Kraken API trades endpoint flawed data

Question

i wrote a script to get historical data from the public trades endpoint of the Kraken API, code as follows:

import pandas as pd
import json
import time
import urllib.request

def get_data(pair, since, until):
    global data
    global query
    global json_response
    global api_data
    
    data_columns= ["price", "volume", "time", "buy/sell", "market/limit", "miscellaneous"]
    data = pd.DataFrame(columns= data_columns)
    
    api_start = since
    app_start_time = time.time()
    counter = 1
    
    while api_start < until:
        last_time = time.time()
        api_domain = "https://api.kraken.com/0/public/Trades" + \
                    "?pair=%(pair)s&since=%(since)s" % {"pair":pair, "since": api_start}
        api_request = urllib.request.Request(api_domain)
        try:
            api_data = urllib.request.urlopen(api_request).read()
        except Exception:
            time.sleep(3)
        api_data = json.loads(api_data) 
        if len(api_data["error"]) != 0:
            print(api_data["error"])
            time.sleep(3)
            continue 
        query = pd.DataFrame(api_data["result"][pair], columns = data_columns)
        data = data.append(query, ignore_index= True)
        api_start = int(api_data["result"]["last"][:10])
        counter +=1
        time.sleep(1)    
        print("Request number: %s" %counter)
        print("Time since start: %s minutes" % round((time.time() - app_start_time)/60,2))
        print("Time since last request: %s seconds" % round((time.time() - last_time),2))
        print("last: %s" %api_start)
        print("")

get_data("XXBTZUSD", 1414761200, 1455761200)

After some successful responses, i get flawed responses, looking like this:

As you can see, at some point, the UNIX time stamp simply jumps from 142894080.33775 to 1654992002.801943 and thus resulting in wrong data.

Is that a problem with my code or with the API?

Thanks in advance.

Answer 1

Taking the liberty to simplify your code I cannot confirm your observation. I get proper timestamps.

Try this:

import requests

def get_data(pair, since):
    url = f"https://api.kraken.com/0/public/Trades?pair={pair}&since={since}"
    api_data = requests.get(url)
    api_data = json.loads(api_data.content) 
    return api_data

results = get_data("XBTUSD", 1414761200)

columns= ["price", "volume", "time", "buy/sell", "market/limit", "miscellaneous"]
df = pd.DataFrame(results["result"]["XXBTZUSD"], columns=columns)
df.time = df.time.astype(int)
df.head()

Print out:

    price   volume  time    buy/sell    market/limit    miscellaneous
0   340.09209   0.02722956  1414815678  s   m   
1   340.15346   0.21604000  1414820304  s   m   
2   340.00000   0.03395999  1414820304  s   m   
3   340.00001   0.01000000  1414821818  s   l   
4   340.00000   0.25668009  1414821818  s   l   

Edit:

Using pagination I can confirm the jump in timestamps. The problem very likely lies with the API.

def get_data(pair, since):
    url = f"https://api.kraken.com/0/public/Trades?pair={pair}&since={since}"
    api_data = requests.get(url)
    api_data = json.loads(api_data.content) 
    return api_data

start_ts = 1414761200

frames = []

for _ in range(30):
    print(start_ts)
    print(datetime.fromtimestamp(int(start_ts)))
    tmp = get_data("XBTUSD", start_ts)
    start_ts = tmp["result"]["last"][:10]
    frames.append(pd.DataFrame(results["result"]["XXBTZUSD"]))
    time.sleep(2)

Print out after a couple of iterations:

1438313128
2015-07-31 05:25:28
1653648031
2022-05-27 12:40:31