starmen1265
912773fc65
- Add test_answer_crawler.py with tests for crawl_answer() - Add test_article_crawler.py with tests for crawl_article() - Add test_metadata_extraction.py with tests for author/metadata parsing Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
94 lines
3.6 KiB
Python
94 lines
3.6 KiB
Python
"""Tests for Zhihu Answer Crawler"""
|
|
|
|
import pytest
|
|
from unittest.mock import MagicMock, patch, PropertyMock
|
|
|
|
from kb_workflow.crawler.models import AnswerData, CrawlResult
|
|
|
|
|
|
class TestCrawlAnswer:
|
|
"""Tests for crawl_answer() method."""
|
|
|
|
def test_crawl_answer_returns_crawl_result(self, mock_browser, sample_answer_url):
|
|
"""Test that crawl_answer returns a CrawlResult object."""
|
|
from kb_workflow.crawler.zhihu_crawler import ZhihuCrawler
|
|
|
|
with patch.object(ZhihuCrawler, '_get_cookie', return_value='test_cookie'):
|
|
with patch('kb_workflow.crawler.zhihu_crawler.PlaywrightBrowser') as mock_pb:
|
|
mock_pb_instance = MagicMock()
|
|
mock_pb.return_value = mock_pb_instance
|
|
mock_pb_instance.page = MagicMock()
|
|
mock_pb_instance.page.route = MagicMock()
|
|
|
|
crawler = ZhihuCrawler(headless=True, timeout=10)
|
|
result = crawler.crawl_answer(sample_answer_url)
|
|
|
|
assert isinstance(result, CrawlResult)
|
|
|
|
def test_crawl_answer_invalid_url_returns_failure(self):
|
|
"""Test that invalid URL returns CrawlResult with success=False."""
|
|
from kb_workflow.crawler.zhihu_crawler import ZhihuCrawler
|
|
|
|
crawler = ZhihuCrawler(headless=True, timeout=10)
|
|
result = crawler.crawl_answer("https://www.example.com/invalid")
|
|
|
|
assert result.success is False
|
|
assert result.error is not None
|
|
assert "Invalid" in result.error
|
|
|
|
def test_crawl_answer_extracts_question_title(
|
|
self, sample_answer_url, sample_answer_api_response
|
|
):
|
|
"""Test that crawl_answer extracts question title from API response."""
|
|
from kb_workflow.crawler.zhihu_crawler import ZhihuCrawler, ZhihuApiInterceptor
|
|
|
|
# Create interceptor with captured data
|
|
interceptor = ZhihuApiInterceptor()
|
|
interceptor.captured_data["answer"] = sample_answer_api_response
|
|
|
|
crawler = ZhihuCrawler(headless=True, timeout=10)
|
|
|
|
# Test the parse method directly
|
|
result_data = crawler._parse_answer_data(
|
|
sample_answer_api_response,
|
|
answer_id=123456789,
|
|
question_id=987654321
|
|
)
|
|
|
|
assert result_data.question_title == "What is the best way to learn programming?"
|
|
|
|
|
|
class TestAnswerDataExtraction:
|
|
"""Tests for answer data extraction."""
|
|
|
|
def test_parse_answer_data_contains_content(self, sample_answer_api_response):
|
|
"""Test that parsed answer contains content."""
|
|
from kb_workflow.crawler.zhihu_crawler import ZhihuCrawler
|
|
|
|
crawler = ZhihuCrawler(headless=True, timeout=10)
|
|
result = crawler._parse_answer_data(
|
|
sample_answer_api_response,
|
|
answer_id=123456789,
|
|
question_id=987654321
|
|
)
|
|
|
|
assert isinstance(result, AnswerData)
|
|
assert result.content == "<p>This is a sample answer content in HTML format.</p>"
|
|
assert result.excerpt == "This is a sample answer content..."
|
|
|
|
def test_parse_answer_data_contains_metadata(self, sample_answer_api_response):
|
|
"""Test that parsed answer contains metadata."""
|
|
from kb_workflow.crawler.zhihu_crawler import ZhihuCrawler
|
|
|
|
crawler = ZhihuCrawler(headless=True, timeout=10)
|
|
result = crawler._parse_answer_data(
|
|
sample_answer_api_response,
|
|
answer_id=123456789,
|
|
question_id=987654321
|
|
)
|
|
|
|
assert result.metadata.voteup_count == 1000
|
|
assert result.metadata.comment_count == 50
|
|
assert result.metadata.author is not None
|
|
assert result.metadata.author.name == "John Doe"
|