crawl4ai官方docker镜像rest api复杂配置示例
·
import asyncio
import json
import time
import asyncio
payload = {
"urls": ["https://example.com"],
"browser_config": {
"type": "BrowserConfig",
"params": {
"headless": True,
"viewport": {
"type": "dict",
"value": {
"width": 1200,
"height": 800
}
}
}
},
"crawler_config": {
"type": "CrawlerRunConfig",
"params": {
"cache_mode": "bypass",
"markdown_generator": {
"type": "DefaultMarkdownGenerator",
"params": {
"options": {
"type": "dict",
"value": {
"ignore_links": True, # 不输出链接(Markdown里不会出现引用/URL)
"ignore_images": True, # 可选:图片引用也不要
"escape_html": False,
}
}
}
}
}
}
}
async def task1(session):
urls=["https://www.baidu.com"]
payload['urls']=urls
async with session.post("http://192.168.2.5:11235/crawl",
json=payload) as response:
data = await response.json()
return data
async def task2(session):
urls=["https://www.baidu.com"]
payload['urls']=urls
async with session.post("http://192.168.2.5:11235/crawl",
json=payload) as response:
data = await response.json()
return data
async def run_tests():
import aiohttp
print("Starting API Tests...")
async with aiohttp.ClientSession() as session:
print("\n=== Testing Crawl Endpoint ===")
results = await asyncio.gather(task1(session), task2(session))
print("\n所有请求完成!")
with open('output.json', 'w', encoding='utf-8') as f:
json.dump(results, f, ensure_ascii=False, indent=2)
start = time.time()
asyncio.run(run_tests())
print('耗时', time.time() - start)
更多推荐
所有评论(0)