Skip to content

run compute_simhash and collapse_urls in the thread executor #3331

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

Open
liquidsec wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

run compute_simhash and collapse_urls in the thread executor #3331

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 bbot/modules/bevigil.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ async def handle_event(self, event):
if self.urls:
urls = await self.query(query, request_fn=self.request_urls, parse_fn=self.parse_urls)
if urls:
for parsed_url in await self.helpers.run_in_executor_mp(self.helpers.validators.collapse_urls, urls):
for parsed_url in await self.helpers.run_in_executor_cpu(self.helpers.validators.collapse_urls, urls):
await self.emit_event(
parsed_url.geturl(),
"URL_UNVERIFIED",
Expand Down
4 changes: 2 additions & 2 deletions bbot/modules/waf_bypass.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,7 +111,7 @@ async def handle_event(self, event):
return

# Store a "simhash" (fuzzy hash) of the response data for later comparison
simhash = await self.helpers.run_in_executor_mp(compute_simhash, response.text)
simhash = await self.helpers.run_in_executor_cpu(compute_simhash, response.text)

self.content_fingerprints[url] = {
"simhash": simhash,
Expand Down Expand Up @@ -157,7 +157,7 @@ async def check_ip(self, ip, source_domain, protected_domain, source_event):
self.debug(f"Failed to get content through IP {ip} for URL {matching_url}")
return None

bypass_simhash = await self.helpers.run_in_executor_mp(compute_simhash, bypass_response.text or "")
bypass_simhash = await self.helpers.run_in_executor_cpu(compute_simhash, bypass_response.text or "")

if original_response["http_code"] != bypass_response.status_code:
self.debug(f"Ignoring code difference {original_response['http_code']} != {bypass_response.status_code}")
Expand Down
Loading