Python HTML Parsing Help!

Ok, i am trying to parse this html file so that the table read the 2 rows i want but the problem is it reads every table? can you help? i have posted my code, the source code of the html, what output i am getting, and which output i want.

Here is the python code


import htmllib
import formatter
import pprint

class TableParser(htmllib.HTMLParser):
    def __init__(self):
        self.active=0
        self.finished=0
        self.skipping=0
        self.result=[]
        self.current_row=[]
        self.current_data=[]
        htmllib.HTMLParser.__init__(
            self, formatter.NullFormatter())
    def start_table(self,attributes):
        if not self.finished:
            self.active=1
    def end_table(self):
        self.active=1
        self.finished=1
    def start_tbody(self,attributes):
        self.skipping=0
    def end_tbody(self):
        self.skipping=1
    def start_tr(self,attributes):
        if self.active and not self.skipping:
            self.current_row = []
    def end_tr(self):
        if self.active and not self.skipping:
            self.result.append(self.current_row)
    def start_td(self,attributes):
        if self.active and not self.skipping:
            self.current_data = []
    def end_td(self):
        if self.active and not self.skipping:
            self.current_row.append(
                ' '.join(self.current_data))
    def handle_data(self, data):
        if self.active and not self.skipping:
            self.current_data.append(data)

def process(filename):
    parser=TableParser()
    parser.feed(open(filename).read())
    parser.close()
    return parser.result

def showparse(filename):
    pprint.pprint(process(filename))

def _test():
    return showparse('490.html')

if __name__=='__main__':
    _test()

Here is the Html source


<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<!-- saved from url=(0095)http://banner7bl04.uncfsu.edu:9000/PROD/bwckschd.p_disp_detail_sched?term_in=201020&crn_in=3221 -->
<HTML lang=en><HEAD><TITLE>Detailed Class Information</TITLE>
<META http-equiv=Content-Type content="text/html; charset=WINDOWS-1252">
<META http-equiv=Pragma content=no-cache name=Cache-Control>
<META http-equiv=Cache-Control content=no-cache name=Cache-Control><LINK 
href="490_files/web_defaultapp.css" type=text/css rel=stylesheet><LINK 
media=print href="490_files/web_defaultprint.css" type=text/css rel=stylesheet>
<META http-equiv=Content-Script-Type content=text/javascript 
name=Default_Script_Language>
<script language=Javascript type=text/javascript> 
<!-- Hide Javascript from older browsers 
var submitcount=0;
function checkSubmit() {
if (submitcount == 0)
   {
   submitcount++;
   return true;
   }
else
   {
alert("Your changes have already been submitted.");
   return false;
   }
}
//  End script hiding -->
</SCRIPT>
 
<script language=Javascript type=text/javascript> 
<!-- Hide Javascript from older browsers 
//  Function to open a window
function windowOpen(window_url) {
   helpWin = window.open(window_url,'','toolbar=yes,status=no,scrollbars=yes,menubar=yes,resizable=yes,directories=no,location=no,width=350,height=400');
   if (document.images) { 
       if (helpWin) helpWin.focus()
   }
}
//  End script hiding -->
</SCRIPT>
 
