Create a CHM file for PyGTK2 Tutorial

Document source: PyGTK2 Tutorial[1]
[1] http://www.pygtk.org/dist/pygtk2tutorial.tgz

The main problem is to parse the contents from index.html write then into a HHC file for MS HtmlHelp Workshop.

You can use this simple script to do this (see below)
pygtk-index2hhc.py pygtk2tut.hhc index.html

P.S:
As to the PyGTK2 Reference[2], you can download the devhelp index file[3], and then use my devhelp2chm.sh[4]to get the .HHP, .HHC and .HHK.
[2] http://www.pygtk.org/dist/pygtk2reference.tbz2
[3] http://www.moeraki.com/pygtkreference/pygtk2reference.devhelp.gz
[4] http://www.linuxeden.com/forum/blog/resserver.php?blogId=110848&resource=devhelp2chm.sh







#!env python from sgmllib import SGMLParser import htmlentitydefs from chmmaker import HHCWriter import os class ContentParser(SGMLParser): def __init__(self, outputfile): self.hhcwriter = HHCWriter(outputfile) self.hhcwriter.print_header() SGMLParser.__init__(self) def __del__(self): self.hhcwriter.print_footer() def reset(self): SGMLParser.reset(self) # some temp variables self.level=0 self.title = self.url = "" self.in_href = False def start_dd(self, attrs):
self.hhcwriter.hhcfile.write("<UL>")

def end_dd(self):
self.hhcwriter.hhcfile.write("</UL>")

def start_a(self, attrs): for attr in attrs: if attr[0].lower()=='href': self.in_href = True self.title = "" self.url = attr[1] break def end_a(self): if self.in_href and self.title and self.url: self.on_href(self.title.replace('"', ""), self.url) self.in_href = False self.title = self.url = "" def handle_data(self, text): self.title += text def handle_charref(self, ref): if self.in_href: self.title += "&#%(ref)s;" % locals() def handle_entityref(self, ref): if self.in_href: self.title += "&%(ref)s" % locals() if htmlentitydefs.entitydefs.has_key(ref): self.title += ";" def on_href(self, title, url): target=url if url[-3:]=='fig': target= "" if title and target: self.hhcwriter.add_topic(title, target) if __name__=='__main__': import sys if len(sys.argv)<3: print "Usage: %s hhcfilename index.html" % sys.argv[0] sys.exit() trans=ContentParser(sys.argv[1]) fh=open(sys.argv[2], "r"[img]/images/wink.gif[/img] try: trans.feed(fh.read()) except: pass trans.close() fh.close()
# vim:expandtab softtabstop=4

Powered by ScribeFire.