增加对producthunt网站的数据爬取

This commit is contained in:
2025-11-17 07:39:45 +08:00
parent 256850f752
commit d07017cf11
27 changed files with 26638 additions and 2153 deletions

42
run_stealth_example.py Normal file
View File

@@ -0,0 +1,42 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
playwright_stealth 使用示例
演示如何使用 stealth 模式运行 ProductHunt 爬虫
"""
import asyncio
from loguru import logger
from product.new_data_stealth import ProductHuntScraper
async def run_stealth_scraper():
"""运行 stealth 版本的爬虫"""
logger.info("开始运行 stealth 版本的 ProductHunt 爬虫")
# 创建爬虫实例
scraper = ProductHuntScraper()
# 执行爬取
success = await scraper.scrape()
if success:
logger.success("Stealth 爬虫执行成功!")
logger.info("生成的文件:")
logger.info("- product_info_stealth.json: 产品信息数据")
logger.info("- product_page_stealth.html: 页面HTML内容")
logger.info("- product_screenshot_stealth.png: 页面截图")
else:
logger.error("Stealth 爬虫执行失败")
return success
def main():
"""主函数"""
logger.info("=== playwright_stealth 使用示例 ===")
logger.info("此示例演示如何使用 playwright_stealth 模块增强浏览器反检测能力")
# 运行异步任务
asyncio.run(run_stealth_scraper())
if __name__ == "__main__":
main()