python思维导图xmind高清_python解析FreeMind和XMind思维导图

importzipfileimportosimportioimportsysimporthashlibimportxml.etree.ElementTree as ETclassAnalyseMindMap:def __init__(self, file_path, mark):

self.file_path=file_path

self.context= ""

if mark == "":

self.mark= " "

elif mark == "#":

self.mark= "#"

elif mark == "*":

self.mark= "*"

#解析xmind数据

defanalyse_xmind(self):

file_name=os.path.basename(self.file_path)ifos.path.isfile(self.file_path):

base_dir=os.path.dirname(self.file_path)

m=hashlib.md5()

file= io.FileIO(self.file_path, 'r')

read_bytes= file.read(1024)while read_bytes != b'':

m.update(read_bytes)

read_bytes= file.read(1024)

file.close()

md5value=m.hexdigest()for dir_name inos.listdir(base_dir):if dir_name ==md5value:print('已经存在了该文件', md5value)continuefile_zip= zipfile.ZipFile(self.file_path, 'r')for file infile_zip.namelist():

file_zip.extract(file, base_dir+ '/' +md5value)

file_zip.close()

xml_file= os.path.join(base_dir, md5value, 'content.xml')returnself.analyse_xml(xml_file)else:return "{} 不存在".format(file_name)#file_list = os.listdir(self.file_path)

# #for file_name in file_list:

#print(file_name)

#if os.path.splitext(file_name)[1] == '.xmind':

#print(file_name)

#zip_file = os.path.join(self.file_path, file_name)

#m = hashlib.md5()

#file = io.FileIO(zip_file, 'r')

#read_bytes = file.read(1024)

#while read_bytes != b'':

#m.update(read_bytes)

#read_bytes = file.read(1024)

#file.close()

#md5value = m.hexdigest()

#for dir_name in os.listdir(r'Upload/'):

#if dir_name == md5value:

#print('已经存在了该文件', md5value)

#continue

#file_zip = zipfile.ZipFile(zip_file, 'r')

#for file in file_zip.namelist():

#file_zip.extract(file, r'./' + md5value)

#file_zip.close()

#xml_file = os.path.join('./', md5value, 'content.xml')

#self.analyse_xml(xml_file)

#os.remove(file_name)

#解析xml文件

defanalyse_xml(self, xml_file):try:

tree=ET.parse(xml_file)#获得根节点

root =tree.getroot()except Exception as e: #捕获除与程序退出sys.exit()相关之外的所有异常

print("parse test.xml fail!")

sys.exit()

pre_tag= '{' + root.tag.split('{')[1].split('}')[0] + '}'title_path= pre_tag + 'sheet/' + pre_tag + 'topic/' + pre_tag + 'title'

print("h1.", root.find(title_path).text)

self.context= "\nh1." + root.find(title_path).text + "\n"plain_path= pre_tag + 'sheet/' + pre_tag + 'topic/' + pre_tag + 'notes/' + pre_tag + 'plain'

if root.find(plain_path) is notNone:print("

备注：" + root.find(plain_path).text + "

")

self.context+= "

备注：" + root.find(plain_path).text + "

" + "\n\n"third_path= pre_tag + 'sheet/' + pre_tag + 'topic/' + pre_tag + 'children'num= 1 #对分层进行标记

for first_topic inroot.findall(third_path):

self.recursive_xml(first_topic, pre_tag, num)returnself.context#递归调用获取元素值

defrecursive_xml(self, root, pre_tag, num):

topics_path= pre_tag + 'topics' #一个children下面可能会有多个topics，所以需要循环一下

for topics inroot.findall(topics_path):

topic_path= pre_tag + 'topic'

for topic intopics.findall(topic_path):

title_path= pre_tag + 'title'

if num > 1:print(self.mark * (num - 1), topic.find(title_path).text)

self.context+= self.mark * (num - 1) + " " + topic.find(title_path).text + "\n"

else:print("h3.", topic.find(title_path).text)

self.context+= "\nh3." + topic.find(title_path).text + '\n\n'plain_path= pre_tag + 'notes/' + pre_tag + 'plain'

if topic.find(plain_path) is notNone:print("

备注："+topic.find(plain_path).text + "

")

self.context+= "

备注："+topic.find(plain_path).text+"

" + "\n\n"label_path= pre_tag + 'labels/' + pre_tag + 'label'

if topic.find(label_path) is notNone:print("-->标签：", topic.find(label_path).text + "<--")

self.context+= "-->标签：" + topic.find(label_path).text + "<--" + "\n\n"children_path= pre_tag + 'children'

for new_topic intopic.findall(children_path):

self.recursive_xml(new_topic, pre_tag, num+1)#解析freemind的xml文件

defanalyse_mm_xml(self):ifos.path.isfile(self.file_path):try:

tree=ET.parse(self.file_path)#获得根节点

root =tree.getroot()except Exception as e: #捕获除与程序退出sys.exit()相关之外的所有异常

print("parse test.xml fail!")

sys.exit()

node_path= "node"num= 1

for node inroot.findall(node_path):print("h1.", node.attrib['TEXT'])

self.context+= "\nh1." + node.attrib['TEXT'] + "\n"

if node.find('richcontent') is notNone:

context_p= 'richcontent/html/body/p'

print('

备注：', node.find(context_p).text.replace(' ', '').replace('\n', ''), '

')

self.context+= '

备注：' + node.find(context_p).text.replace(' ', '').replace('\n', '') + '

' + "\n\n"self.recursive_node(node, num)returnself.context#递归运行查看结果

defrecursive_node(self, root, num):

node_path= 'node'richcontent_path= 'richcontent'

for node inroot.findall(node_path):if 'TEXT' innode.attrib:if num > 1:print(self.mark * (num - 1), node.attrib['TEXT'])

self.context+= self.mark * (num - 1) + ' ' + node.attrib['TEXT'] + "\n"

else:print("h3.", node.attrib['TEXT'])

self.context+= "\nh3." + node.attrib['TEXT'] + "\n\n"

if node.find(richcontent_path) is notNone:

context_p= 'richcontent/html/body/p'context_out= ''

for p innode.findall(context_p):

context_out+= p.text.replace(' ', '').replace('\n', '') + '\n'

print('

备注：', context_out, '

')

self.context+= '

备注：' + context_out + '

' + "\n\n"

if node.find(node_path) is notNone:

self.recursive_node(node, num+ 1)if __name__ == '__main__':

file_path= r'C:\path\to\file.xmind'amm= AnalyseMindMap(file_path, "#")

amm.analyse_xmind()

file_path= r'C:\path\to\file.mm'amm= AnalyseMindMap(file_path, "#")

amm.analyse_mm_xml()