我尝试使用polygon.io下载股票代码两个日期之间的所有分钟条。根据他们的API，API限制为50000个结果。
从他们的Github问题中，我发现了以下comment：
聚合端点没有用于分页的next_url。相反，如果响应中的消息超过50，000条，则需要查询较小时间范围的数据。我建议每次查询查询1个月的分钟条。
这是我目前所做的：
返回符号列表：

from polygon import RESTClient
import os.path
from IPython.display import display
import pandas as pd

key = ''
all_tickers = []
df_list = []
final_df = []
from_ = '2021-05-01'
to = '2022-12-01'

def get_tickers():
    
    with RESTClient(key) as client:
        next_url = None
        while True:
            if next_url is None:
                tickers = client.reference_tickers_v3(type="CS")
            else:
                tickers = client._handle_response("ReferenceTickersV3ApiResponse", next_url, {})
            all_tickers.extend(tickers.results)
            if hasattr(tickers, 'next_url'):
                next_url = tickers.next_url
            else:
                break
    

file_name = 'tickers.csv'
if not os.path.exists(file_name):
    get_tickers()

    all_tickers_copy = pd.DataFrame(all_tickers)
    all_tickers_copy.to_csv(file_name, index=False)
else:
    all_tickers = pd.read_csv(file_name)
    all_tickers = all_tickers['ticker']

返回一个列表，其中包含from_和to日期之间月份的开始和结束日期：

import pandas as pd

start_date, end_date = from_, to
dtrange = pd.date_range(start=start_date, end=end_date, freq='d')
months = pd.Series(dtrange .month)

starts, ends = months.ne(months.shift(1)), months.ne(months.shift(-1))
df = pd.DataFrame({'month_starting_date': dtrange[starts].strftime('%Y-%m-%d'),
                   'month_ending_date': dtrange[ends].strftime('%Y-%m-%d')})

# as a list of lists:
months = [df.columns.values.tolist()] + df.values.tolist()
months = pd.DataFrame(months)

然后，我有一个函数循环遍历我的符号，并在from_和to之间的每个月发出API请求：

def get_daily_agg(from_, to, ticker):
    with RESTClient(key) as client:
        folder_name = 'intraday_bars_gapped_new'
        final_df = pd.DataFrame([])

        try:
            # skip the header and loop through the rows
            for index, row in months[1:].iterrows():
                # save the start and end dates as variables
                from_ = row[0]
                to = row[1]
                print(f'{to} and {from_}')
                r = client.stocks_equities_aggregates(ticker, 1, "minute", from_, to, unadjusted=False, limit='50000')
                print(f'downloading {ticker} from {from_} to {to}')
                df = pd.DataFrame(r.results)
                df = df[['t','v','o','c','h','l', 'vw']]
                df.columns = ['datetime', 'volume','open','close','high', 'low', 'vwap']
                df['datetime'] = pd.to_datetime(df['datetime'],unit='ms')
                df['time'] = df['datetime'].dt.strftime("%H:%M:%S")
                df['date'] = df['datetime'].dt.strftime("%Y-%m-%d")

                final_df.append(df)

        except:
            print(f'nothing found for {ticker} from {from_} to {to}')
            pass

            
    if not os.path.exists(folder_name):
        os.makedirs(folder_name)
        final_df.to_csv('{}/{}.csv'.format(folder_name, ticker), index=False)
    else:
        final_df.to_csv('{}/{}.csv'.format(folder_name, ticker), index=False)

import glob
from pathlib import Path

folder = "daily_bars_filtered/*.csv"
for fname in glob.glob(folder)[:20]:
    ticker = Path(fname).stem
    get_daily_agg(from_, to, ticker)

我的问题是-如何正确分页的结果从polygon.ioAPI？