* Skip Montanaro
|
| Is there a simple example available that demonstrates how to use
| elements of the new xml.sax package?
Here are a couple from an internal seminar I recently gave on this. I
could make the slides available as well, if there is interest.
--Lars M.
--- elem_count.py
import sys
from xml.sax import make_parser, handler
class FancyCounter(handler.ContentHandler):
def __init__(self):
self._elems = 0
self._attrs = 0
self._elem_types = {}
self._attr_types = {}
def startElement(self, name, attrs):
self._elems = self._elems + 1
self._attrs = self._attrs + len(attrs)
self._elem_types[name] = self._elem_types.get(name, 0) + 1
for name in attrs.keys():
self._attr_types[name] = self._attr_types.get(name, 0) + 1
def endDocument(self):
print "There were", self._elems, "elements."
print "There were", self._attrs, "attributes."
print "---ELEMENT TYPES"
for pair in self._elem_types.items():
print "%20s %d" % pair
print "---ATTRIBUTE TYPES"
for pair in self._attr_types.items():
print "%20s %d" % pair
parser = make_parser()
parser.setContentHandler(FancyCounter())
parser.parse(sys.argv[1])
--- roundtrip.py
"""
A simple demo that reads in an XML document and spits out an equivalent,
but not necessarily identical, document.
"""
import sys, string
from xml.sax import saxutils, handler, make_parser
# --- The ContentHandler
class ContentGenerator(handler.ContentHandler):
def __init__(self, out = sys.stdout):
handler.ContentHandler.__init__(self)
self._out = out
# ContentHandler methods
def startDocument(self):
self._out.write('<?xml version="1.0" encoding="iso-8859-1"?>\n')
def startElement(self, name, attrs):
self._out.write('<' + name)
for (name, value) in attrs.items():
self._out.write(' %s="%s"' % (name, saxutils.escape(value)))
self._out.write('>')
def endElement(self, name):
self._out.write('</%s>' % name)
def characters(self, content):
self._out.write(saxutils.escape(content))
def ignorableWhitespace(self, content):
self._out.write(content)
def processingInstruction(self, target, data):
self._out.write('<?%s %s?>' % (target, data))
# --- The main program
parser = make_parser()
parser.setContentHandler(ContentGenerator())
parser.parse(sys.argv[1])
--- rss2html.py
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])
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4