61 lines
1.8 KiB
Python
61 lines
1.8 KiB
Python
|
|
from scraping_engine import FingerprintScrapingEngine
|
|
from job_scraper2 import AmazonJobScraper # Updated class name
|
|
import os
|
|
from dotenv import load_dotenv
|
|
import asyncio
|
|
import random
|
|
import time
|
|
|
|
load_dotenv()
|
|
|
|
async def main():
|
|
engine = FingerprintScrapingEngine(
|
|
seed="amazon_job_scraping_12",
|
|
target_os="windows",
|
|
db_path="amazon_jobs.db",
|
|
markdown_path="amazon_jobs.md"
|
|
)
|
|
|
|
scraper = AmazonJobScraper(
|
|
engine,
|
|
human_speed=1.4,
|
|
user_request="Extract title, company, location, description, basic qualifications, preferred qualifications, job ID, and job type (full-time, part-time, etc.)"
|
|
)
|
|
|
|
job_titles = [
|
|
"Software Development Engineer",
|
|
"Data Scientist",
|
|
"Product Manager",
|
|
"UX Designer",
|
|
"Solutions Architect",
|
|
"Machine Learning Engineer",
|
|
"Frontend Engineer",
|
|
"Backend Engineer",
|
|
"Full Stack Engineer",
|
|
"Data Engineer"
|
|
]
|
|
|
|
fixed_location = "United States" # Amazon uses country/region, not city
|
|
|
|
while True:
|
|
random.shuffle(job_titles)
|
|
for job_title in job_titles:
|
|
search_keywords = f"{job_title} location:{fixed_location}"
|
|
print(f"\n{'='*60}")
|
|
print(f"Starting Amazon scrape for: {search_keywords}")
|
|
print(f"{'='*60}")
|
|
|
|
await scraper.scrape_jobs(
|
|
search_keywords=search_keywords,
|
|
max_pages=3 # Amazon loads 10 per page; 3 pages = ~30 jobs
|
|
)
|
|
|
|
print(f"\n✅ Completed scraping for: {job_title}")
|
|
print(f"⏳ Waiting 90 seconds before next job title...")
|
|
time.sleep(90)
|
|
|
|
print(f"\n✅ Completed full cycle. Restarting...")
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main()) |