爬虫处理gzip压缩格式网站的方法
#coding:utf-8import urllib2import reimport zliburl_address = 'http://www.sina.com.cn'f = urllib2.urlopen(url_address)buf = f.read()buf = zlib.decompress(buf, 16+zlib.MAX_WBITS);#buf = buf.replace("\n","")print buf
