Skip to content
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

🚫 Prevent email popups from mailto: and tel: links #70

Open
wants to merge 10 commits into
base: main
Choose a base branch
from
Open

🚫 Prevent email popups from mailto: and tel: links #70

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
a7cf07b
🔥feat: Add page-level event handlers for dismissing dialogs and abort…
mohamedmamdouh22 Sep 19, 2024
c1464ac
feat: Add MailtoTelBlockerHandler to playwright harness🦍
mohamedmamdouh22 Sep 19, 2024
311c950
refactor
mohamedmamdouh22 Sep 19, 2024
7596e41
refactor: Improve page load performance by lazy loading images and pr…
mohamedmamdouh22 Sep 19, 2024
105fe28
refactor: Update email popup prevention logic in test_e2e.py
mohamedmamdouh22 Sep 20, 2024
fea48a3
Merge branch 'main' into APE-160
mohamedmamdouh22 Oct 23, 2024
4ccad85
Update version to 0.32.0 in pyproject.toml
mohamedmamdouh22 Oct 23, 2024
02b9d06
Merge branch 'main' into APE-160
mohamedmamdouh22 Oct 24, 2024
68bd381
Merge branch 'main' into APE-160
mohamedmamdouh22 Oct 27, 2024
50bd8e1
Merge branch 'main' into APE-160
mohamedmamdouh22 Oct 30, 2024
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
4 changes: 3 additions & 1 deletion harambe/contrib/playwright/harness.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
from playwright_stealth import stealth_async

from harambe.contrib.playwright.impl import PlaywrightPage
from harambe.handlers import UnnecessaryResourceHandler
from harambe.handlers import UnnecessaryResourceHandler, MailtoTelBlockerHandler
from harambe.proxy import proxy_from_url
from harambe.types import SetCookieParam, BrowserType, LocalStorage
from harambe.user_agent import random_user_agent, compute_user_agent, UserAgentFactory
Expand Down Expand Up @@ -112,9 +112,11 @@ async def playwright_harness(

if abort_unnecessary_requests:
await ctx.route("**/*", UnnecessaryResourceHandler().handle)
await ctx.route("**/*", MailtoTelBlockerHandler().handle)

async def page_factory(*_: Any, **__: Any) -> PlaywrightPage:
page = await ctx.new_page()
page.on("dialog", lambda dialog: dialog.dismiss())
if on_new_page:
await on_new_page(page)
if stealth:
Expand Down
11 changes: 10 additions & 1 deletion harambe/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -406,9 +406,18 @@ async def run(
)
if setup:
await setup(sdk)

if not harness_options.get("disable_go_to_url", False):
await page.goto(url)
if harness == playwright_harness:
await page.wait_for_load_state("domcontentloaded")
await page.evaluate("""
document.addEventListener('click', (event) => {
const target = event.target.closest('a[href^="mailto:"], a[href^="tel:"]');
if (target) {
event.preventDefault();
}
});
Comment on lines +411 to +419
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why do we need this if we have the route handler already?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

because the route handler will prevent the request from being sent, but it will not prevent the js code from being executed so the popup window will still appear, using this code, it will prevent the js code itself from opening a new window since its href starts with mailto or tel. @asim-shrestha

""")
elif isinstance(page, SoupPage):
page.url = url
await scraper(sdk, url, context)
Expand Down
10 changes: 10 additions & 0 deletions harambe/handlers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,3 +88,13 @@ async def handle(self, route: Route) -> None:
return

await route.fallback()


class MailtoTelBlockerHandler:
async def handle(self, route: Route) -> None:
request_url = route.request.url

if request_url.startswith(("mailto:", "tel:")):
await route.abort("blockedbyclient")
else:
await route.continue_()
23 changes: 23 additions & 0 deletions test/mock_html/emails.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Mock Page for Testing Mailto and Tel Blocking</title>
</head>
<body>
<h1>Test Mailto and Tel Links</h1>

<p>
<a href="mailto:[email protected]">Email Us</a>
</p>

<p>
<a href="tel:+1234567890">Call Us</a>
</p>

<p>
<a href="https://example.com">Go to Example</a>
</p>
</body>
</html>
32 changes: 32 additions & 0 deletions test/test_e2e.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -534,3 +534,35 @@ async def scraper(sdk: SDK, current_url: str, *args, **kwargs):

assert len(observer.data) == 1
assert observer.data[0]["local_storage"] == {}


@pytest.mark.parametrize("harness", [playwright_harness])
async def test_email_popup_prevention(server, observer, harness):
@SDK.scraper("test", "detail", observer=observer)
async def scraper(sdk: SDK, *args, **kwargs) -> None:
page = sdk.page
dialog_opened = False
page.on("dialog", lambda dialog: dialog.dismiss() and set_dialog_flag())

def set_dialog_flag():
nonlocal dialog_opened
dialog_opened = True

mailto_link = await page.query_selector('a[href^="mailto:"]')
await mailto_link.click()
current_url = page.url

assert not current_url.startswith(
"mailto:"
), "Popup prevention failed, mailto link triggered."
assert (
not dialog_opened
), "A dialog (popup) was opened, but it should have been prevented."

await SDK.run(
scraper=scraper,
url=f"{server}/emails",
schema={},
headless=True,
harness=harness,
)
Loading