量化数据源

1

pip install tigeropen

1

pip install futu-api

1

pip install yfinance

1

pip install polygon-api-client

1

pip install alpha_vantage

1
2
3
4
5
6
7
8

from tigeropen.tiger_open_config import TigerOpenClientConfig
from tigeropen.quote.quote_client import QuoteClient
from tigeropen.common.consts import Market

client_config = TigerOpenClientConfig(props_path='tiger_openapi_config.properties')
quote_client = QuoteClient(client_config)

symbols = quote_client.get_symbol_names(market=Market.US,include_otc=False)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

import pandas as pd
from tigeropen.quote.domain.filter import StockFilter
from tigeropen.common.consts.filter_fields import StockField

filter1 = StockFilter(StockField.MarketValue,filter_min=100000000)
filter2 = StockFilter(StockField.Volume,filter_min=10000000)
scanner_result = quote_client.market_scanner(filters=[filter1,filter2], market=Market.US)

sr = pd.Series([item.symbol for item in scanner_result.items],name='symbol').sort_values()
sr.to_csv('stock.csv',index=False)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31

params = {
    'exchanges': [],
    'plates': [],
    'values': [
        {
            'key': 'marketValue',
            'value': {
                'min': 1,
                'max': None
            }
        },
        {
            'key': 'volume-intraday-volumeCumulativeAverage',
            'value': {
                'period': 30,
                'min': 1000,
                'max': None
            }
        }
    ],
    'isWatch': False,
    'market': 2,
    'dataFrom': 0,
    'dataMaxCount': 50,
    'extendsRetrie': True,
    'sort': {
        'key': 'changeRatio',
        'order': 'desc'
    },
    'accountStatus': False
}

1
2
3
4
5
6
7
8
9

import hashlib
import hmac
import json

def get_quote_token(params):
    t = json.dumps(params,separators=(',', ':'))
    hmac_result = hmac.new(key="quote_web".encode('utf-8'),msg=t.encode('utf-8'),digestmod=hashlib.sha512).hexdigest()
    hash_result = hashlib.sha256(hmac_result[:10].encode('utf-8')).hexdigest()[:10]
    return hash_result

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31

import requests
import pandas as pd
from utils import get_quote_token

quote_token = get_quote_token(params)
csrf_token = 'xxxxx'

headers = {
    'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
    'accept':'application/json, text/plain, */*',
    'accept-encoding':'gzip, deflate, br, zstd',
    'accept-language':'zh-CN,zh;q=0.9',
    'Content-Type':'application/json',
    'referer':'https://www.futunn.com/screener',
    'origin':'https://www.futunn.com',
    'futu-x-csrf-token':csrf_token,
    'quote-token':quote_token
}
cookies = {
    'csrfToken':csrf_token
}

url = 'https://www.futunn.com/quote-api/quote-v2/get-screener-list'
response = requests.post(url, headers=headers, json=params,cookies=cookies)

if response.status_code == 200:
    data = response.json()
    df = pd.DataFrame(data['data']['list'])
	df.to_csv('stock.csv',index=False)
else:
    print(f"请求失败: {response.text}")

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

import time
params = {
  "stockId": "xxx",
  "marketType": "2",
  "type": "2",
  "marketCode": "11",
	"instrumentType": "3",
	"subInstrumentType": "0",
	"_": str(int(time.time()))
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30

def get_kline(stock_id):
    params = {
      "stockId": str(stock_id),
      "marketType": "2",
      "type": "2",
      "marketCode": "11",
      "instrumentType": "3",
      "subInstrumentType": "0",
      "_": str(int(time.time()))
    }
    quote_token = get_quote_token(params)
    csrf_token = 'xxxxx'
    headers = {
      'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
      'accept':'application/json, text/plain, */*',
      'accept-encoding':'gzip, deflate, br, zstd',
      'accept-language':'zh-CN,zh;q=0.9',
      'Content-Type':'application/json',
      'origin':'https://www.futunn.com',
      'futu-x-csrf-token':csrf_token,
      'quote-token':quote_token
    }
    cookies = {
      'csrfToken':csrf_token
    }
    url = 'https://www.futunn.com/quote-api/quote-v2/get-kline'
    response = requests.get(url, headers=headers, params=params,cookies=cookies)
    if response.status_code == 200:
        data = response.json()
        return data

