matitos/matitos_news
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Debug enlarge

Browse Source
This commit is contained in:
Luciano Gervasoni
2025-09-05 14:06:10 +02:00
parent e4a325d6b4
commit c17f09a94f
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
app_urls/fetcher/src/fetch_utils_url_processor.py
View File

@@ -71,6 +71,8 @@ def process_url(url, paywall_bypass=False):
config.request_timeout = 15 # timeout in seconds config.request_timeout = 15 # timeout in seconds
# Default mode # Default mode
article = newspaper.article(url_of_interest, config=config) article = newspaper.article(url_of_interest, config=config)
logger.debug("Processing raw URL 2: {}".format(url))
except newspaper.ArticleBinaryDataException: except newspaper.ArticleBinaryDataException:
logger.warning("ArticleException for input URL {}".format(url)) logger.warning("ArticleException for input URL {}".format(url))
return {"override_status": "invalid"} return {"override_status": "invalid"}
@@ -120,6 +122,8 @@ def process_url(url, paywall_bypass=False):
logger.warning("Exception for input URL {}\n{}".format(url, str(e))) logger.warning("Exception for input URL {}\n{}".format(url, str(e)))
return None return None
logger.debug("Processing raw URL 3: {}".format(url))
# Not a valid URL? # Not a valid URL?
if (not article.is_valid_url()): if (not article.is_valid_url()):
logger.debug("Invalid URL found: {}".format(url)) logger.debug("Invalid URL found: {}".format(url))