我正在使用Python处理存储在Firestore中的数据。我已经在本地计算机上创建了一个函数来更新Firestore中的数据,但是现在我想添加一个云功能,以便每天使用Pub / sub和云调度程序自动更新。
这是我正在使用的功能:
from google.cloud import firestore
from datetime import datetime, timedelta
db = firestore.Client.from_service_account_json('credentials/gc.json')
def update_collection__persons():
persons = db.collection(u'collection__persons')
#person_docs = persons.stream()
person_docs = [snapshot for snapshot in persons.stream()]
for person_doc in person_docs:
person_dict = person_doc.to_dict()
#last_updated = person_dict['last_updated']
#last_processed = person_dict['last_processed']
#dt_last_updated = datetime(1, 1, 1) + timedelta(microseconds=last_updated/10)
#dt_last_processed = datetime(1, 1, 1) + timedelta(microseconds=last_processed/10)
#if dt_last_processed < dt_last_updated:
orders = db.collection(u'collection__orders').where(u'email', u'==', person_dict['email'])
orders_docs = [snapshot for snapshot in orders.stream()]
sum_price = 0
count = 0
date_add_list = []
for order_doc in orders_docs:
order_dict = order_doc.to_dict()
sum_price += order_dict['total_price']
count +=1
date_add_list.append(order_dict['dateAdded'])
if count > 0:
data = {'metrics': {'LTV': sum_price,
'AOV': sum_price/count,
'Quantity_orders': count,
'first_order_date': min(date_add_list),
'last_order_date': max(date_add_list)},
'last_processed': int((datetime.utcnow() - datetime(1, 1, 1)).total_seconds() * 10000000),
'delta_last_updated_last_processed': 0}
db.collection(u'collection__persons').document(person_dict['email']).set(data, merge = True)
我想将其放在google函数中,这里有两个问题:
我已阅读到我必须在函数中放入这两个变量:https://cloud.google.com/functions/docs/calling/pubsub?hl=en
def My_function (event, context):
我不知道该变量有什么用,我必须在函数中更改哪些才能使用此变量?
但是我不知道如何在我的函数中实现此日志,我对此没有太多经验
答案 0 :(得分:2)
调用update_blanklabelcom__persons()
的pubsub Cloud Function看起来像这样:
from google.cloud import firestore
from datetime import datetime, timedelta
# Service account provided by Cloud Function environment
db = firestore.Client()
def update_blanklabelcom__persons():
persons = db.collection(u'collection__persons')
person_docs = [snapshot for snapshot in persons.stream()]
for person_doc in person_docs:
person_dict = person_doc.to_dict()
orders = db.collection(u'collection__orders').where(u'email', u'==', person_dict['email'])
orders_docs = [snapshot for snapshot in orders.stream()]
sum_price = 0
count = 0
date_add_list = []
for order_doc in orders_docs:
order_dict = order_doc.to_dict()
sum_price += order_dict['total_price']
count +=1
date_add_list.append(order_dict['dateAdded'])
if count > 0:
data = {'metrics': {'LTV': sum_price,
'AOV': sum_price/count,
'Quantity_orders': count,
'first_order_date': min(date_add_list),
'last_order_date': max(date_add_list)},
'last_processed': int((datetime.utcnow() - datetime(1, 1, 1)).total_seconds() * 10000000),
'delta_last_updated_last_processed': 0}
db.collection(u'collection__persons').document(person_dict['email']).set(data, merge = True)
def persons_pubsub(event, context):
print("update blanklabel started")
update_blanklabelcom__persons()
print("update blanklabel done")
您不需要使用event
和context
变量。它们提供有关调用该函数的pubsub事件的更多信息。要编写日志,可以使用print
语句。您打印的所有内容都会显示在带有时间戳的Cloud Function日志中:
我从控制台as described here部署了此Cloud Function。这是requirements.txt
:
google-cloud-firestore>=1.4.0