mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-03 22:32:12 +08:00
2363b21447
* fix: some lint fix using tools Signed-off-by: yihong0618 <zouzou0208@gmail.com> * fix: md lint Signed-off-by: yihong0618 <zouzou0208@gmail.com> * fix: some lint fix using tools Signed-off-by: yihong0618 <zouzou0208@gmail.com> * fix: address comments Signed-off-by: yihong0618 <zouzou0208@gmail.com> * fix: tests Signed-off-by: yihong0618 <zouzou0208@gmail.com> --------- Signed-off-by: yihong0618 <zouzou0208@gmail.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
30 lines
957 B
Python
30 lines
957 B
Python
# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
from src.crawler import Crawler
|
|
|
|
|
|
def test_crawler_initialization():
|
|
"""Test that crawler can be properly initialized."""
|
|
crawler = Crawler()
|
|
assert isinstance(crawler, Crawler)
|
|
|
|
|
|
def test_crawler_crawl_valid_url():
|
|
"""Test crawling with a valid URL."""
|
|
crawler = Crawler()
|
|
test_url = "https://finance.sina.com.cn/stock/relnews/us/2024-08-15/doc-incitsya6536375.shtml"
|
|
result = crawler.crawl(test_url)
|
|
assert result is not None
|
|
assert hasattr(result, "to_markdown")
|
|
|
|
|
|
def test_crawler_markdown_output():
|
|
"""Test that crawler output can be converted to markdown."""
|
|
crawler = Crawler()
|
|
test_url = "https://finance.sina.com.cn/stock/relnews/us/2024-08-15/doc-incitsya6536375.shtml"
|
|
result = crawler.crawl(test_url)
|
|
markdown = result.to_markdown()
|
|
assert isinstance(markdown, str)
|
|
assert len(markdown) > 0
|