# print data.encode("utf8") return data def save_stock_struct(stock_code, data, dir): file_name = dir + "/" + stock_code file = open(file_name, "w") file.write(data) file.close() web = "http://f10.eastmoney.com/f10_v2/CapitalStockStructure.aspx?code=sz000001" save_dir = "../../../data/stock_struct/eastmoney" if __name__ == "__main__": stocks = read_stock("sh") print len(stocks) # for k,v in stocks.items(): # url = "http://f10.eastmoney.com/f10_v2/CapitalStockStructure.aspx?code=sh{0}".format(k) # print url # save(k, get_stock_struct(k, url), save_dir) # stocks = read_stock("sz") print len(stocks) i = 0 for k, v in stocks.items()[500:]: url = "http://f10.eastmoney.com/f10_v2/CapitalStockStructure.aspx?code=sz{0}".format(k) print i, url save(k, get_stock_struct(k, url), save_dir) i += 1
# print data.encode("utf8") return data def save_stock_struct(stock_code, data, dir): file_name = dir + "/" + stock_code file = open(file_name, "w") file.write(data) file.close() web = "http://f10.eastmoney.com/f10_v2/CapitalStockStructure.aspx?code=sz000001" save_dir = "../../../data/stock_struct/eastmoney" if __name__ == "__main__": stocks = read_stock("sh") print len(stocks) # for k,v in stocks.items(): # url = "http://f10.eastmoney.com/f10_v2/CapitalStockStructure.aspx?code=sh{0}".format(k) # print url # save(k, get_stock_struct(k, url), save_dir) # stocks = read_stock("sz") print len(stocks) i = 0 for k, v in stocks.items()[500:]: url = "http://f10.eastmoney.com/f10_v2/CapitalStockStructure.aspx?code=sz{0}".format( k) print i, url save(k, get_stock_struct(k, url), save_dir)
finally: pass def wget2(url): try: buf = cStringIO.StringIO() c = pycurl.Curl() c.setopt(c.URL, url) c.setopt(pycurl.USERAGENT, "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:40.0) Gecko/20100101 Firefox/40.0") c.setopt(c.WRITEFUNCTION, buf.write) c.perform() s = buf.getvalue() buf.close() return s finally: pass return None if __name__ == "__main__": stocks = read_stock("sz") i=0 for k,v in stocks.items()[700:]: print i, v[0], v[1] url = "http://xueqiu.com/S/SZ{0}/historical.csv".format(v[0]) # url = "http://real-chart.finance.yahoo.com/table.csv?s={0}.SS&ignore=.csv".format(v[0]) wget(url, "../../../data/price/sz/xueqiu/{0}".format(v[0])) i += 1
try: buf = cStringIO.StringIO() c = pycurl.Curl() c.setopt(c.URL, url) c.setopt( pycurl.USERAGENT, "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:40.0) Gecko/20100101 Firefox/40.0" ) c.setopt(c.WRITEFUNCTION, buf.write) c.perform() s = buf.getvalue() buf.close() return s finally: pass return None if __name__ == "__main__": stocks = read_stock("sz") i = 0 for k, v in stocks.items()[700:]: print i, v[0], v[1] url = "http://xueqiu.com/S/SZ{0}/historical.csv".format(v[0]) # url = "http://real-chart.finance.yahoo.com/table.csv?s={0}.SS&ignore=.csv".format(v[0]) wget(url, "../../../data/price/sz/xueqiu/{0}".format(v[0])) i += 1