<META content="MSHTML 6.00.6000.16981" name=GENERATOR></HEAD>
<BODY>
<DIV class=headerwrapperdiv>
<DIV class=pageheaderdiv1><A class=skiplinks 
onblur="window.status=''; return true" 
onmouseover="window.status='Go to Main Content'; return true" 
onfocus="window.status='Go to Main Content'; return true" 
onmouseout="window.status=''; return true" 
href="http://banner7bl04.uncfsu.edu:9000/PROD/bwckschd.p_disp_detail_sched?term_in=201020&amp;crn_in=3221#main_content">Go 
to Main Content</A> 
<H1>FAYETTEVILLE STATE UNIVERSITY</H1></DIV>
<DIV class=headerlinksdiv></DIV>
<TABLE class=plaintable width="100%" 
summary="This table displays Menu Items and Banner Search textbox.">
  <TBODY>
  <TR>
    <TD class=pldefault>
      <DIV class=headerlinksdiv2>
      <FORM action=/PROD/twbksrch.P_ShowResults method=post>Search <SPAN 
      class=fieldlabeltextinvisible><LABEL for=keyword_in_id><SPAN 
      class=fieldlabeltext>Search</SPAN></LABEL></SPAN> <INPUT id=keyword_in_id 
      maxLength=65 name=KEYWRD_IN> <INPUT type=submit value=Go> </FORM></DIV></TD>
    <TD class=pldefault>
      <P class=rightaligntext><SPAN class=pageheaderlinks><A 
      class=submenulinktext2 accessKey=2 
      href="http://banner7bl04.uncfsu.edu:9000/PROD/twbksite.P_DispSiteMap?menu_name_in=bmenu.P_MainMnu&amp;depth_in=2&amp;columns_in=3">SITE 
      MAP</A> | <A class=submenulinktext2 onblur="window.status=''; return true" 
      onmouseover="window.status='';  return true" 
      onfocus="window.status='';  return true" accessKey=H 
      onclick="popup = window.open('/wtlhelp/twbhhelp.htm', 'PopupPage','height=450,width=500,scrollbars=yes,resizable=yes'); return false" 
      onmouseout="window.status=''; return true" 
      href="http://banner7bl04.uncfsu.edu:9000/wtlhelp/twbhhelp.htm" 
      target=_blank>HELP</A> | <A class=submenulinktext2 accessKey=3 
      href="http://banner7bl04.uncfsu.edu:9000/PROD/twbkwbis.P_Logout">EXIT</A> 
      </SPAN></P></TD></TR></TBODY></TABLE></DIV>
<DIV class=pagetitlediv>
<TABLE class=plaintable width="100%" 
summary="This table displays title and static header displays.">
  <TBODY>
  <TR>
    <TD class=pldefault>
      <H2>Detailed Class Information</H2></TD>
    <TD class=pldefault>&nbsp; </TD>
    <TD class=pldefault>
      <P class=rightaligntext>
      <DIV class=staticheaders>Spring Semester 2010<BR>Mar 25, 
  2010<BR></DIV></TD></TR>
  <TR>
    <TD class=bg3 width="100%" colSpan=3><IMG title="Transparent Image" 
      height=3 alt="Transparent Image" hspace=0 
      src="490_files/web_transparent.gif" width=10 border=0 
    name=web_transparent></TD></TR></TBODY></TABLE><A name=main_content></A></DIV>
<DIV class=pagebodydiv><!--  ** END OF twbkwbis.P_OpenDoc **  -->
<TABLE class=datadisplaytable width="100%" 
summary="This table is used to present the detailed class information.">
  <CAPTION class=captiontext>Detailed Class Information</CAPTION>
  <TBODY>
  <TR>
    <TH class=ddlabel scope=row>Senior Project - 3221 - CSC 490 - 
  01<BR><BR></TH></TR>
  <TR>
    <TD class=dddefault><SPAN class=fieldlabeltext>Associated Term: 
      </SPAN>Spring Semester 2010 <BR><SPAN class=fieldlabeltext>Levels: 
      </SPAN>Undergraduate <BR><BR>Main Campus <BR>Lecture Schedule Type 
      <BR>Classroom Instructional Method <BR>3.000 Credits <BR><A 
      href="http://banner7bl04.uncfsu.edu:9000/PROD/bwckctlg.p_display_courses?term_in=201020&amp;one_subj=CSC&amp;sel_crse_strt=490&amp;sel_crse_end=490&amp;sel_subj=&amp;sel_levl=&amp;sel_schd=&amp;sel_coll=&amp;sel_divs=&amp;sel_dept=&amp;sel_attr=">View 
      Catalog Entry</A> <BR><BR><BR>
      <TABLE class=datadisplaytable width="100%" 
      summary="This layout table is used to present the seating numbers.">
        <CAPTION class=captiontext>Registration Availability</CAPTION>
        <TBODY>
        <TR>
          <TD class=dddead>&nbsp;</TD>
          <TH class=ddheader scope=col><SPAN 
            class=fieldlabeltext>Capacity</SPAN></TH>
          <TH class=ddheader scope=col><SPAN 
          class=fieldlabeltext>Actual</SPAN></TH>
          <TH class=ddheader scope=col><SPAN 
            class=fieldlabeltext>Remaining</SPAN></TH>
        <TR>
          <TH class=ddlabel scope=row><SPAN 
          class=fieldlabeltext>Seats</SPAN></TH>
          <TD class=dddefault>15</TD>
          <TD class=dddefault>16</TD>
          <TD class=dddefault>-1</TD></TR>
        <TR>
          <TH class=ddlabel scope=row><SPAN class=fieldlabeltext>Waitlist 
            Seats</SPAN></TH>
          <TD class=dddefault>0</TD>
          <TD class=dddefault>0</TD>
          <TD 
class=dddefault>0</TD></TR></TBODY></TABLE><BR><BR></TD></TR></TBODY></TABLE><BR>
<TABLE class=datadisplaytable width="50%" 
summary="This is for formatting of the bottom links.">
  <TBODY>
  <TR>
    <TD class=ntdefault><A onblur="window.status='';  return true" 
      onmouseover="window.status='Return to Previous';  return true" 
      onfocus="window.status='Return to Previous';  return true" 
      onmouseout="window.status='';  return true" 
      href="javascript:history.go(-1)">Return to Previous</A> </TD>
    <TD class=ntdefault><A 
      href="http://banner7bl04.uncfsu.edu:9000/PROD/bwckschd.p_disp_dyn_sched">New 
      Search</A></TD></TR></TBODY></TABLE><!--  ** START OF twbkwbis.P_CloseDoc **  -->
<TABLE class=plaintable cellSpacing=0 cellPadding=0 width="100%" 
summary="This is table displays line separator at end of the page." border=0>
  <TBODY>
  <TR>
    <TD class=bgtabon width="100%" colSpan=2><IMG title="Transparent Image" 
      height=3 alt="Transparent Image" hspace=0 
      src="490_files/web_transparent.gif" width=10 border=0 
    name=web_transparent></TD></TR></TBODY></TABLE><A class=skiplinks 
onblur="window.status=''; return true" 
onmouseover="window.status='Skip to top of page'; return true" 
onfocus="window.status='Skip to top of page'; return true" 
onmouseout="window.status=''; return true" 
href="http://banner7bl04.uncfsu.edu:9000/PROD/bwckschd.p_disp_detail_sched?term_in=201020&amp;crn_in=3221#top">Skip 
to top of page</A> </DIV>
<DIV class=pagefooterdiv><SPAN class=releasetext>Release: 8.0</SPAN> </DIV>
<DIV class=poweredbydiv><A href="http://www.sct.com/"><IMG 
title="Powered by Sungard" height=24 alt="Powered by Sungard" hspace=0 
src="490_files/web_powered_by.gif" width=187 border=0 name=web_powered_by></A> 
</DIV>
<DIV class=div1></DIV>
<DIV class=div2></DIV>
<DIV class=div3></DIV>
<DIV class=div4></DIV>
<DIV class=div5></DIV>
<DIV class=div6></DIV></BODY></HTML>

