diff options
| -rw-r--r-- | src/crawler/classic_crawler.py | 2 | ||||
| -rw-r--r-- | src/web/lib/article_utils.py | 6 |
2 files changed, 6 insertions, 2 deletions
diff --git a/src/crawler/classic_crawler.py b/src/crawler/classic_crawler.py index dc367440..2e292624 100644 --- a/src/crawler/classic_crawler.py +++ b/src/crawler/classic_crawler.py @@ -122,7 +122,7 @@ async def insert_database(user, feed): existing_article_req = art_contr.read(feed_id=feed.id, **extract_id(article)) except Exception as e: - print("existing_article_req: " + e) + print("existing_article_req: " + str(e)) continue exist = existing_article_req.count() != 0 diff --git a/src/web/lib/article_utils.py b/src/web/lib/article_utils.py index b5b9f246..71e83880 100644 --- a/src/web/lib/article_utils.py +++ b/src/web/lib/article_utils.py @@ -26,8 +26,12 @@ def extract_id(entry, keys=[('link', 'link'), ('published', 'date'), if entry_key in entry and pyagg_key not in ids: ids[pyagg_key] = entry[entry_key] if 'date' in pyagg_key: - ids[pyagg_key] = dateutil.parser.parse(ids[pyagg_key])\ + try: + ids[pyagg_key] = dateutil.parser.parse(ids[pyagg_key])\ .isoformat() + except ValueError as e: + print("extract_id: " + str(e)) + ids[pyagg_key] = datetime.now().isoformat() return ids |