Python爬虫实例扒取2345天气预报

#-*- coding:utf-8 -*- 
import urllib2 
import json 
 
months = [1,2,3,4,5,6,7,8,9,10,11,12] 
years = [2011,2012,2013,2014,2015,2016] 
city = [53892]  #邯郸代码53892 
 
for y in years: 
  for m in months: 
    for c in city: 
      url = "http://tianqi.2345.com/t/wea_history/js/"+str(c)+"_"+str(y)+str(m)+".js" 
      print url 
      html = urllib2.urlopen(url) 
      srcData = html.read() 
      #JsonData = json.loads(srcData) 
      file = open("d:/json/"+str(c)+"handan/weather"+str(c)+"_"+str(y)+str(m)+".json","w") 
      file.write(srcData) 
      file.close() 

#-*- coding:utf-8 -*- 
import json 
import re 
import time 
 
Year = [2014] 
Month = [1] 
 
for y in Year: 
  for m in Month: 
     
    """ 
    2016年2月15日终于改成功。 
    是因为正则匹配后的编码问题，导致输出时无法显示。 
    在每个正则匹配的元组后添加 .decode('gbk').encode('utf-8'),成功输出 
    """ 
    content = fRead.read() 
    pattern = re.compile('{ymd:\'(.*","+item[1].decode('gbk').encode('utf-8'),","+item[2].decode('gbk').encode('utf-8'),","+item[3].decode('gbk').encode('utf-8'),","+item[4].decode('gbk').encode('utf-8'),","+item[5].decode('gbk').encode('utf-8') 
      time.sleep(0.1) 
 
    fRead.close()