There output i receive is

[['\n       \n       Search  Search      ',
  '\n       SITE \n      MAP [2]  |  HELP [3]  |  EXIT [4]  \n      '],
 ['\n       Detailed Class Information',
  '\xa0  ',
  '\n       \n       Spring Semester 2010 Mar 25, \n  2010'],
 ['Transparent Image'],
 [],
 ['15', '16', '-1'],
 ['0', '0', '0'],
 ['0', '0', '0'],
 ['Return to Previous [6]  ', 'New \n      Search [7]'],
 ['Transparent Image']]

The out put i am looking to receive is

 ['15', '16', '-1'],
 ['0', '0', '0'],

I would appreciate help, thanks!

I am trying to parse a specific part of this html file

0 Replies - 1811 Views - Last Post: 27 April 2010 - 06:25 PM Rate Topic:

#1 hazezoos

Python HTML Parsing Help!

General Discussion

Programming Help

Web Development

Follow & Share

Give It A Try!

Python Tutorials

Reference Sheets

Python Snippets

DIC Chatroom

Bye Bye Ads

Monthly Drawing

I am trying to parse a specific part of this html file

Python HTML Parsing Help!

Related Python Topicsbeta

Follow & Share

Give It A Try!

Reference Sheets

Bye Bye Ads

Monthly Drawing

Related Python Topics^beta