def read_xml(in_path): # f = codecs.open(in_path,"r", ) # content = f.read() # f.flush() # f.close() content = MDCompressFile.uncompress_file(in_path) tree = etree.parse(StringIO(content), parser=etree.XMLParser(huge_tree=True)) return tree
def praseXML(path):
'''
解析xml 获取命名空间, 和实例
:param path:xml文档路径
:return: 命名空间 和 实例集合
'''
itemArr = []#存储xml中实例
try:
tree = etree.parse(StringIO.StringIO(MDCompressFile.uncompress_file(path)), parser=etree.XMLParser(huge_tree=True))
root = tree.getroot()
nsmap = root.nsmap
#nsmap双向映射
pamsn = {v:k for k,v in nsmap.items()}
#xsd文件获取命名空间, xsd获取命名空间 为了进一步确认是否是拓展或者未确认
# xsdPath = path[:-4]+'.xsd'
# xsdNsmap = None
# xsdPamsn = None
# if os.path.exists(xsdPath):
# xsdTree = etree.parse(xsdPath)
# xsdRoot = xsdTree.getroot()
# xsdNsmap = xsdRoot.nsmap
# xsdPamsn = {v: k for k, v in xsdNsmap.items()}
#获取当前文件名年数
for child in root:
# 去除辅助性元素
try:
if child.tag.split('}')[-1] in SupportItem:
continue
except Exception, e:
continue
nameSpaceLink = str(child.tag).strip('{').split('}')[0]
#判断 tag前命名引用 是否是存在namespace中间的
if pamsn[nameSpaceLink] != None:
#规则过滤
attDic = child.attrib
#拼接参数
tag = child.tag
text = child.text
value = {}
try:
value['CONTENTTEXT'] = text
except Exception,e:
print e
print 'something wrong to get <CONTENTTEXT> ============'
#处理tag属性
for attTemp in attDic:
try:
temp = attTemp.split('}')
# 判断属性中是否带有命名空间
if len(temp) > 1:
if pamsn[temp[0].strip('{')] != None:
value[pamsn[temp[0].strip('{')] + ':' + temp[-1]] = attDic[attTemp]
else:
value[attTemp] = attDic[attTemp]
except Exception, e:
continue
dic = {pamsn[nameSpaceLink] +':'+ tag.split('}')[-1]:value}
itemArr.append(dic)
def praseXML(path):
'''
解析xml 获取命名空间, 和实例
:param path:xml文档路径
:return: 命名空间 和 实例集合
'''
itemArr = [] #存储xml中实例
try:
tree = etree.parse(StringIO.StringIO(
MDCompressFile.uncompress_file(path)),
parser=etree.XMLParser(huge_tree=True))
root = tree.getroot()
nsmap = root.nsmap
#nsmap双向映射
pamsn = {v: k for k, v in nsmap.items()}
#xsd文件获取命名空间, xsd获取命名空间 为了进一步确认是否是拓展或者未确认
# xsdPath = path[:-4]+'.xsd'
# xsdNsmap = None
# xsdPamsn = None
# if os.path.exists(xsdPath):
# xsdTree = etree.parse(xsdPath)
# xsdRoot = xsdTree.getroot()
# xsdNsmap = xsdRoot.nsmap
# xsdPamsn = {v: k for k, v in xsdNsmap.items()}
#获取当前文件名年数
for child in root:
# 去除辅助性元素
try:
if child.tag.split('}')[-1] in SupportItem:
continue
except Exception, e:
continue
nameSpaceLink = str(child.tag).strip('{').split('}')[0]
#判断 tag前命名引用 是否是存在namespace中间的
if pamsn[nameSpaceLink] != None:
#规则过滤
attDic = child.attrib
#拼接参数
tag = child.tag
text = child.text
value = {}
try:
value['CONTENTTEXT'] = text
except Exception, e:
print e
print 'something wrong to get <CONTENTTEXT> ============'
#处理tag属性
for attTemp in attDic:
try:
temp = attTemp.split('}')
# 判断属性中是否带有命名空间
if len(temp) > 1:
if pamsn[temp[0].strip('{')] != None:
value[pamsn[temp[0].strip('{')] + ':' +
temp[-1]] = attDic[attTemp]
else:
value[attTemp] = attDic[attTemp]
except Exception, e:
continue
dic = {pamsn[nameSpaceLink] + ':' + tag.split('}')[-1]: value}
itemArr.append(dic)
