Python-实现网络爬虫、蜘蛛.doc

| python 中如何提取网页正文啊 谢谢 import urllib.request ? url=/ ? response=urllib.request.urlopen(url) ? page=response.read() ? python提取网页中的文本 import os,sys,datetime??? import httplib,urllib, re??? from sgmllib import SGMLParser??? ?? import types??? ?? class Html2txt(SGMLParser):??? ????def reset(self):??? ????????self.text = ?? ????????self.inbody = True?? ???????? SGMLParser.reset(self)??? ????def handle_data(self,text):??? ????????if self.inbody:??? ????????????self.text += text??? ?? ????def start_head(self,text):??? ????????self.inbody = False?? ????def end_head(self):??? ????????self.inbody = True?? ?? ?? if __name__ == __main__:??? ???? parser = Html2txt()??? ???? parser.feed(urllib.urlopen().read())??? ???? parser.close()??? ????print parser.text.strip()?? python 下载网页 import httplib?? conn=httplib.HTTPConnection( HYPERLINK /) conn.request(GET,/index.html) r1=conn.getresponse() print r1.status,r1.reason data=r1.read() print data conn.close 用python下载网页，超级简单！ from urllib import urlopenwebdata = urlopen().read()print webdata 深入python里面有 python?下载网页内容,用python的pycurl模块实现 用python 下载网页内容还是很不错的，之前是使用urllib模块实验的，但听说有pycurl这个模块，而且比urllib好，所以尝试下，废话不说，以下是代码 #!/usr/bin/env python # -*- coding: utf-8 -*- import StringIO import pycurl def writefile(fstr,xfilename):? f=open(xfilename,w)? f.write(fstr)? f.close html = StringIO.StringIO() c = pycurl.Curl() myurl= HYPERLINK / \n _blank ? c.setopt(pycurl.URL, myurl) ? #写的回调 c.setopt(pycurl.WRITEFUNCTION, html.write) ? c.setopt(pycurl.FOLLOWLOCATION, 1) ? #最大重定向次数,可以预防重定向陷阱 c.setopt(pycurl.MAXREDIRS, 5) ? #连接超时设置 c.setopt(pycurl.CONNECTTIMEOUT, 60) c.setopt(pycurl.TIMEOUT, 300) ? #模拟浏览器 c.setopt(pycurl.USERAGENT, Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322)) ? ? ? #访问,阻塞到访问结束 c.perform() ? #打印出 200(HTTP状态码，可以不需要) print c.getinfo(pycurl.HTTP_CODE) ? #输出网页的内容 print html.getvalue() #保存成down.txt文件 writefile(html.getvalue(),down.txt)  HYPERLINK /archives/category/python/ \n _blan