使用re, urllib, threading 多线程抓取天涯帖子内容，设置url为需抓取的天涯帖子的第一页，设置file_name为下载后的文件名
代码如下:
#coding:utf-8
import urllibimport reimport threadingimport os, time
class down_tianya(threading.thread): “””多线程下载””” def __init__(self, url, num, dt): threading.thread.__init__(self) self.url = url self.num = num self.txt_dict = dt
def run(self): print ‘downling from %s’ % self.url self.down_text()
def down_text(self): “””根据传入的url抓出各页内容，按页数做键存入字典””” html_content =urllib.urlopen(self.url).read() text_pattern = re.compile(‘时间：(.*?).*?.*?