python 爬取网页正文

#!/usr/bin/env python
#coding:utf-8
import htmllib,urllib2
import formatter,StringIO
import urllib

class TrackingParser(htmllib.HTMLParser):
    """Try to keep accurate pointer of parsing location."""
    def __init__(self, writer, *args):
        htmllib.HTMLParser.__init__(self, *args)
        self.writer = writer
    def parse_starttag(self, i):
        index = htmllib.HTMLParser.parse_starttag(self, i)
        self.writer.index = index
        print 'vvvvvvvvvvvvvvvvvvvvvvv\n'
        print index
        return index
    def parse_endtag(self, i):
        print 'vvvvvvvvvvvvvvvvvvvvvvv\n'
        self.writer.index = i
        return htmllib.HTMLParser.parse_endtag(self, i)
class Paragraph:
    def __init__(self):
        self.text = ''
        self.bytes = 0
        self.density = 0.0

class LineWriter(formatter.AbstractWriter):
    def __init__(self, *args):
        self