Hi All,
I've picked up the PyParsing module and am trying to figure out how to
do a simple parsing of some HTML source code. My specific problem is
dealing with an <TD></TD> element that is blank.
from pyparsing import *
import sys
integer = Word("0123456789")
trStart = Literal("<TR>").suppress()
trEnd = Literal("</TR>").suppress()
tdStart = Literal("<TD>").suppress()
tdEnd = Literal("</TD>").suppress()
#dataItem = Word(alphas)
BlankItem = Word('')
dataItem = Word(alphanums + " " + "," + ":") # works with spaces in
data
MultiItem = Optional(OneOrMore(dataItem))
TestLine = ['<TR><TD>Group</TD><TD>Year</TD><TD>City</TD></TR>',
'<TR><TD>AAA</TD><TD>1992</TD><TD>Los Angeles</TD></TR>',
'<TR><TD>BBB</TD><TD>2007</TD><TD>Santa Cruz</TD></TR>',
'<TR><TD></TD><TD>2001</TD><TD>Santa Cruz</TD></TR>']
htmlLine = trStart + tdStart + MultiItem.setResultsName('status') +
tdEnd + tdStart + MultiItem.setResultsName('year') + tdEnd + tdStart +
MultiItem.setResultsName('title') + tdEnd + trEnd
for CurrentLine in TestLine:
print 'Line = ', CurrentLine
for srvrtokens,startloc,endloc in htmlLine.scanString( CurrentLine ):
print 'tokens = %s %d %d \n' % (srvrtokens, startloc,endloc)
Output :
Line = <TR><TD>Group</TD><TD>Year</TD><TD>City</TD></TR>
tokens = ['Group', 'Year', 'City'] 0 49
Line = <TR><TD>AAA</TD><TD>1992</TD><TD>Los Angeles</TD></TR>
tokens = ['AAA', '1992', 'Los Angeles'] 0 54
Line = <TR><TD>BBB</TD><TD>2007</TD><TD>Santa Cruz</TD></TR>
tokens = ['BBB', '2007', 'Santa Cruz'] 0 53
*** Blank 1st element - only shows 2 elements - need 3 elements to be
consistent ***
Line = <TR><TD></TD><TD>2001</TD><TD>Santa Cruz</TD></TR>
tokens = ['2001', 'Santa Cruz'] 0 50
Any assistance would be greatly appreciated!
Steve
--
http://mail.python.org/mailman/listinfo/python-list
