Python获得所有上证公司列表

import urllib
import urllib2
import json
import random
import sys
import os
import codecs

DEBUG=False

# function get the current dirctory
def cur_file_dir():
     path = sys.path[0]
     if os.path.isdir(path):
         return path
     elif os.path.isfile(path):
         return os.path.dirname(path)

url = ‘http://query.sse.com.cn/commonQuery.do‘

headers = {
    ‘Accept‘:r‘*/*‘,
    ‘Accept-Encoding‘:r‘gzip, deflate, sdch‘,
    ‘Accept-Language‘:r‘zh-CN,zh;q=0.8‘,
    ‘Connection‘:r‘keep-alive‘,
    ‘Host‘:r‘query.sse.com.cn‘,
    ‘Referer‘:r‘http://www.sse.com.cn/assortment/stock/list/name/?type=5‘,
    ‘User-Agent‘:r‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.80 Safari/537.36‘
}


values = {
    ‘jsonCallBack‘:‘jsonpCallback47701‘,
    ‘isPagination‘:‘true‘,
    ‘sqlId‘:‘COMMON_SSE_ZQPZ_GPLB_MCJS_SSAG_L‘,
    ‘pageHelp.pageSize‘:‘2000‘,
    ‘_‘:‘1447409570125‘
}


#generate a random integer,  used as query parameter value
values[‘_‘] = random.randint(1000000000000,1999999999999)


data = urllib.urlencode(values)
req = urllib2.Request(url, data, headers)
response = urllib2.urlopen(req)
the_page = response.read()

the_page = unicode(the_page, "utf8").encode("gb2312")

page02 = the_page[19:-1]


jsonContent = json.loads(page02, ‘gb2312‘)

if DEBUG:
    print json.dumps(jsonContent, ensure_ascii=False,indent=1)
    jsonContent.keys()

#Create a new utf-8 file used to store the stock info
stockFile = codecs.open(cur_file_dir() + ‘stocklist.txt‘,‘w‘,‘utf-8‘)

for d in jsonContent[‘pageHelp‘][‘data‘]:
    info = (d[‘NUM‘],d[‘PRODUCTID‘],d[‘PRODUCTNAME‘],d[‘FULLNAME‘])
    stockFile.write(‘ ‘.join(info) + ‘\n‘)

stockFile.close()