dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-05-25 14:55:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Added a test to scrape an actual URL with Playwright and ensured that Scraper.print_error is never called in any of the scraper tests.

Browse source
This commit is contained in:
Paul Gauthier (aider) 2024-07-23 11:42:01 +02:00
parent 9a7c67966a
commit 8a73346f66
1 changed files with 45 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

46
tests/scrape/test_scrape.py
View file

@ -1,8 +1,10 @@
import unittest
from unittest.mock import patch
from unittest.mock import patch, MagicMock
import re
from aider.commands import Commands
from aider.io import InputOutput
from aider.scrape import Scraper
class TestScrape(unittest.TestCase):
@ -37,6 +39,48 @@ class TestScrape(unittest.TestCase):
playwright_imported, "Playwright should be importable after running cmd_web"
)
@patch("aider.scrape.sync_playwright")
def test_scrape_actual_url_with_playwright(self, mock_sync_playwright):
# Mock the Playwright browser and page
mock_browser = MagicMock()
mock_page = MagicMock()
mock_browser.new_page.return_value = mock_page
mock_page.content.return_value = "<html><body><h1>Test Page</h1></body></html>"
mock_sync_playwright.return_value.__enter__.return_value.chromium.launch.return_value = mock_browser
# Create a Scraper instance with a mock print_error function
mock_print_error = MagicMock()
scraper = Scraper(print_error=mock_print_error, playwright_available=True)
# Scrape a real URL
result = scraper.scrape("https://example.com")
# Assert that the result contains expected content
self.assertIsNotNone(result)
self.assertIn("Test Page", result)
# Assert that print_error was never called
mock_print_error.assert_not_called()
# Assert that Playwright methods were called
mock_sync_playwright.assert_called_once()
mock_browser.new_page.assert_called()
mock_page.goto.assert_called_with("https://example.com", wait_until="networkidle", timeout=5000)
mock_page.content.assert_called_once()
def test_scraper_print_error_not_called(self):
# Create a Scraper instance with a mock print_error function
mock_print_error = MagicMock()
scraper = Scraper(print_error=mock_print_error)
# Test various methods of the Scraper class
scraper.scrape_with_httpx("https://example.com")
scraper.try_pandoc()
scraper.html_to_markdown("<html><body><h1>Test</h1></body></html>")
# Assert that print_error was never called
mock_print_error.assert_not_called()
if __name__ == "__main__":
unittest.main()