main.py

"""
This script is responsible for collecting data from various websites \
related to financial and policy information in China. It fetches data from various sources,\
extracts relevant information, translates it, and updates the content accordingly.
Collected data includes policy interpretations, financial news, macroeconomic research.
"""
import logging
import os

from dotenv import load_dotenv
from prefect import flow

from source import cbirc, csrc, eastmoney, gov, mofcom, ndrc, safe, stats, mof, sohu_ccef
# from glue import glue_job_run

load_dotenv()

logging.basicConfig(
    format='%(asctime)s - %(levelname)s - %(funcName)s - %(message)s',
    datefmt="%Y-%m-%d %H:%M:%S",
    level=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()
    sohu_ccef.crawl(delta)

if __name__ == '__main__':
    main()