首页 > 代码库 > 爬虫4 html输出器 html_outputer.py

爬虫4 html输出器 html_outputer.py

#coding:utf8
__author__ = wang


class HtmlOutputer(object):

    def __init__(self):
        self.datas = [];

    def collect_data(self, data):
        if data is None:
            return
        print data
        self.datas.append(data)

    def output_html(self):
        fout = open(output.html, w)
        fout.write(<html>)
        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].encode(utf-8))
            fout.write(<td>%s</td> % data[summary].encode(utf-8))
            fout.write(</tr>)

        fout.write(</table>)
        fout.write(</body>)
        fout.write(</html>)

    def test(self):
        pass

 

爬虫4 html输出器 html_outputer.py