diff options
| -rw-r--r-- | src/crawler/default_crawler.py | 7 | ||||
| -rw-r--r-- | src/lib/feed_utils.py | 4 |
2 files changed, 8 insertions, 3 deletions
diff --git a/src/crawler/default_crawler.py b/src/crawler/default_crawler.py index 80cee92f..e5df3c04 100644 --- a/src/crawler/default_crawler.py +++ b/src/crawler/default_crawler.py @@ -101,7 +101,10 @@ async def parse_feed(user, feed): up_feed['last_error'] = "" # Feed information - construct_feed_from(feed.link, parsed_feed).update(up_feed) + try: + construct_feed_from(feed.link, parsed_feed).update(up_feed) + except: + logger.exception('error when constructing feed: {}'.format(feed.link)) if feed.title and 'title' in up_feed: # do not override the title set by the user del up_feed['title'] @@ -198,7 +201,7 @@ def retrieve_feed(loop, user, feed_id=None): try: loop.run_until_complete(asyncio.wait(tasks)) - except Exception: + except: logger.exception('an error occured') finally: logger.info('Articles retrieved for {}'.format(user.nickname)) diff --git a/src/lib/feed_utils.py b/src/lib/feed_utils.py index 4c2cee29..c2d4ca6e 100644 --- a/src/lib/feed_utils.py +++ b/src/lib/feed_utils.py @@ -73,7 +73,9 @@ def construct_feed_from(url=None, fp_parsed=None, feed=None, query_site=True): try: response = requests.get(feed['site_link'], **requests_kwargs) - except Exception: + except requests.exceptions.InvalidSchema as e: + return feed + except: logger.exception('failed to retrieve %r', feed['site_link']) return feed bs_parsed = BeautifulSoup(response.content, 'html.parser', |