Python基本爬虫（数据存储器）

作者: 原来不语 | 来源:发表于2017-12-12 19:51 被阅读0次

# -*-encoding:utf-8 -*-
import codecs

class DataOutput(object):
"""docstring for DataOutput"""
def __init__(self):
    super(DataOutput, self).__init__()
    self.datas=[]
    
def store_data(self,data):
    if data is None:
        return 
    self.datas.append(data)

def output_html(self):
    fout = codecs.open('baike.html','w',encoding='utf-8')
    fout.write("<html>")
    fout.write("<head><meta charset='utf-8'/></head>")
    fout.write("<body>")
    fout.write("<table>")
    for data in self.datas:
        fout.write("<tr>")
        fout.write("<td>%s</td>"%data['url'])
        fout.write("<td>%s</td>"%data['title'])
        fout.write("<td>%s</td>"%data['summary'])
        fout.write("</tr>")
        self.datas.remove(data)
    fout.write("</table>")
    fout.write("</body>")
    fout.write("</html>")
    fout.close()