Python解析ofd文件

ofd文件解析步骤

• 参考文档

• 1、先import zipfile解压ofd文件，获得xml文件，然后在浏览器打开xml文件即可看到内容
  
  
  

• 2、再通过import xmltodict解析xml文件
  

• 3、完整代码如下

  # encoding: utf-8
  
  import zipfile
  import xmltodict
  import requests
  import os
  import shutil
  
  
  def unzip_file(zip_path, unzip_path=None):
      """
      :param zip_path: ofd格式文件路径
      :param unzip_path: 解压后的文件存放目录
      :return: unzip_path
      """
      if not unzip_path:
          unzip_path = zip_path.split('.')[0]
      with zipfile.ZipFile(zip_path, 'r') as f:
          for file in f.namelist():
              f.extract(file, path=unzip_path)
      return unzip_path
  
  
  def parse_ofd(content, path):
      """
      :param content: ofd文件字节内容
      :param path: ofd文件存取路径
      """
      with open(path, "wb") as f:
          f.write(content)
      file_path = unzip_file(path)
      xml_path = f"{file_path}/OFD.xml"
      data_dict = {}
      with open(xml_path, "r", encoding="utf-8") as f:
          _text = f.read()
          tree = xmltodict.parse(_text)
          # 以下解析部分
          for row in tree['ofd:OFD']['ofd:DocBody']['ofd:DocInfo']['ofd:CustomDatas']['ofd:CustomData']:
              data_dict[row['@Name']] = row.get('#text')
      shutil.rmtree(file_path)
      os.remove(path)
      return data_dict
  
  
  headers = {
      'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
      'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36',
  }
  ofd_url = "http://222.143.33.74/spyx_api/storage/upload/qianzhang/988d08768b3d462fa16de7a5c62722e0.ofd"
  res = requests.get(ofd_url, headers=headers)
  _data_dict = parse_ofd(res.content, f'E://{ofd_url.split("/")[-1]}')
  print(_data_dict)