import urllib
from lxml import etree
url = 'http://mp.weixin.qq.com/s?__biz=MjM5NzU0MzU0Nw==&mid=2651371848&idx=1&sn=2aeeeacc12a8fa8533b912743a58b764&scene=0#wechat_redirect'
page = urllib.urlopen(url)
html = page.read()
tree = etree.HTML(html)
#去掉多余字符和标签
mystr = tree.xpath('//*[@id="js_content"]')[0].xpath('string(.)').replace('\n','').replace(' ','').replace('\r','')