aboutsummaryrefslogtreecommitdiff
path: root/src/web/controllers
diff options
context:
space:
mode:
authorCédric Bonhomme <cedric@cedricbonhomme.org>2016-11-08 14:39:47 +0100
committerCédric Bonhomme <cedric@cedricbonhomme.org>2016-11-08 14:39:47 +0100
commit2d72f44a90a76fe7450e59fdfdf4d42f44b9cd96 (patch)
tree39895c10f68cf0b13d957073268769d04aa924a0 /src/web/controllers
parentCloses section HTML tag. (diff)
downloadnewspipe-2d72f44a90a76fe7450e59fdfdf4d42f44b9cd96.tar.gz
newspipe-2d72f44a90a76fe7450e59fdfdf4d42f44b9cd96.tar.bz2
newspipe-2d72f44a90a76fe7450e59fdfdf4d42f44b9cd96.zip
various improvements to the crawler (better use of coroutines, test if an article should be updated). tags are now retrieved for the k-means clustering (previously achived with the content of articles)
Diffstat (limited to 'src/web/controllers')
-rw-r--r--src/web/controllers/abstract.py7
-rw-r--r--src/web/controllers/article.py29
2 files changed, 8 insertions, 28 deletions
diff --git a/src/web/controllers/abstract.py b/src/web/controllers/abstract.py
index 58532660..3c91e08a 100644
--- a/src/web/controllers/abstract.py
+++ b/src/web/controllers/abstract.py
@@ -91,11 +91,8 @@ class AbstractController:
obj = self._db_cls(**attrs)
db.session.add(obj)
- try:
- db.session.commit()
- except Exception as e:
- db.session.rollback()
- logger.exception(str(e))
+ db.session.flush()
+ db.session.commit()
return obj
def read(self, **filters):
diff --git a/src/web/controllers/article.py b/src/web/controllers/article.py
index 02c8fc75..4607b225 100644
--- a/src/web/controllers/article.py
+++ b/src/web/controllers/article.py
@@ -6,6 +6,7 @@ from collections import Counter
from bootstrap import db
from .abstract import AbstractController
+from web.lib.article_utils import process_filters
from web.controllers import CategoryController, FeedController
from web.models import Article
@@ -43,29 +44,11 @@ class ArticleController(AbstractController):
"no right on feed %r" % feed.id
attrs['user_id'], attrs['category_id'] = feed.user_id, feed.category_id
- # handling feed's filters
- for filter_ in feed.filters or []:
- match = False
- if filter_.get('type') == 'regex':
- match = re.match(filter_['pattern'], attrs.get('title', ''))
- elif filter_.get('type') == 'simple match':
- match = filter_['pattern'] in attrs.get('title', '')
- take_action = match and filter_.get('action on') == 'match' \
- or not match and filter_.get('action on') == 'no match'
-
- if not take_action:
- continue
-
- if filter_.get('action') == 'mark as read':
- attrs['readed'] = True
- logger.warn("article %s will be created as read",
- attrs['link'])
- elif filter_.get('action') == 'mark as favorite':
- attrs['like'] = True
- logger.warn("article %s will be created as liked",
- attrs['link'])
-
- return super().create(**attrs)
+ skipped, read, liked = process_filters(feed.filters, attrs)
+ if skipped:
+ return None
+ article = super().create(**attrs)
+ return article
def update(self, filters, attrs):
user_id = attrs.get('user_id', self.user_id)
bgstack15