alihan/news-please-content-crawler
1
0
Fork 0
mirror of https://github.com/fhamborg/news-please.git synced 2021-09-19 22:26:00 +03:00
Code Issues Projects Releases Wiki Activity

Merge pull request #200 from mood-mapping-muppets/allow-none-fully-extracted-log

Browse Source 
Check for when log_pathname_fully_extracted_warcs is None and don't log in this case
This commit is contained in:
Felix Hamborg
2021-02-07 14:59:59 +01:00
committed by GitHub
parent 09754829c7 584facb897
commit f3e478cde3
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
newsplease/crawler/commoncrawl_extractor.py
View File

@@ -89,8 +89,9 @@ class CommonCrawlExtractor:
:param warc_url:
:return:
"""
with open(self.__log_pathname_fully_extracted_warcs, 'a') as log_file:
log_file.write(warc_url + '\n')
if self.__log_pathname_fully_extracted_warcs is not None:
with open(self.__log_pathname_fully_extracted_warcs, 'a') as log_file:
log_file.write(warc_url + '\n')
def filter_record(self, warc_record, article=None):
"""