python提取网页内容_python 提取网页内容工具

#!/usr/bin/python

#coding=utf8

__doc__="""

This class is used to extract text from a string content,

mostly used when we need to extract what we want from a

downloaded html page

"""

__author__="""jemygraw@gmail.com"""

class TextUtil:

def __init__(self,content):

self.content=content

self.start_index=0

def selectText(self,start,end):

self.start_flag=start

self.end_flag=end

from_index=self.content.find(start,self.start_index)

if from_index!=-1:

end_index=self.content.find(end,from_index+len(start))

if end_index!=-1:

self.start_index=end_index+len(end)

self.from_index=from_index

self.end_index=end_index

return True

return False

def extractText(self):

return self.content[self.from_index+len(self.start_flag):self.end_index]

def deselectText(self):

self.from_index=0

self.end_index=0

self.start_index=0