构建每日亚马逊价格监控器

[
  "https://www.amazon.com/dp/B0D1XD1ZV3",
  "https://www.amazon.com/dp/B0863TXGM3",
  "https://www.amazon.com/dp/B09V3KXJPB"
]

import json
import os
import sys

import requests

DATASET_ID = "gd_l7q7dkf244hwjntr0"  # Amazon products by URL
TRIGGER_URL = "https://api.brightdata.com/datasets/v3/trigger"


def main() -> int:
    api_key = os.environ.get("BRIGHT_DATA_API_KEY")
    if not api_key:
        print("BRIGHT_DATA_API_KEY environment variable is not set.")
        return 1

    with open("skus.json") as f:
        urls = json.load(f)

    payload = [{"url": url} for url in urls]

    response = requests.post(
        TRIGGER_URL,
        params={"dataset_id": DATASET_ID, "format": "json"},
        headers={
            "Authorization": f"Bearer {api_key}",
            "Content-Type": "application/json",
        },
        json=payload,
        timeout=30,
    )
    response.raise_for_status()

    snapshot_id = response.json().get("snapshot_id")
    print(f"Triggered scrape for {len(urls)} SKUs. Snapshot: {snapshot_id}")
    return 0


if __name__ == "__main__":
    sys.exit(main())

name: Daily Amazon price scrape

on:
  schedule:
    - cron: "0 6 * * *"   # 06:00 UTC every day
  workflow_dispatch:        # Allows manual runs from the Actions tab

jobs:
  trigger:
    runs-on: ubuntu-latest
    steps:
      - name: Check out the repo
        uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"

      - name: Install dependencies
        run: pip install -r requirements.txt

      - name: Trigger Bright Data scrape
        env:
          BRIGHT_DATA_API_KEY: ${{ secrets.BRIGHT_DATA_API_KEY }}
        run: python trigger_scrape.py