podcastrss_to_html.py

# coding=utf-8

import re

from lxml import etree

import requests

__author__ = 'namh'


class JdnyRssParser(object):
    url = 'http://pod.ssenhosting.com/rss/rrojia2/rrojia2.xml'

    def __init__(self):
        pass


    def _getText(self, item, xpath, namespaces=None):

        text = item.xpath(xpath, namespaces=namespaces)[0].text
        if text is not None:
            text = text.encode('utf-8')
        return text


    def open(self, printformat="<a href={fpath}>{title} - {subtitle}</a>, {pubdate}{space}"):
        r = requests.get(self.url)
        r.encoding = 'utf-8'

        print "<meta charset='utf-8'/>"

        root = etree.fromstring(r.text.encode('utf-8'))
        items = root.xpath('//item')
        for item in items:

            title = self._getText(item, 'title')
            pubDate = item.xpath('pubDate')[0].text
            guid = item.xpath('guid')[0].text
            subtitle = self._getText(item, 'itunes:subtitle',
                                     namespaces={'itunes':"http://www.itunes.com/dtds/podcast-1.0.dtd"})


            print printformat \
                .format(fpath=guid, pubdate=pubDate,
                        title=title, subtitle=subtitle,
                        space='<br>')


class GMoneyParser(JdnyRssParser):
    url = 'http://apple.radiorss.ytn.co.kr/news_new.xml'
    def __init__(self):
        super(GMoneyParser, self).__init__()


def main():
    """

    :return:
    """
    # parser = JdnyRssParser()
    # print parser.open()

    parser = GMoneyParser()
    print parser.open(printformat="<a href={fpath}>{title}</a>, {pubdate}{space}")


if __name__ == '__main__':
    main()