标签:
1 import re 2 3 from lxml import etree 4 5 def indent(elem, level=0): 6 i = "\n" + level*"\t" 7 if len(elem): 8 if not elem.text or not elem.text.strip(): 9 elem.text = i + "\t" 10 for e in elem: 11 indent(e, level+1) 12 if not e.tail or not e.tail.strip(): 13 e.tail = i 14 if level and (not elem.tail or not elem.tail.strip()): 15 elem.tail = i 16 return elem 17 18 19 file_name = ‘lr_xml.txt‘ 20 21 elems_root = etree.parse(file_name).getroot() 22 final_elem=indent(elems_root) 23 init_content=etree.tostring(final_elem, encoding="utf-8", method="xml") 24 25 26 27 # 每行左对齐 28 regex1 = re.compile("\t") 29 convert_first= re.sub(regex1,"",init_content) 30 31 # 每行开始加上" 32 regex2=re.compile("^<",flags=re.M) 33 convert_second = re.sub(regex2,"\"<",convert_first) 34 35 #每行末尾加上" 36 regex3 = re.compile(">$", flags=re.M) 37 final_content=re.sub(regex3,">\"",convert_second) 38 39 print final_content
标签:
原文地址:http://www.cnblogs.com/martinsun/p/5047723.html