在这里希望得到一些帮助。全文，这是我的第一个“有目的” Python脚本。在此之前，我只涉猎了一点，说实话，我仍然在学习，所以也许我在这里跳得太早了。
长话短说，一直在解决各种类型的不匹配或只是一般的缩进问题（亲爱的python上帝对此不宽容）。
我想我快完成了，但还有最后几个问题。他们中的大多数人似乎也来自同一部分。该脚本仅意味着获取具有3列的csv文件，并使用该文件根据第一列（iOS或Android）发送请求。问题是当我创建要发送的正文时... 这是代码（为便于发布，省略了一些标记）：
#!/usr/bin/python
# -*- coding: utf-8 -*-
import requests
import json
import pandas as pd
from tqdm import tqdm
from datetime import *
import uuid
import warnings
from math import isnan
import time
## throttling based on AF's 80 request per 2 minute rule
def throttle():
i = 0
while i <= 3:
print ("PAUSED FOR THROTTLING!" + "\n" + str(3-i) + " minutes remaining")
time.sleep(60)
i = i + 1
print (i)
return 0
## function for reformating the dates
def date():
d = datetime.utcnow() # # <-- get time in UTC
d = d.isoformat('T') + 'Z'
t = d.split('.')
t = t[0] + 'Z'
return str(t)
## function for dealing with Android requests
def android_request(madv_id,mtime,muuid,android_app,token,endpoint):
headers = {'Content-Type': 'application/json', 'Accept': 'application/json'}
params = {'api_token': token }
subject_identities = {
"identity_format": "raw",
"identity_type": "android_advertising_id",
"identity_value": madv_id
}
body = {
'subject_request_id': muuid,
'subject_request_type': 'erasure',
'submitted_time': mtime,
'subject_identities': dict(subject_identities),
'property_id': android_app
}
body = json.dumps(body)
res = requests.request('POST', endpoint, headers=headers,
data=body, params=params)
print("android " + res.text)
## function for dealing with iOS requests
def ios_request(midfa, mtime, muuid, ios_app, token, endpoint):
headers = {'Content-Type': 'application/json',
'Accept': 'application/json'}
params = {'api_token': token}
subject_identities = {
'identity_format': 'raw',
'identity_type': 'ios_advertising_id',
'identity_value': midfa,
}
body = {
'subject_request_id': muuid,
'subject_request_type': 'erasure',
'submitted_time': mtime,
'subject_identities': list(subject_identities),
'property_id': ios_app,
}
body = json.dumps(body)
res = requests.request('POST', endpoint, headers=headers, data=body, params=params)
print("ios " + res.text)
## main run function. Determines whether it is iOS or Android request and sends if not LAT-user
def run(output, mdf, is_test):
# # assigning variables to the columns I need from file
print ('Sending requests! Stand by...')
platform = mdf.platform
device = mdf.device_id
if is_test=="y":
ios = 'id000000000'
android = 'com.tacos.okay'
token = 'OMMITTED_FOR_STACKOVERFLOW_Q'
endpoint = 'https://hq1.appsflyer.com/gdpr/stub'
else:
ios = 'id000000000'
android = 'com.tacos.best'
token = 'OMMITTED_FOR_STACKOVERFLOW_Q'
endpoint = 'https://hq1.appsflyer.com/gdpr/opengdpr_requests'
for position in tqdm(range(len(device))):
if position % 80 == 0 and position != 0:
throttle()
else:
req_id = str(uuid.uuid4())
timestamp = str(date())
if platform[position] == 'android' and device[position] != '':
android_request(device[position], timestamp, req_id, android, token, endpoint)
mdf['subject_request_id'][position] = req_id
if platform[position] == 'ios' and device[position] != '':
ios_request(device[position], timestamp, req_id, ios, token, endpoint)
mdf['subject_request_id'][position] = req_id
if 'LAT' in platform[position]:
mdf['subject_request_id'][position] = 'null'
mdf['error status'][position] = 'Limit Ad Tracking Users Unsupported. Device ID Required'
mdf.to_csv(output, sep=',', index = False, header=True)
# mdf.close()
print ('\nDONE. Please see ' + output
+ ' for the subject_request_id and/or error messages\n')
## takes the CSV given by the user and makes a copy of it for us to use
def read(mname):
orig_csv = pd.read_csv(mname)
mdf = orig_csv.copy()
# Check that both dataframes are actually the same
# print(pd.DataFrame.equals(orig_csv, mdf))
return mdf
## just used to create the renamed file with _LOGS.csv
def rename(mname):
msuffix = '_LOG.csv'
i = mname.split('.')
