diff options
author | Cédric Bonhomme <cedric@cedricbonhomme.org> | 2015-02-22 09:54:29 +0100 |
---|---|---|
committer | Cédric Bonhomme <cedric@cedricbonhomme.org> | 2015-02-22 09:54:29 +0100 |
commit | eb73ac5952dc5e83229d58437b50feeeed215cfb (patch) | |
tree | 52498b4cc533a86c3f439b6a4f6f2e958a988d7f /pyaggr3g470r/crawler.py | |
parent | bug fix... (diff) | |
download | newspipe-eb73ac5952dc5e83229d58437b50feeeed215cfb.tar.gz newspipe-eb73ac5952dc5e83229d58437b50feeeed215cfb.tar.bz2 newspipe-eb73ac5952dc5e83229d58437b50feeeed215cfb.zip |
Indexation is now restored.
Diffstat (limited to 'pyaggr3g470r/crawler.py')
-rw-r--r-- | pyaggr3g470r/crawler.py | 27 |
1 files changed, 15 insertions, 12 deletions
diff --git a/pyaggr3g470r/crawler.py b/pyaggr3g470r/crawler.py index 85cdbdd0..e813c96e 100644 --- a/pyaggr3g470r/crawler.py +++ b/pyaggr3g470r/crawler.py @@ -33,6 +33,7 @@ import requests import feedparser import dateutil.parser from datetime import datetime +from itertools import chain from bs4 import BeautifulSoup from sqlalchemy import or_ @@ -40,6 +41,8 @@ from pyaggr3g470r import utils from pyaggr3g470r import conf from pyaggr3g470r import db from pyaggr3g470r.models import User, Article +if not conf.ON_HEROKU: + import pyaggr3g470r.search as fastsearch logger = logging.getLogger(__name__) @@ -205,8 +208,18 @@ def insert_database(user, feed): @asyncio.coroutine def init_process(user, feed): + # Fetch the feed and insert new articles in the database articles = yield from asyncio.async(insert_database(user, feed)) #print('inserted articles for {}'.format(feed.title)) + + # Indexation of the new articles for the feed + if not conf.ON_HEROKU and articles != []: + try: + #print('indexing articles for {}'.format(feed.title)) + fastsearch.add_to_index(user.id, articles, feed) + except: + logger.exception("Problem during indexation:") + return articles def retrieve_feed(user, feed_id=None): @@ -215,7 +228,7 @@ def retrieve_feed(user, feed_id=None): """ logger.info("Starting to retrieve feeds.") - # 1 - Get the list of feeds to fetch + # 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.enabled] if feed_id is not None: @@ -224,20 +237,10 @@ def retrieve_feed(user, feed_id=None): if feeds == []: return - # 2 - Fetch the feeds. + # Launch the process for all the feeds loop = asyncio.get_event_loop() tasks = [init_process(user, feed) for feed in feeds] #tasks = [asyncio.async(init_process(user, feed)) for feed in feeds] loop.run_until_complete(asyncio.wait(tasks)) - """ - # 3 - Indexation - if not conf.ON_HEROKU: - self.index(new_articles) - - # 4 - Mail notification - if not conf.ON_HEROKU and conf.NOTIFICATION_ENABLED: - self.mail_notification(new_articles) - """ - logger.info("All articles retrieved. End of the processus.") |