Git-Mirrors/brozzler
1
0
Fork 0
mirror of https://github.com/internetarchive/brozzler.git synced 2025-04-20 23:56:34 -04:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

feat: add _get_page_headers timeout

Browse Source
This commit is contained in:
Adam Miller 2025-02-04 16:35:11 -08:00
commit 298e5efe33
1 changed files with 10 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
brozzler/worker.py
View File

@ -52,6 +52,7 @@ class BrozzlerWorker:
# cluster with slow rethinkdb.
HEARTBEAT_INTERVAL = 200.0
SITE_SESSION_MINUTES = 15
HEADER_REQUEST_TIMEOUT = 30
def __init__(
self,
@ -340,13 +341,18 @@ class BrozzlerWorker:
def _get_page_headers(self, page):
# bypassing warcprox, requests' stream=True defers downloading the body of the response
# see https://docs.python-requests.org/en/latest/user/advanced/#body-content-workflow
page_headers = {}
try:
with requests.get(page.url, stream=True, verify=False) as r:
page_headers = r.headers
with requests.get(
page.url, stream=True, verify=False, timeout=HEADER_REQUEST_TIMEOUT
) as r:
return r.headers
except requests.exceptions.Timeout as e:
self.logger.warning(
"Timed out trying to get headers for %s: %s", page.url, e
)
except requests.exceptions.RequestException as e:
self.logger.warning("Failed to get headers for %s: %s", page.url, e)
return page_headers
return {}
def _needs_browsing(self, page_headers) -> bool:
return not bool(