i = i[0] + msuffix
return i
## adds relevant columns to the log file
def logs_csv(out, df):
mdf = df
mdf['subject_request_id'] = ''
mdf['error status'] = ''
mdf['device_id'].fillna('')
mdf.to_csv(out, sep=',', index=None, header=True)
return mdf
## solely for reading in the file name from the user. creates string out of filename
def readin_name():
mprefix = input('FILE NAME: ')
msuffix = '.csv'
mname = str(mprefix + msuffix)
print ('\n' + 'Reading in file: ' + mname)
return mname
def start():
print ('\nWelcome to GDPR STREAMLINE')
# # blue = OpenFile()
testing = input('Is this a test? (y/n) : ')
# return a CSV
name = readin_name()
import_csv = read(name)
output_name = rename(name)
output_file = logs_csv(output_name, import_csv)
run( output_name, output_file, testing)
# # print ("FILE PATH:" + blue)
## to disable all warnings in console logs
warnings.filterwarnings('ignore')
start()
这是错误堆栈跟踪：
Reading in file: test.csv
Sending requests! Stand by...
0%| | 0/384 [00:00<?, ?it/s]
Traceback (most recent call last):
File "a_GDPR_delete.py", line 199, in <module>
start()
File "a_GDPR_delete.py", line 191, in start
run( output_name, output_file, testing)
File "a_GDPR_delete.py", line 114, in run
android_request(device[position], timestamp, req_id, android, token, endpoint)
File "a_GDPR_delete.py", line 57, in android_request
body = json.dumps(body)
File "/Users/joseph/anaconda3/lib/python3.6/json/__init__.py", line 231, in dumps
return _default_encoder.encode(obj)
File "/Users/joseph/anaconda3/lib/python3.6/json/encoder.py", line 199, in encode
chunks = self.iterencode(o, _one_shot=True)
File "/Users/joseph/anaconda3/lib/python3.6/json/encoder.py", line 257, in iterencode
return _iterencode(o, 0)
File "/Users/joseph/anaconda3/lib/python3.6/json/encoder.py", line 180, in default
o.__class__.__name__)
TypeError: Object of type 'int64' is not JSON serializable
TL; DR： 在具有另一个嵌套JSON的JSON上调用时，出现typeError。我已经确认嵌套的JSON是问题所在，因为如果我删除“ subject_identities”部分，则该部分可以编译并起作用...但是我使用的API需要这些值，因此如果没有该部分，该操作实际上将不起作用。 / p>
这又是相关的代码（在我最初使用WAS的版本中）：
def android (madv_id, mtime, muuid):
headers = {
"Content-Type": "application/json",
"Accept": "application/json"
}
params = {
"api_token": "OMMITTED_FOR_STACKOVERFLOW_Q"
}
body = {
"subject_request_id": muuid, #muuid,
"subject_request_type": "erasure",
"submitted_time": mtime,
"subject_identities": [
{ "identity_type": "android_advertising_id",
"identity_value": madv_id,
"identity_format": "raw" }
],
"property_id": "com.tacos.best"
}
body = json.dumps(body)
res = requests.request("POST",
"https://hq1.appsflyer.com/gdpr/opengdpr_requests",
headers=headers, data=body, params=params)
我感觉自己已经接近这项工作。早期，我有一个简单得多的版本可以工作，但我改写了它，使其更具动态性，并使用了较少的硬编码值（以便最终可以将其应用于我正在使用的任何应用程序，而不仅仅是这两个应用程序）。
请很好，我是python的新手，并且对一般的编码也很生疏（因此尝试做这样的项目）
答案 0 :(得分：0)
您可以像这样检查numpy dtypes：
if hasattr(obj, 'dtype'):
obj = obj.item()
这会将其转换为最接近的等效数据类型
编辑：
显然np.nan是JSON可序列化的，所以我从答案中删除了这个问题
答案 1 :(得分：0)
感谢大家在这里提供的如此迅速的帮助。显然，错误消息欺骗了我，因为@ juanpa.arrivillaga的修复程序做了一次调整。
正确的代码在以下部分上：
DoSomething()
在这里：
android_request(str(device[position]), timestamp, req_id, android, token, endpoint)
我显然不得不转换为字符串，即使这些值本来不是整数，并且看起来像这样ios_request(str(device[position]), timestamp, req_id, ios, token, endpoint)