Skip to content

GitHub Read Timeout Handling #80

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
LRWeber merged 1 commit into from
Mar 20, 2025
Merged

GitHub Read Timeout Handling #80

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
48 changes: 29 additions & 19 deletions scraper/github/queryManager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -262,20 +262,33 @@ def queryGitHub(
_vPrint(
(verbosity >= 0), "Sending %s query..." % ("REST" if rest else "GraphQL")
)
response = self._submitQuery(
gitquery,
gitvars=gitvars,
verbose=(verbosity > 0),
rest=rest,
headers=headers,
)
try:
response = self._submitQuery(
gitquery,
gitvars=gitvars,
verbose=(verbosity > 0),
rest=rest,
headers=headers,
)
except requests.exceptions.ReadTimeout: # Handles intermittent response delays
_vPrint((verbosity >= 0), "Read timed out.")
_vPrint((verbosity >= 0), "Repeating query...")
return self.queryGitHub(
gitquery,
gitvars=gitvars,
verbosity=verbosity,
paginate=paginate,
cursorVar=cursorVar,
keysToList=keysToList,
rest=rest,
requestCount=requestCount,
pageNum=(pageNum - 1), # retry same page
headers=headers,
)
_vPrint((verbosity >= 0), "Checking response...")
_vPrint((verbosity >= 0), "HTTP STATUS %s" % (response["statusTxt"]))
statusNum = response["statusNum"]

# Decrement page count before error checks to properly reflect any repeated queries
pageNum -= 1

# Make sure the query limit didn't run out
try:
apiStatus = {
Expand All @@ -297,7 +310,7 @@ def queryGitHub(
keysToList=keysToList,
rest=rest,
requestCount=(requestCount - 1), # not counted against retries
pageNum=pageNum,
pageNum=(pageNum - 1), # retry same page
headers=headers,
)
except KeyError: # Handles error responses without X-RateLimit data
Expand Down Expand Up @@ -339,8 +352,8 @@ def queryGitHub(
cursorVar=cursorVar,
keysToList=keysToList,
rest=rest,
requestCount=(requestCount),
pageNum=pageNum,
requestCount=requestCount,
pageNum=(pageNum - 1), # retry same page
headers=headers,
)
# Check for accepted but not yet processed, usually due to un-cached data
Expand Down Expand Up @@ -369,7 +382,7 @@ def queryGitHub(
keysToList=keysToList,
rest=rest,
requestCount=requestCount,
pageNum=pageNum,
pageNum=(pageNum - 1), # retry same page
headers=headers,
)
# Check for server error responses
Expand Down Expand Up @@ -398,7 +411,7 @@ def queryGitHub(
keysToList=keysToList,
rest=rest,
requestCount=requestCount,
pageNum=pageNum,
pageNum=(pageNum - 1), # retry same page
headers=headers,
)
# Check for other error responses
Expand Down Expand Up @@ -443,17 +456,14 @@ def queryGitHub(
keysToList=keysToList,
rest=rest,
requestCount=requestCount,
pageNum=pageNum,
pageNum=(pageNum - 1), # retry same page
headers=headers,
)

raise RuntimeError(
"GraphQL API error.\n%s" % (json.dumps(outObj["errors"]))
)

# Re-increment page count before the next page query
pageNum += 1

# Pagination
if paginate:
if rest and response["linkDict"]:
Expand Down
Loading