File size: 1,227 Bytes
74475ac 01677a0 5d719e2 74475ac 82a33ed 5d719e2 74475ac 01677a0 5d719e2 |
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 34 35 36 37 38 39 40 41 42 |
"""
This script is responsible for collecting data from various websites related to financial and policy information in China.
It fetches data from different sources, extracts relevant information, translates it, and updates the content accordingly.
The collected data includes policy interpretations, financial news, macroeconomic research, and more.
"""
import logging
import os
from dotenv import load_dotenv
from source import cbirc, csrc, eastmoney, gov, mofcom, ndrc, safe, stats, mof
from glue import glue_job_run
from prefect import flow
load_dotenv()
logging.basicConfig(
format='%(asctime)s - %(levelname)s - %(funcName)s - %(message)s')
logging.getLogger().setLevel(logging.INFO)
delta = int(os.environ.get('DELTA') or '1')
logging.info("DELTA = %s", delta)
@flow(name="Data Collection - Daily", log_prints=True)
def main():
"""
Orchestrates the data collection process by calling the crawl functions of different sources.
"""
eastmoney.crawl(delta)
cbirc.crawl(delta)
csrc.crawl(delta)
stats.crawl(delta)
gov.crawl(delta)
safe.crawl(delta)
mofcom.crawl(delta)
ndrc.crawl(delta)
mof.crawl(delta)
glue_job_run()
if __name__ == '__main__':
main()
|