voussoir/timesearch
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Log the size of received batches from pushshift.

Browse source
This commit is contained in:
Ethan Dalool 2020-09-06 21:41:44 -07:00
parent 83d5a8e70e
commit e136aeea4e
1 changed files with 2 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
timesearch_modules/pushshift.py
View file

@ -109,6 +109,7 @@ def _pagination_core(url, params, dummy_type, lower=None, upper=None):
setify = lambda items: set(item['id'] for item in items) setify = lambda items: set(item['id'] for item in items)
prev_batch_ids = set() prev_batch_ids = set()
while True: while True:
for retry in range(5): for retry in range(5):
try: try:
@ -120,6 +121,7 @@ def _pagination_core(url, params, dummy_type, lower=None, upper=None):
else: else:
break break
common.log.debug('Got batch of %d items.', len(batch))
batch_ids = setify(batch) batch_ids = setify(batch)
if len(batch_ids) == 0 or batch_ids.issubset(prev_batch_ids): if len(batch_ids) == 0 or batch_ids.issubset(prev_batch_ids):
break break