Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 11 additions & 14 deletions tests/integration/crawlers/_playwright/test_utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,9 @@ def track_requests(page: Page) -> tuple[set[str], set[str]]:

Chromium fails a request blocked by `Network.setBlockedURLs` with the `inspector` reason. Any other failure, such
as `net::ERR_NO_BUFFER_SPACE` on a loaded Windows runner, is a transport error and does not count as blocked.

The sets are complete once `page.goto` returns: it waits for the `load` event, which the browser fires only after
the page's script and image requests have finished or failed.
"""
requested: set[str] = set()
blocked: set[str] = set()
Expand Down Expand Up @@ -118,15 +121,13 @@ async def test_block_requests_default(server_url: URL) -> None:
page = await browser.new_page()
requested_no_block, blocked_no_block = track_requests(page)
await page.goto(target_url)
await page.wait_for_load_state('networkidle')
await page.close()

# With blocking
page = await browser.new_page()
requested_blocked, blocked_blocked = track_requests(page)
await block_requests(page)
await page.goto(target_url)
await page.wait_for_load_state('networkidle')
await page.close()

await browser.close()
Expand All @@ -148,18 +149,16 @@ async def test_block_requests_with_extra_patterns(server_url: URL) -> None:
target_url = str(server_url / 'resource_loading_page')

page = await browser.new_page()
loaded_urls_blocked = []

page.on('requestfinished', lambda req: loaded_urls_blocked.append(req.url.rsplit('/', 1)[-1]))
requested, blocked = track_requests(page)
await block_requests(page, extra_url_patterns=['*.js'])
await page.goto(target_url)
await page.wait_for_load_state('networkidle')
await page.close()

await browser.close()

# With blocking, only HTML should load
assert set(loaded_urls_blocked) == {'resource_loading_page'}
# The page requests both resources, and both the image and the script are blocked
assert requested == {'resource_loading_page', 'test.js', 'test.png'}
assert blocked == {'test.js', 'test.png'}


async def test_block_requests_with_custom_patterns(server_url: URL) -> None:
Expand All @@ -170,15 +169,13 @@ async def test_block_requests_with_custom_patterns(server_url: URL) -> None:
target_url = str(server_url / 'resource_loading_page')

page = await browser.new_page()
loaded_urls_blocked = []

page.on('requestfinished', lambda req: loaded_urls_blocked.append(req.url.rsplit('/', 1)[-1]))
requested, blocked = track_requests(page)
await block_requests(page, url_patterns=['*.js'])
await page.goto(target_url)
await page.wait_for_load_state('networkidle')
await page.close()

await browser.close()

# With blocking, only PNG should load
assert set(loaded_urls_blocked) == {'resource_loading_page', 'test.png'}
# The page requests both resources, and only the script is blocked
assert requested == {'resource_loading_page', 'test.js', 'test.png'}
assert blocked == {'test.js'}
Loading