利用difflib模块比较两个XML文件内容之间差异性输出到HTML

 需求说明：比较两个路径下所有相同文件名的XML文件内容，将差异行输出到日志和HTML中。

    XML路径：

XML内容：

 

     输出结果如图：

日志：

HTML：

1. 获取两个路径下所有的XML文件路径：

       def get_xml_name(self, path):
           """获取所有的 XML文件名"""
           xml_name_list = []
           parents = os.listdir(path)
           for xml_name in parents:
               xml_name_list.append(xml_name)
           return xml_name_list

    

2. 读取 XML文件：

       def read_xml_file(self, file_name):
           """读取 XML文件"""
           try:
               file_handle = open(file_name, 'r', encoding='UTF-8')
               text = file_handle.read().splitlines()  # 读取后以行进行分割
               file_handle.close()
               return text
           except IOError as error:
               self.logger.error('read_xml_file Error: {0}'.format(error))
               sys.exit()

    

3. 对比xml文件并输出HTML:

       def compare_file(self, file1_name, file2_name, html_name):
           """对比xml文件并输出HTML"""
           text1_lines = self.read_xml_file(file1_name)
           text2_lines = self.read_xml_file(file2_name)
           diff = difflib.HtmlDiff()  # 创建 diff 对象
           result = diff.make_file(text1_lines, text2_lines)  # 通过 make_file 方法输出源文件 HTML 的对比结果
           try:
               with open(html_name, 'w', encoding='UTF-8') as f:  # 将结果保存到文件中
                   f.write(result)
           except IOError as error:
               self.logger.error('write_compare_file error：{0}'.format(error))

    

4. 完整代码：

   import os
   import sys
   import difflib
   import datetime
   from bs4 import BeautifulSoup
   from AnhuiMobile.script.checkauth.logModule import LogClass
   
   
   class ComparisonXMLFileDiff(LogClass):
       """比较两个XML文件差异性"""
   
       def __init__(self, origin_root_path="E:\\AnhuiMobile\\AnhuiMobile\\script\\checkauth\\dir1\\",
                    comparison_root_path="E:\\AnhuiMobile\\AnhuiMobile\\script\\checkauth\\dir2\\",
                    html_path="E:\\AnhuiMobile\\AnhuiMobile\\script\\checkauth\\htmlresult\\",
                    log_path="E:\\AnhuiMobile\\AnhuiMobile\\script\\checkauth\\logs\\"):
           """初始化"""
           LogClass.__init__(self, logName='ComparisonXMLFileDiff')
           # 日志输出到文件
           self.setTimedRotatingFileHandler(fileName='ComparisonXMLFileDiff', path=log_path)
           # 控制台输出日志
           self.setStreamHandler()
           # XML文件所在路径
           self.origin_root_path = origin_root_path
           self.comparison_root_path = comparison_root_path
           # 输出的 HTML文件路径
           self.html_path = html_path
           # 模板 HTML文件路径
           self.base_html_path = "E:\\AnhuiMobile\\AnhuiMobile\\script\\checkauth\\"
           # 当前时间
           self.now = datetime.datetime.strftime(datetime.datetime.now(), "%Y-%m-%d")
           # HTML模板list
           self.base_html_list = []
           # 记录模板 HTML第26行为<tbody></tbody>
           self.count = 26
   
       def get_xml_name(self, path):
           """获取所有的 XML文件名"""
           xml_name_list = []
           parents = os.listdir(path)
           for xml_name in parents:
               xml_name_list.append(xml_name)
           return xml_name_list
   
       def read_xml_file(self, file_name):
           """读取 XML文件"""
           try:
               file_handle = open(file_name, 'r', encoding='UTF-8')
               text = file_handle.read().splitlines()  # 读取后以行进行分割
               file_handle.close()
               return text
           except IOError as error:
               self.logger.error('read_xml_file Error: {0}'.format(error))
               sys.exit()
   
       def compare_file(self, file1_name, file2_name, html_name):
           """对比xml文件并输出HTML"""
           text1_lines = self.read_xml_file(file1_name)
           text2_lines = self.read_xml_file(file2_name)
           diff = difflib.HtmlDiff()  # 创建 diff 对象
           result = diff.make_file(text1_lines, text2_lines)  # 通过 make_file 方法输出源文件 HTML 的对比结果
           try:
               with open(html_name, 'w', encoding='UTF-8') as f:  # 将结果保存到文件中
                   f.write(result)
           except IOError as error:
               self.logger.error('write_compare_file error：{0}'.format(error))
   
