aboutsummaryrefslogtreecommitdiff
path: root/src/crawler/classic_crawler.py
diff options
context:
space:
mode:
authorFrançois Schmidts <francois.schmidts@gmail.com>2016-02-02 23:30:57 +0100
committerFrançois Schmidts <francois.schmidts@gmail.com>2016-02-02 23:30:57 +0100
commit4a8438d7f2b7b16941240b91f39a9402c431ffc2 (patch)
tree89380f41b802256d8fdbf724e7d9e63b48209b4a /src/crawler/classic_crawler.py
parentMerge branch 'feature/categories' (diff)
downloadnewspipe-4a8438d7f2b7b16941240b91f39a9402c431ffc2.tar.gz
newspipe-4a8438d7f2b7b16941240b91f39a9402c431ffc2.tar.bz2
newspipe-4a8438d7f2b7b16941240b91f39a9402c431ffc2.zip
writing a bit of doc, moving crawler together
Diffstat (limited to 'src/crawler/classic_crawler.py')
-rw-r--r--src/crawler/classic_crawler.py168
1 files changed, 168 insertions, 0 deletions
diff --git a/src/crawler/classic_crawler.py b/src/crawler/classic_crawler.py
new file mode 100644
index 00000000..0598c418
--- /dev/null
+++ b/src/crawler/classic_crawler.py
@@ -0,0 +1,168 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -
+
+# jarr - A Web based news aggregator.
+# Copyright (C) 2010-2015 Cédric Bonhomme - https://www.JARR-aggregator.org
+#
+# For more information : https://github.com/JARR-aggregator/JARR/
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as
+# published by the Free Software Foundation, either version 3 of the
+# License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+__author__ = "Cedric Bonhomme"
+__version__ = "$Revision: 3.3 $"
+__date__ = "$Date: 2010/09/02 $"
+__revision__ = "$Date: 2015/12/07 $"
+__copyright__ = "Copyright (c) Cedric Bonhomme"
+__license__ = "AGPLv3"
+
+import asyncio
+import logging
+import feedparser
+import dateutil.parser
+from datetime import datetime
+from sqlalchemy import or_
+
+import conf
+from bootstrap import db
+from web.models import User
+from web.controllers import FeedController, ArticleController
+from web.lib.feed_utils import construct_feed_from, is_parsing_ok
+from web.lib.article_utils import construct_article, extract_id
+
+logger = logging.getLogger(__name__)
+
+sem = asyncio.Semaphore(5)
+
+import ssl
+try:
+ _create_unverified_https_context = ssl._create_unverified_context
+except AttributeError:
+ # Legacy Python that doesn't verify HTTPS certificates by default
+ pass
+else:
+ # Handle target environment that doesn't support HTTPS verification
+ ssl._create_default_https_context = _create_unverified_https_context
+
+
+async def get(*args, **kwargs):
+ #kwargs["connector"] = aiohttp.TCPConnector(verify_ssl=False)
+ try:
+ data = feedparser.parse(args[0])
+ return data
+ except Exception as e:
+ raise e
+
+
+async def parse_feed(user, feed):
+ """
+ Fetch a feed.
+ Update the feed and return the articles.
+ """
+ parsed_feed = None
+ up_feed = {}
+ articles = []
+ with (await sem):
+ try:
+ parsed_feed = await get(feed.link)
+ except Exception as e:
+ up_feed['last_error'] = str(e)
+ up_feed['error_count'] = feed.error_count + 1
+ finally:
+ up_feed['last_retrieved'] = datetime.now(dateutil.tz.tzlocal())
+ if parsed_feed is None:
+ FeedController().update({'id': feed.id}, up_feed)
+ return
+
+ if not is_parsing_ok(parsed_feed):
+ up_feed['last_error'] = str(parsed_feed['bozo_exception'])
+ up_feed['error_count'] = feed.error_count + 1
+ FeedController().update({'id': feed.id}, up_feed)
+ return
+ if parsed_feed['entries'] != []:
+ articles = parsed_feed['entries']
+
+ up_feed['error_count'] = 0
+ up_feed['last_error'] = ""
+
+ # Feed informations
+ construct_feed_from(feed.link, parsed_feed).update(up_feed)
+ if feed.title and 'title' in up_feed:
+ # do not override the title set by the user
+ del up_feed['title']
+ FeedController().update({'id': feed.id}, up_feed)
+
+ return articles
+
+
+async def insert_database(user, feed):
+
+ articles = await parse_feed(user, feed)
+ if None is articles:
+ return []
+
+ logger.debug('inserting articles for {}'.format(feed.title))
+
+ logger.info("Database insertion...")
+ new_articles = []
+ art_contr = ArticleController(user.id)
+ for article in articles:
+ exist = art_contr.read(feed_id=feed.id,
+ **extract_id(article)).count() != 0
+ if exist:
+ logger.debug("Article %r (%r) already in the database.",
+ article['title'], article['link'])
+ continue
+ article = construct_article(article, feed)
+ try:
+ new_articles.append(art_contr.create(**article))
+ logger.info("New article % (%r) added.",
+ article['title'], article['link'])
+ except Exception:
+ logger.exception("Error when inserting article in database:")
+ continue
+ return new_articles
+
+
+async def init_process(user, feed):
+ # Fetch the feed and insert new articles in the database
+ articles = await insert_database(user, feed)
+ logger.debug('inserted articles for %s', feed.title)
+ return articles
+
+
+def retrieve_feed(loop, user, feed_id=None):
+ """
+ Launch the processus.
+ """
+ logger.info("Starting to retrieve feeds.")
+
+ # Get the list of feeds to fetch
+ user = User.query.filter(User.email == user.email).first()
+ feeds = [feed for feed in user.feeds if
+ feed.error_count <= conf.DEFAULT_MAX_ERROR and feed.enabled]
+ if feed_id is not None:
+ feeds = [feed for feed in feeds if feed.id == feed_id]
+
+ if feeds == []:
+ return
+
+ # Launch the process for all the feeds
+ tasks = [asyncio.ensure_future(init_process(user, feed)) for feed in feeds]
+
+ try:
+ loop.run_until_complete(asyncio.wait(tasks))
+ except Exception:
+ logger.exception('an error occured')
+
+ logger.info("All articles retrieved. End of the processus.")
bgstack15