def extract_text(self,data) -> str:
text = []
for i, v in enumerate(data["Packed"]["Files"]):
if v["Name"].lower() == "document.xml":
tree = cetXML(open(v["Path"],"rb").read())
for par in tree.iter(self.para):
text.append(''.join(node.text for node in par.iter(self.text)))
return '\n'.join(text)
def extract_dde(self, data) -> str:
'''
Extract dde
'''
text = []
for index, temp_var in enumerate(data["Packed"]["Files"]):
if temp_var["Name"].lower() == "document.xml":
tree = cetXML(open(temp_var["Path"], "rb").read())
for par in tree.iter(self.para):
string = ''.join(node.text for node in par.iter(self.instrtext))
if len(string) > 0:
text.append(string)
return '\n'.join(text)
def office_meta_info(self,data) -> dict:
'''
get office meta data
'''
_dict = {}
corePropNS = '{http://schemas.openxmlformats.org/package/2006/metadata/core-properties}'
meta = ["filename","title","subject","creator","keywords","description","lastModifiedBy","revision","modified","created"]
for i, v in enumerate(data["Packed"]["Files"]):
if v["Name"].lower() == "core.xml":
tree = cetXML(open(v["Path"],"rb").read())
for item in meta:
x = tree.find("{}{}".format(corePropNS,item))
if x is not None:
_dict.update({item:x.text})
break
return _dict