       def get_base_html(self):
           """获取模板 HTML存入 List"""
           try:
               with open(self.base_html_path + "base_language_diff.html", "r", encoding="UTF-8") as f:
                   for i in f.readlines():
                       self.base_html_list.append(i)
           except IOError as error:
               self.logger.error('get_base_html error：{0}'.format(error))
   
       def delete_same_from_html(self, html_name, xml_name1):
           """剔除HTML中没有差异行，输出差异行日志"""
           sign = 0  # 标记是否有差异行，0表示没有
           diff_html_list = []
           try:
               with open(html_name, 'r', encoding="UTF-8") as f:
                   lines = f.readlines()
                   for line_html in lines:
                       if line_html.__contains__('encoding="utf-8"') or line_html.__contains__('encoding="UTF-8"'):
                           xml_name = """<tr><td class="diff_next"></td><td class="diff_header"></td><td nowrap="nowrap"><span
                                  style="text-align: center;display:block;color:blue;font-size:20px;background-color:#999;">
                                  <strong>""" + xml_name1 + """</strong></span></td><td class="diff_next"></td><td 
                                  class="diff_header"></td><td nowrap="nowrap" style="text-align: center;display:block;
                                  color:blue;font-size:20px;background-color:#999;"><span ><strong>""" + xml_name1 \
                                      + """</strong></span></td></tr>"""  # 将文件名拼到 HTML 中
                           diff_html_list.append(xml_name)  # XML文件名存入list
                       elif line_html.__contains__('<tr><td class="diff_next"'):
                           if line_html.__contains__('class="diff_add"') or line_html.__contains__('class="diff_chg"') or \
                                   line_html.__contains__('class="diff_sub"'):  # 筛选出差异行 HTML
                               diff_html_list.append(line_html)  # 差异行 HTML存入list
                               sign = 1  # 有差异行，标记改为 1
                               soup = BeautifulSoup(line_html, 'html.parser')
                               line = soup.find("td", attrs={'class': 'diff_header'}).get_text().strip()
                               # content1 = soup.find_all("td", attrs={'nowrap': 'nowrap'})[0].get_text().strip()  # 提取差异文本
                               # content2 = soup.find_all("td", attrs={'nowrap': 'nowrap'})[1].get_text().strip()
                               self.logger.debug(xml_name1 + "][line: " + line + "]")
                           else:
                               continue
                       else:
                           continue
               os.remove(html_name)  # 移除源文件 HTML 的对比结果
               if sign == 1:  # 有差异行,写入模板
                   for diff_html in diff_html_list:
                       self.base_html_list.insert(self.count, diff_html)  # 将差异行 HTML 插入<tbody></tbody>中
                       self.count += 1
               else:  # 没有差异行,返回
                   return
           except Exception as e:
               self.logger.error(e)
   
       def main(self):
           origin_xml_name_list = self.get_xml_name(self.origin_root_path)  # 获取所有的xml文件名
           comparison_xml_name_list = self.get_xml_name(self.comparison_root_path)
   
           for xml_name1 in list(set(origin_xml_name_list).difference(set(comparison_xml_name_list))):  # 判断对比文件夹中是否存在
               self.logger.info(
                   xml_name1 + "][" + self.origin_root_path + " -> exist" + "][" + self.comparison_root_path + " -> not_exist")
   
           for xml_name2 in list(set(comparison_xml_name_list).difference(set(origin_xml_name_list))):
               self.logger.info(
                   xml_name2 + "][" + self.origin_root_path + " -> not_exist" + "][" + self.comparison_root_path + " -> exist")
           self.get_base_html()
           for xml_name1 in origin_xml_name_list:
               for xml_name2 in comparison_xml_name_list:
                   if xml_name1 == xml_name2:
                       file_path1 = self.origin_root_path + xml_name1  # 获取所有的xml文件名
                       file_path2 = self.comparison_root_path + xml_name2
                       html_name = self.html_path + self.now + "-" + str(xml_name1).split(".")[0] + '.html'
                       self.compare_file(file_path1, file_path2, html_name)  # 对比xml文件并输出HTML
                       self.delete_same_from_html(html_name, xml_name1)  # 剔除HTML中没有差异行，输出差异行日志
                   else:
                       continue
           try:
               html_list = "".join(self.base_html_list)  # 将模板List拼接写入
               with open(self.html_path + self.now + "_language_diff.html", "w", encoding="UTF-8") as f_write:
                   f_write.write(html_list)
           except IOError as error:
               self.logger.error('write_language_diff error：{0}'.format(error))
   
   
   if __name__ == '__main__':
       c = ComparisonXMLFileDiff()
       c.main()