今天学习如何利用Python来解析XML文档。
给定一个XML文件,现在我们用Python来提取里面的内容。
<deals> <data> <deal> <deal_id>11111111</deal_id> <sales_num>120</sales_num> <price>15.0</price> </deal> </data> </deals>
Python代码:
import xml.etree.ElementTree as ET class MeiTuanParser: def __init__(self): self.meituan_deal_set = [] def parse(self,filepath): tree = ET.parse(filepath) root = tree.getroot() for data in root.iter(‘data‘): deal = data.find(‘deal‘) meituan_deal = {} if deal is not None: try: meituan_deal[‘deal_id‘] = deal.find(‘deal_id‘).text except Exception, exp: print "No deal id" try: meituan_deal[‘sales‘] = int(deal.find(‘sales_num‘).text) except Exception, exp: print "Invalid sales number" try: meituan_deal[‘price‘] = float(deal.find(‘price‘).text) except Exception, exp: print "Invalid price" self.meituan_deal_set.append(meituan_deal) return self.meituan_deal_set if __name__ == ‘__main__‘: parser = MeiTuanParser() deals = parser.parse(‘meituan.xml‘) print deals
原文地址:http://blog.csdn.net/acdreamers/article/details/24707837