# html.py - parser functions for html content # # Copyright (C) 2005, 2006, 2007, 2009 Arthur de Jong # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA # # The files produced as output from the software do not automatically fall # under the copyright of the software, unless explicitly stated otherwise. """Parser functions for processing HTML content. This module uses the legacy HTMLParser module. It will only be used if BeatifulSoup is not available and can be considered depricated. This parser will only handle properly formatted HTML.""" import debugio import HTMLParser import urlparse import re import crawler import myurllib from parsers.html import htmlunescape # pattern for matching numeric html entities _charentitypattern = re.compile('([0-9]{1,3});') # pattern for matching spaces _spacepattern = re.compile(' ') # pattern for matching charset declaration for http-equiv tag _charsetpattern = re.compile('charset=([^ ]*)', re.I) # pattern for matching the encoding part of an xml declaration _encodingpattern = re.compile('^xml .*encoding="([^"]*)"', re.I) class _MyHTMLParser(HTMLParser.HTMLParser): """A simple subclass of HTMLParser.HTMLParser continuing after errors and gathering some information from the parsed content.""" def __init__(self, link): """Inialize the menbers in which we collect data from parsing the document.""" self.link = link self.collect = None self.base = None self.title = None self.author = None self.embedded = [] self.children = [] self.anchors = [] self.errmsg = None self.errcount = 0 HTMLParser.HTMLParser.__init__(self) def _location(self): """Return the current parser location as a string.""" (lineno, offset) = self.getpos() if lineno is not None: msg = 'at line %d' % lineno else: msg = 'at unknown line' if offset is not None: msg += ', column %d' % (offset + 1) return msg def _cleanurl(self, url, what='link'): """Do some translations of url.""" # check for spaces in urls # (characters are escaped in myurllib.normalizeurl()) if _spacepattern.search(url): self.link.add_pageproblem( what+' contains unescaped spaces: '+url+', '+self._location() ) # replace nnn; entity refs with proper characters url = _charentitypattern.sub(lambda x:chr(int(x.group(1))), url) return myurllib.normalizeurl(url) def error(self, message): """Override superclass' error() method to ignore errors.""" # construct error message message += ', ' + self._location() # store error message debugio.debug('parsers.html.htmlparser._MyHTMLParser.error(): problem parsing html: '+message) if self.errmsg is None: self.errmsg = message # increment error count self.errcount += 1 if self.errcount > 10: raise HTMLParser.HTMLParseError(message, self.getpos()) def check_for_whole_start_tag(self, i): """Override to catch assertion exception.""" try: return HTMLParser.HTMLParser.check_for_whole_start_tag(self, i) except AssertionError: debugio.debug('parsers.html.htmlparser._MyHTMLParser.check_for_whole_start_tag(): caught assertion error') return None def handle_starttag(self, tag, attrs): """Handle start tags in html.""" # turn attrs into hash attrs = dict(attrs) #