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>
110 lines
3.5 KiB
Python
110 lines
3.5 KiB
Python
"""Tests for metadata extraction from Zhihu API responses"""
|
|
|
|
import pytest
|
|
|
|
from kb_workflow.crawler.models import AuthorInfo, ContentMetadata
|
|
|
|
|
|
class TestAuthorExtraction:
|
|
"""Tests for author information extraction."""
|
|
|
|
def test_parse_author_with_full_data(self):
|
|
"""Test parsing author with all fields present."""
|
|
from kb_workflow.crawler.zhihu_crawler import ZhihuCrawler
|
|
|
|
crawler = ZhihuCrawler(headless=True, timeout=10)
|
|
author_data = {
|
|
"name": "Test User",
|
|
"url_token": "test-user-123",
|
|
"headline": "Test headline"
|
|
}
|
|
|
|
result = crawler._parse_author(author_data)
|
|
|
|
assert isinstance(result, AuthorInfo)
|
|
assert result.name == "Test User"
|
|
assert result.url_token == "test-user-123"
|
|
assert result.headline == "Test headline"
|
|
|
|
def test_parse_author_with_minimal_data(self):
|
|
"""Test parsing author with only required fields."""
|
|
from kb_workflow.crawler.zhihu_crawler import ZhihuCrawler
|
|
|
|
crawler = ZhihuCrawler(headless=True, timeout=10)
|
|
author_data = {"name": "Minimal User"}
|
|
|
|
result = crawler._parse_author(author_data)
|
|
|
|
assert result.name == "Minimal User"
|
|
assert result.url_token is None
|
|
assert result.headline is None
|
|
|
|
def test_parse_author_with_empty_data(self):
|
|
"""Test parsing author with empty/None data."""
|
|
from kb_workflow.crawler.zhihu_crawler import ZhihuCrawler
|
|
|
|
crawler = ZhihuCrawler(headless=True, timeout=10)
|
|
|
|
result = crawler._parse_author(None)
|
|
assert result is None
|
|
|
|
result = crawler._parse_author({})
|
|
assert result.name == ""
|
|
|
|
|
|
class TestMetadataExtraction:
|
|
"""Tests for content metadata extraction."""
|
|
|
|
def test_parse_metadata_with_full_data(self):
|
|
"""Test parsing metadata with all fields present."""
|
|
from kb_workflow.crawler.zhihu_crawler import ZhihuCrawler
|
|
|
|
crawler = ZhihuCrawler(headless=True, timeout=10)
|
|
data = {
|
|
"author": {"name": "Test Author"},
|
|
"voteup_count": 100,
|
|
"comment_count": 20,
|
|
"created_time": 1700000000,
|
|
"updated_time": 1700100000
|
|
}
|
|
|
|
result = crawler._parse_metadata(data)
|
|
|
|
assert isinstance(result, ContentMetadata)
|
|
assert result.voteup_count == 100
|
|
assert result.comment_count == 20
|
|
assert result.created_time == 1700000000
|
|
assert result.updated_time == 1700100000
|
|
assert result.author is not None
|
|
assert result.author.name == "Test Author"
|
|
|
|
def test_parse_metadata_with_defaults(self):
|
|
"""Test parsing metadata with missing optional fields."""
|
|
from kb_workflow.crawler.zhihu_crawler import ZhihuCrawler
|
|
|
|
crawler = ZhihuCrawler(headless=True, timeout=10)
|
|
data = {}
|
|
|
|
result = crawler._parse_metadata(data)
|
|
|
|
assert result.voteup_count == 0
|
|
assert result.comment_count == 0
|
|
assert result.created_time is None
|
|
assert result.updated_time is None
|
|
assert result.author is None
|
|
|
|
def test_parse_metadata_with_zero_values(self):
|
|
"""Test parsing metadata when counts are zero."""
|
|
from kb_workflow.crawler.zhihu_crawler import ZhihuCrawler
|
|
|
|
crawler = ZhihuCrawler(headless=True, timeout=10)
|
|
data = {
|
|
"voteup_count": 0,
|
|
"comment_count": 0
|
|
}
|
|
|
|
result = crawler._parse_metadata(data)
|
|
|
|
assert result.voteup_count == 0
|
|
assert result.comment_count == 0
|