showtbls.py

来自「python web programming 部分」· Python 代码 · 共 40 行

import htmllib, urllib, formatter, sys

def Usage():
    print """
Usage: python showtbls.py URL
"""

class myHTMLParser(htmllib.HTMLParser):

    def __init__(self, f):
        htmllib.HTMLParser.__init__(self, f)
        self.tblindent = 0

    def start_table(self, attrs):
        sys.stdout.write("%s<table" % ("    " * self.tblindent, ))
        for k, v in attrs:
            if k in ("width", "cellspacing"):
                sys.stdout.write(' %s="%s"' % (k, v),)
        print ">"
        self.tblindent += 1

    def end_table(self):
        self.tblindent -= 1
        print "%s</table>" % ("    " * self.tblindent, )

def parse(url, formatter):
    f = urllib.urlopen(url)
    data = f.read()
    f.close()
    p = myHTMLParser(formatter)
    p.feed(data)
    p.close()

if len(sys.argv) != 2:
    Usage()
else:
    fmt  = formatter.NullFormatter()
    parse(sys.argv[1], fmt)