxText) objectObj.appendChild(objectBndBox) else: continue # save xml xmlName=os.path.splitext(k)[0]+'.xml' targetPath = os.path.join(self._targetPath, xmlName) with open(targetPath, mode='w', encoding=fileEncoding) as fw: doc.writexml(fw, indent='t', newl='n', addindent='t', encoding=fileEncoding) except Exception as ex:MyLogger().error(f'OperateXML:Save xml errorn{ex}')returnif __name__ == ’__main__’: srcPath = r'C:UsersSurpassDocumentsPycharmProjectsdataTEST-8outs' srcName = 'locations.txt' targetPath = r'C:UsersSurpassDocumentsPycharmProjectsdataTEST-8outsin_number' operateXML = OpeateXML(srcPath, targetPath, srcName) a = operateXML.readSrcFileName() operateXML.createXML(a)
最終生成的XML效果如下所示:
在LabelImg中的效果如下所示:
PS:這里再為大家提供幾款關于xml操作的在線工具供大家參考使用:
在線XML/JSON互相轉換工具:http://tools.jb51.net/code/xmljson
在線格式化XML/在線壓縮XML:http://tools.jb51.net/code/xmlformat
XML在線壓縮/格式化工具:http://tools.jb51.net/code/xml_format_compress
XML代碼在線格式化美化工具:http://tools.jb51.net/code/xmlcodeformat
對關于Python生成XML相關內容感興趣的讀者可查看本站專題:《Python操作xml數據技巧總結》
以上就是Python根據指定文件生成XML的方法的詳細內容,更多關于Python生成XML的資料請關注好吧啦網其它相關文章!
相關文章: