File size: 2,325 Bytes
13bc594 4006c52 13bc594 71da872 13bc594 71da872 13bc594 71da872 13bc594 4006c52 311da71 13bc594 71da872 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
#
# Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from abc import ABC
import asyncio
from crawl4ai import AsyncWebCrawler
from agent.component.base import ComponentBase, ComponentParamBase
from api.utils.web_utils import is_valid_url
class CrawlerParam(ComponentParamBase):
"""
Define the Crawler component parameters.
"""
def __init__(self):
super().__init__()
self.proxy = None
self.extract_type = "markdown"
def check(self):
self.check_valid_value(self.extract_type, "Type of content from the crawler", ['html', 'markdown', 'content'])
class Crawler(ComponentBase, ABC):
component_name = "Crawler"
def _run(self, history, **kwargs):
ans = self.get_input()
ans = " - ".join(ans["content"]) if "content" in ans else ""
if not is_valid_url(ans):
return Crawler.be_output("URL not valid")
try:
result = asyncio.run(self.get_web(ans))
return Crawler.be_output(result)
except Exception as e:
return Crawler.be_output(f"An unexpected error occurred: {str(e)}")
async def get_web(self, url):
proxy = self._param.proxy if self._param.proxy else None
async with AsyncWebCrawler(verbose=True, proxy=proxy) as crawler:
result = await crawler.arun(
url=url,
bypass_cache=True
)
if self._param.extract_type == 'html':
return result.cleaned_html
elif self._param.extract_type == 'markdown':
return result.markdown
elif self._param.extract_type == 'content':
result.extracted_content
return result.markdown
|