python提取xml里面的链接源码详解

#coding=utf-8
import urllib
import urllib.request
import re
url='http://zhimo.yuanzhumuban.cc/sitemaps.xml'
html=urllib.request.urlopen(url).read()
html=html.decode('utf-8')
r=re.compile(r'(http://zhimo.yuanzhumuban.cc.*?\.html)')
big=re.findall(r,html)
for i in big:
 print(i)
 op_xml_txt=open('xml.txt','a')
 op_xml_txt.write('%s\n'%i)

import xml.dom.minidom

def find_child(Par_nodes, mystr):
  for child_node in Par_nodes:
    if(len(child_node.childNodes) > 0):
      mystr = find_child(child_node.childNodes, mystr)
    elif(child_node.nodeValue != None):
      mystr += child_node.data.replace('\n', '')
  return mystr

if __name__ == '__main__':

  dom1 = xml.dom.minidom.parse('2.XML') #打开xml文件
  root = dom1.documentElement     #得到文档元素对象
  app_nums = root.getElementsByTagName('base:DocNumber') #按标签名称查找，返回标签结点数组
  app_num = app_nums[2]
  print('专利申请号：'+app_num.firstChild.data)
  titles = root.getElementsByTagName('business:InventionTitle')
  title = titles[0]
  print('专利名称：'+title.firstChild.data)
  Paragraphs = root.getElementsByTagName('base:Paragraphs')
  abstract = Paragraphs[0]
  print('专利摘要：'+abstract.firstChild.data)
  company_names = root.getElementsByTagName('base:Name')
  company_name = company_names[0]
  print('公司名称：'+company_name.firstChild.data)
  mystr = ''
  for i in range(len(Paragraphs)):
    if (Paragraphs[i].firstChild.data == '发明内容\n\t'):
      i+=1
      while Paragraphs[i].firstChild.data != '附图说明\n\t':
        mystr = find_child(Paragraphs[i].childNodes, mystr)
        i+=1

  print('发明内容：' + mystr)