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20

import time
from sqlalchemy import create_engine

engine = create_engine('mysql+pymysql://USERNAME:PASSWORD@HOST:PORT/DATABASE')

for idx,row in stock.iterrows():
    stock_id = row['stockId']
    stock_code = row['stockCode']
    print(f'{idx+1}/{len(stock)} {stock_code}')
    data = get_kline(stock_id)
    df = pd.DataFrame(data['data']['list'])
    df = df.drop('lc',axis=1)
    df['k'] = pd.to_datetime(df['k'],unit='s').dt.tz_localize('UTC').dt.tz_convert('US/Eastern')
    df['r'] = df['r']*100
    df['symbol'] = stock_code
    df.columns=['datetime','open','close','high','low','volumn','turnover','turnover_rate','close_price_diff','symbol']
    begin = datetime.strftime(datetime.now()-timedelta(days=365*2),'%Y-%m-%d %H:%M:%S')
    result = df[df['datetime']>begin]
    result.to_sql('DailyStock', con=engine, if_exists='append', index=False)
    time.sleep(5)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12

from datetime import datetime

params = {
    'fetchType': '2',
    'code': 'xxxxx',
    'market': 'US',
    'quarter': '8',
    'date': datetime.strftime(datetime.now(),'%Y-%m-%d'),
    'flag': '0',
    'size': '12',
    '_':str(int(time.time()))
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33

def get_report(symbol,fetchType):
    params = {
    'fetchType': str(fetchType),
    'code': symbol,
    'market': 'US',
    'quarter': '8',
    'date': datetime.strftime(datetime.now(),'%Y-%m-%d'),
    'flag': '0',
    'size': '12',
    '_':str(int(time.time()))
    }
    quote_token = get_quote_token(params)
    csrf_token = 'xxxxx'
    headers = {
        'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
        'accept':'application/json, text/plain, */*',
        'accept-encoding':'gzip, deflate, br, zstd',
        'accept-language':'zh-CN,zh;q=0.9',
        'Content-Type':'application/json',
        'origin':'https://www.futunn.com',
        'futu-x-csrf-token':csrf_token,
        'quote-token':quote_token
    }
    cookies = {
        'csrfToken':csrf_token
    }
    url = 'https://www.futunn.com/quote-api/quote-v2/get-reports-data'

    response = requests.get(url, headers=headers, params=params,cookies=cookies)
    
    if response.status_code == 200:
        data = response.json()
        return data

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25

import time
from sqlalchemy import create_engine

engine = create_engine('mysql+pymysql://USERNAME:PASSWORD@HOST:PORT/DATABASE')


for idx,row in stock.iterrows():
    stock_code = row['stockCode']
    print(f'{idx+1}/{len(stock)} {stock_code}')
    data = get_report(stock_code,2)
    df = pd.DataFrame([[row['raw_value'] for row in item ] for item in data['data']['list']['values']],columns=data['data']['list']['keys'])
    df['symbol'] = stock_code
    columns = ['symbol','PeriodEndingDate','TotalRevenue','OperatingRevenue','GrossProfit',
           'NetIncome','NetIncomeCommonStockholders','BasicEPS','DilutedEPS',
           'OperatingIncome','InterestIncome','InterestExpense','TotalExpenses',
           'OperatingExpense','ResearchAndDevelopment','DepreciationAmortizationDepletion',
           'ProvisionForDoubtfulAccounts','PretaxIncome','NetPremiumsWritten','NetRealizedGainLossOnInvestments',
           'TaxProvision','MinorityInterests','SpecialIncomeCharges','CumulativeEffectOfAccountingChange',
           'NetIncomeFromTaxLossCarryforward','DividendPerShare','TotalPremiumsEarned','NetInvestmentIncome']
    result = df[columns].copy()
    result['PeriodEndingDate'] = pd.to_datetime(result['PeriodEndingDate'],unit='s').dt.tz_localize('UTC').dt.tz_convert('US/Eastern')
    begin = datetime.strftime(datetime.now()-timedelta(days=365*2),'%Y-%m-%d')
    result = result[0:(result['PeriodEndingDate']>begin).sum()+1].copy()
    result.to_sql('StockReport', con=engine, if_exists='append', index=False)
    time.sleep(5)