Skip to content

fix: restore proxy functionality for PlaywrightCrawler broken in v0.5 #889

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jan 15, 2025
Merged

fix: restore proxy functionality for PlaywrightCrawler broken in v0.5 #889

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a0e286a
fix work with proxy for PlaywrightBrowserController
Mantisus Jan 9, 2025
a4c0301
add test
Mantisus Jan 9, 2025
bdb53c9
add comments in test
Mantisus Jan 10, 2025
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
2 changes: 1 addition & 1 deletion src/crawlee/browsers/_playwright_browser_controller.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,7 +171,7 @@ async def _create_browser_context(
)

if proxy_info:
if browser_new_context_options['proxy']:
if browser_new_context_options.get('proxy'):
logger.warning("browser_new_context_options['proxy'] overriden by explicit `proxy_info` argument.")

browser_new_context_options['proxy'] = ProxySettings(
Expand Down
24 changes: 23 additions & 1 deletion tests/unit/crawlers/_playwright/test_playwright_crawler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,11 +18,12 @@
PW_CHROMIUM_HEADLESS_DEFAULT_USER_AGENT,
PW_FIREFOX_HEADLESS_DEFAULT_USER_AGENT,
)
from crawlee.proxy_configuration import ProxyConfiguration

if TYPE_CHECKING:
from yarl import URL

from crawlee.crawlers import PlaywrightCrawlingContext
from crawlee.crawlers import PlaywrightCrawlingContext, PlaywrightPreNavCrawlingContext


async def test_basic_request(httpbin: URL) -> None:
Expand Down Expand Up @@ -188,3 +189,24 @@ async def request_handler(_context: PlaywrightCrawlingContext) -> None:
await crawler.run(['https://example.com', str(httpbin)])

assert mock_hook.call_count == 2


async def test_proxy_set() -> None:
proxy_value = 'http://1111:1111'
mock_handler = mock.AsyncMock(return_value=None)
crawler = PlaywrightCrawler(proxy_configuration=ProxyConfiguration(proxy_urls=[proxy_value]))

handler_data = {}

crawler.router.default_handler(mock_handler)

@crawler.pre_navigation_hook
async def some_hook(context: PlaywrightPreNavCrawlingContext) -> None:
if context.proxy_info:
handler_data['proxy'] = context.proxy_info.url

await context.page.route('**/*', lambda route: route.fulfill(status=200, body=''))

await crawler.run(['https://test.com'])

assert handler_data.get('proxy') == proxy_value
Loading