WebSVN – SmartDukaan – Diff – //trunk/PyDTR/src/dtr/sources/amazon.py

         super(Store, self).__init__(store_id)
     def getName(self):
         return "amazon"
-    def parseOrderRawHtml(self, orderId, subTagId, userId, rawHtml, orderSuccessUrl, insert=False):
+    def parseOrderRawHtml(self, orderId, subTagId, userId, rawHtml, orderSuccessUrl, track=False):
         resp = {}
         resp['result'] = 'ORDER_NOT_CREATED'
         if ORDER_SUCCESS_URL in orderSuccessUrl or THANKYOU_URL in orderSuccessUrl:
             try:
                 soup = BeautifulSoup(rawHtml)
                 if mo is not None:
                     merchantOrder = Order(orderId, userId, subTagId, self.store_id, orderSuccessUrl, False)
                     merchantOrder.createdOn = mo.get("createdOn")
                     merchantOrder.createdOnInt =  mo.get("createdOnInt")
                 else:
+                    print "Could not find amazon order with order Id", orderId
                     merchantOrder = Order(orderId, userId, subTagId, self.store_id, orderSuccessUrl)
                 soup = BeautifulSoup(rawHtml)
                 try:
                     self.parseOldStlye(merchantOrder, soup)
                 except:
     def trackOrdersForUser(self, userId, url, rawHtml):
         directory = "/tmp/User" + str(userId)
         if not os.path.exists(directory):
             os.makedirs(directory)
-        filename = directory + "/" + str(datetime.now())
-        print "filename---", filename
-        f = open(filename,'w')
-        f.write(rawHtml) # python will convert \n to os.linesep
-        f.close() # you can omit in most cases as the destructor will call if
         try:
             searchMap = {'userId':userId}
             collectionMap = {'merchantOrderId':1}
             activeOrders = self._getActiveOrders(searchMap, collectionMap)
             datetimeNow = datetime.now()
             timestamp = int(time.mktime(datetimeNow.timetuple()))
             print "url----------------", url
             if url == 'https://www.amazon.in/gp/css/order-history' or 'https://www.amazon.in/gp/css/order-history/?orderFilter=cancelled' in url:
+                if url == 'https://www.amazon.in/gp/css/order-history':
+                    filename = directory + "/orderSummary" + datetime.strftime(datetime.now(), '%d-%m:%H:%M:%S')
+                else:
+                    filename = directory + "/cancelledSummary" + datetime.strftime(datetime.now(), '%d-%m:%H:%M:%S')
+                f = open(filename,'w')
+                f.write(rawHtml) # python will convert \n to os.linesep
+                f.close() # you can omit in most cases as the destructor will call if
                 soup = BeautifulSoup(rawHtml)
                 allOrders = soup.find(id="ordersContainer").findAll('div', {'class':'a-box-group a-spacing-base order'})
                 bulk = self.db.merchantOrder.initialize_ordered_bulk_op()
                 for activeOrder in activeOrders:
                     for orderEle in allOrders:
                 bulk.execute()
                 return 'PARSED_SUCCESS'
             else:
                 merchantOrderId = re.findall(r'https://www.amazon.in/gp/css/summary/edit.html\?orderID=(.*)?', url, re.IGNORECASE)[0]
                 merchantOrder = self.db.merchantOrder.find_one({"merchantOrderId":merchantOrderId})
+                filename = directory + "/" + merchantOrderId
+                f = open(filename,'w')
+                f.write(rawHtml) # python will convert \n to os.linesep
+                f.close() # you can omit in most cases as the destructor will call if
-                self.parseOrderRawHtml(merchantOrder['orderId'], merchantOrder['subTagId'], merchantOrder['userId'], rawHtml, url, False)['result']
+                self.parseOrderRawHtml(merchantOrder['orderId'], merchantOrder['subTagId'], merchantOrder['userId'], rawHtml, url, True)['result']
                 return 'PARSED_SUCCESS'
                 pass
             return 'PARSED_SUCCESS_NO_ORDERS'
         except:
             traceback.print_exc()
 def main():
+    readSSh("/tmp/order2015-04-23 12:39:09.743683")
-    store = getStore(1)
+    #store = getStore(1)
     #store.scrapeStoreOrders()
 #    br = mechanize.Browser()
 #    br.addheaders = [('User-agent','Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11'),
 #                     ('Accept', 'text/html,application/xhtml+xml,application/json,application/xml;q=0.9,*/*;q=0.8'),
 #                     ('Accept-Encoding', 'gzip,deflate,sdch'),
 #                     ('Accept-Language', 'en-US,en;q=0.8'),
 #                     ('Accept-Charset', 'ISO-8859-1,utf-8;q=0.7,*;q=0.3')]
 #    store.scrapeStoreOrders()
-    store.parseOrderRawHtml(1306, "13232", 14, readSSh("/home/amit/322.html"), "https://www.amazon.in/gp/css/summary/edit.html?orderID=171-5570474-5548341")
+    #store.parseOrderRawHtml(1306, "13232", 14, readSSh("/home/amit/322.html"), "https://www.amazon.in/gp/css/summary/edit.html?orderID=171-5570474-5548341")
     #store.parseOrderRawHtml(2121, "13232", 14, readSSh("/home/amit/f1.html"), "https://www.amazon.in/gp/css/summary/edit.html?orderID=171-5196461-3230730")
     #readSSh("/tmp/User211/2015-04-12 10:32:41.905765")
     #store.scrapeAffiliate()
 def readSSh(fileName):
     try:

Subversion Repositories SmartDukaan

(root)//trunk/PyDTR/src/dtr/sources/amazon.py – Rev 14847 → 14945