『Python の XUL パーサ』のソースコード
import sys, glob, xmllib
import os, re
el_list = {}
w = open('res.html', 'w')
# Unfortunately, I had to put this hack in here to suppress the printing out of the resolved namespace:
# "xmlns="https://www.mozilla.org/keymaster/gatekeeper/there.is.only.xul window", etc.
def strip(snip):
t = re.sub('https://.*?\s', '', snip)
return t
class XULParser(xmllib.XMLParser):
def unknown_starttag(self, t, a):
name = strip(t)
if name not in el_list: el_list[name] = {}
for attr,val in a.items():
el_list[name][strip(attr)] = strip(val)
def syntax_error(self, message):
pass
p = XULParser()
cmd = 'dir /s /b *.xul'
CHROME_DIR = 'C:\Program Files\Netscape\Netscape 6\chrome'
os.chdir(CHROME_DIR)
files = os.popen(cmd).readlines()
for file in files:
file = file.strip()
print '** ' + file + ' **'
data = open(file).read()
p.feed(data)
w.write('<html><h3>Periodic Table of XUL Elements</h3>')
w.write('<table><style>.head {font-weight: bold; background-color: lightgrey;}</style>')
elements = el_list.keys()
elements.sort()
for item in elements:
w.write('<tr><td class="head">' + item + '</td></tr>\n')
for a in el_list[item]:
w.write('<tr><td class="at">' + a + '</td>')
w.write('</table></html>\n')
w.close()