ÿØÿà JFIF ÿþ
ÿÛ C
ÿÛ C ÿÀ ÿÄ ÿÄ " #QrÿÄ ÿÄ & 1! A"2qQaáÿÚ ? Øy,æ/3JæÝ¹Èß²Ø5êXw²±ÉyR¾I0ó2PI¾IÌÚiMö¯þrìN&"KgX:íµnTJnLK
@!-ýùúmë;ºgµ&ó±hw¯Õ@Ü9ñ-ë.²1<yà¹ïQÐUÛ?.¦èûbß±©Ö«Âw*V) `$bØÔëXÖ-ËTÜíGÚ3ð«g §¯JxU/ÂÅv_s(Hÿ @TñJÑãõçn!ÈgfbÓc:él[ðQe9ÀPLbÃãCµm[5¿ç'ªjglåÛí_§Úõl-;"PkÞÞÁQâ¼_Ñ^¢S x?"¸¦ùYé¨ÒOÈ q`~~ÚtËU¹CÚêV I1Áß_ÿÙ"""
A demo that reads in an RSS XML document and emits an HTML file containing
a list of the individual items in the feed.
"""
import sys
import codecs
from xml.sax import make_parser, handler
# --- Templates
top = """\
%s
%s
"""
bottom = """
Converted to HTML by rss2html.py.
"""
# --- The ContentHandler
class RSSHandler(handler.ContentHandler):
def __init__(self, out=sys.stdout):
handler.ContentHandler.__init__(self)
self._out = codecs.getwriter('utf-8')(out)
self._text = ""
self._parent = None
self._list_started = False
self._title = None
self._link = None
self._descr = ""
# ContentHandler methods
def startElement(self, name, attrs):
if name == "channel" or name == "image" or name == "item":
self._parent = name
self._text = ""
def endElement(self, name):
if self._parent == "channel":
if name == "title":
self._out.write(top % (self._text, self._text))
elif name == "description":
self._out.write("%s
\n" % self._text)
elif self._parent == "item":
if name == "title":
self._title = self._text
elif name == "link":
self._link = self._text
elif name == "description":
self._descr = self._text
elif name == "item":
if not self._list_started:
self._out.write("\n")
self._list_started = True
self._out.write(' - %s %s\n' %
(self._link, self._title, self._descr))
self._title = None
self._link = None
self._descr = ""
if name == "rss":
self._out.write(bottom)
def characters(self, content):
self._text = self._text + content
# --- Main program
if __name__ == '__main__':
parser = make_parser()
parser.setContentHandler(RSSHandler())
parser.parse(sys.argv[1])