1 Star 0 Fork 0

feng/python

加入 Gitee
与超过 1400万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
克隆/下载
rss2html.py 2.00 KB
一键复制 编辑 原始数据 按行查看 历史
feng 提交于 2015-10-01 10:15 +08:00 . python
import sys
from xml.sax import make_parser, handler
# --- Templates
top = \
"""
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML>
<HEAD>
<TITLE>%s</TITLE>
</HEAD>
<BODY>
<H1>%s</H1>
"""
bottom = \
"""
</ul>
<HR>
<ADDRESS>
Converted to HTML by sax_rss2html.py.
</ADDRESS>
</BODY>
</HTML>
"""
# --- The ContentHandler
class RSSHandler(handler.ContentHandler):
def __init__(self, out = sys.stdout):
handler.ContentHandler.__init__(self)
self._out = out
self._text = ""
self._parent = None
self._list_started = 0
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("<p>%s</p>\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("<ul>\n")
self._list_started = 1
self._out.write(' <li><a href="%s">%s</a> %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
parser = make_parser()
parser.setContentHandler(RSSHandler())
parser.parse(sys.argv[1])
Loading...
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
Python
1
https://gitee.com/yf33/python.git
git@gitee.com:yf33/python.git
yf33
python
python
master

搜索帮助