aboutsummaryrefslogtreecommitdiff
path: root/pyaggr3g470r/lib/article_utils.py
diff options
context:
space:
mode:
authorCédric Bonhomme <cedric@cedricbonhomme.org>2015-07-06 15:26:29 +0200
committerCédric Bonhomme <cedric@cedricbonhomme.org>2015-07-06 15:26:29 +0200
commita867c1243c80843f3736ee260b92d5b13ec510ec (patch)
tree18f4d724abb04d9a14ad7dd5c0b1aca8eb98b3ca /pyaggr3g470r/lib/article_utils.py
parentMerged in jaesivsm/pyaggr3g470r (pull request #16) (diff)
downloadnewspipe-a867c1243c80843f3736ee260b92d5b13ec510ec.tar.gz
newspipe-a867c1243c80843f3736ee260b92d5b13ec510ec.tar.bz2
newspipe-a867c1243c80843f3736ee260b92d5b13ec510ec.zip
Minor fixes from a quick review. Need to test deeper.
Diffstat (limited to 'pyaggr3g470r/lib/article_utils.py')
-rw-r--r--pyaggr3g470r/lib/article_utils.py26
1 files changed, 3 insertions, 23 deletions
diff --git a/pyaggr3g470r/lib/article_utils.py b/pyaggr3g470r/lib/article_utils.py
index 023be9a7..3c642167 100644
--- a/pyaggr3g470r/lib/article_utils.py
+++ b/pyaggr3g470r/lib/article_utils.py
@@ -52,25 +52,6 @@ def construct_article(entry, feed):
elif entry.get('summary'):
content = entry['summary']
- description = entry.get('description', '')
- try:
- description = entry.content[0].value
- except Exception:
- pass
-
- try:
- soup = BeautifulSoup(description, "lxml")
- # Prevents BeautifulSoup4 from adding extra <html><body> tags
- # to the soup with the lxml parser.
- if soup.html.body:
- description = soup.html.body.decode_contents()
- elif soup.html:
- description = soup.html.decode_contents()
- else:
- description = soup.decode()
- except Exception:
- pass
-
article_link = entry.get('link')
if conf.RESOLVE_ARTICLE_URL and article_link:
try:
@@ -82,13 +63,12 @@ def construct_article(entry, feed):
logger.warning("Unable to get the real URL of %s. Error: %s",
article_link, error)
- return {'feed_id': feed['id'],
- 'user_id': feed['user_id'],
+ return {'feed_id': feed.id,
+ 'user_id': feed.user_id,
'entry_id': extract_id(entry).get('entry_id', None),
- 'link': entry.get('link', feed['site_link']),
+ 'link': entry.get('link', feed.site_link),
'title': entry.get('title', 'No title'),
'readed': False, 'like': False,
- 'description': description,
'content': content,
'retrieved_date': now.isoformat(),
'date': (date or now).isoformat()}
bgstack15