总结了一下使用python对xml文件的解析,用到的模块儿如下:
分别从xml字符串和xml文件转换为xml对象,然后解析xml内容,查询指定信息字段。
from xml.dom.minidom import parse, parsestring
from xml.etree import elementtree
import xml.dom.minidom
"""
get xml string info 查询属性值
response:xml string
tag:xml tag
element:xml attribute
"""
def get_xml_info(response, element):
domtree = xml.dom.minidom.parsestring(response)
return domtree.documentelement.getattribute(element)
"""
get xml string info 查询制定名称的特定标签id
xmlstring:xml str
return config id
"""
def get_config_id_from_xml(xmlstring, scan):
root = elementtree.fromstring(xmlstring)
configs = root.findall('config')
for config in configs:
config_name = config.find('name').text
if config_name == scan:
return config.attrib['id']
"""
get xml string info 查询指定id
xmlstring:xml str
return report id
"""
def get_report_id_from_xml(xmlstring):
root = elementtree.fromstring(xmlstring)
report_id = root.find('report_id').text
return report_id
"""
get xml string info
xmlstring:xml str
return progress
"""
def get_progress_from_xml(xmlstring):
root = elementtree.fromstring(xmlstring)
task = root.find('task')
progress = float(task.find('progress').text)
if progress < 0:
return 100.0
else:
return progress
"""
get xml report info 从xml文件查询
file_path : report path
"""
def get_xml_report(file_path):
report = {}
result_dicts = {}
resultslist = []
try:
root = elementtree.parse(file_path)
except:
return {}
if root is not none:
creation_time = root.find("creation_time")
if creation_time is not none:
report[creation_time.tag] = creation_time.text
if root.find("report") is not none:
scan_start = root.find("report").find("scan_start")
if scan_start is not none:
if scan_start.text:
report[scan_start.tag] = scan_start.text
results = root.getiterator("result")
if results is not none:
for result in results:
if result.find("threat") is not none:
if result.find("threat").text != "log":
resultslist.append(getresults(result))
report["results"] = resultslist
return report
如您对本文有疑问或者有任何想说的,请点击进行留言回复,万千网友为您解惑!