diff options
| -rwxr-xr-x | source/feedgetter.py | 7 | ||||
| -rwxr-xr-x | source/pyAggr3g470r.py | 22 | ||||
| -rwxr-xr-x | source/utils.py | 6 |
3 files changed, 13 insertions, 22 deletions
diff --git a/source/feedgetter.py b/source/feedgetter.py index 14ef2edf..f713f672 100755 --- a/source/feedgetter.py +++ b/source/feedgetter.py @@ -26,11 +26,8 @@ __revision__ = "$Date: 2012/04/22 $" __copyright__ = "Copyright (c) Cedric Bonhomme" __license__ = "GPLv3" -import os.path -import traceback import threading import feedparser -import hashlib from BeautifulSoup import BeautifulSoup from datetime import datetime @@ -38,10 +35,8 @@ from datetime import datetime import utils import mongodb -feeds_list = [] list_of_threads = [] - class FeedGetter(object): """ This class is in charge of retrieving feeds listed in ./var/feed.lst. @@ -123,7 +118,7 @@ class FeedGetter(object): try: # article description description = article.description - except Exception, e: + except Exception: description = "" description = str(BeautifulSoup(description)) article_title = str(BeautifulSoup(article.title)) diff --git a/source/pyAggr3g470r.py b/source/pyAggr3g470r.py index 9a506ffd..4b363cdb 100755 --- a/source/pyAggr3g470r.py +++ b/source/pyAggr3g470r.py @@ -40,7 +40,6 @@ __license__ = "GPLv3" import os import re -import time import cherrypy import calendar @@ -355,7 +354,7 @@ class Root: html += """<h1>Articles containing the string <i>%s</i></h1><br />""" % (query,) if feed_id is not None: - for article in self.feeds[feed_id].articles.values(): + for article in self.mongo.get_articles_from_collection(feed_id): article_content = utils.clear_string(article.article_description) if not article_content: utils.clear_string(article.article_title) @@ -1017,7 +1016,6 @@ class Root: """ try: action, feed_id = param.split(':') - feed = self.feeds[feed_id] except: return self.error_page("Bad URL. This feed do not exists.") @@ -1205,8 +1203,8 @@ class Root: """ Delete all articles. """ - utils.drop_base() - return self.management() + self.mongo.drop_database() + return self.index() drop_base.exposed = True @@ -1217,7 +1215,7 @@ class Root: the appropriate function of the 'export' module. """ try: - getattr(export, export_method)(self.feeds) + getattr(export, export_method)(self.mongo.get_all_articles()) except Exception, e: return self.error_page(e) return self.management() @@ -1238,8 +1236,10 @@ class Root: except: return self.error_page("Bad URL.") try: - feed = self.feeds[feed_id] - article = feed.articles[article_id] + feed_id, article_id = param.split(':') + feed = self.mongo.get_collection(feed_id) + articles = self.mongo.get_articles_from_collection(feed_id) + article = self.mongo.get_article(feed_id, article_id) except: self.error_page("This article do not exists.") try: @@ -1249,9 +1249,9 @@ class Root: # directories already exists (not a problem) pass section = ez_epub.Section() - section.title = article.article_title.decode('utf-8') - section.paragraphs = [utils.clear_string(article.article_description).decode('utf-8')] - ez_epub.makeBook(article.article_title.decode('utf-8'), [feed.feed_title.decode('utf-8')], [section], \ + section.title = article["article_title"].decode('utf-8') + section.paragraphs = [utils.clear_string(article["article_description"]).decode('utf-8')] + ez_epub.makeBook(article["article_title"].decode('utf-8'), [feed["feed_title"].decode('utf-8')], [section], \ os.path.normpath(folder) + "article.epub", lang='en-US', cover=None) return self.article(param) diff --git a/source/utils.py b/source/utils.py index d6365073..0928160a 100755 --- a/source/utils.py +++ b/source/utils.py @@ -51,11 +51,7 @@ import BaseHTTPServer from BeautifulSoup import BeautifulSoup from datetime import datetime -from string import punctuation from collections import Counter -from collections import OrderedDict - -from StringIO import StringIO import os import ConfigParser @@ -116,7 +112,7 @@ def detect_url_errors(list_of_urls): urllib2.urlopen(req) except urllib2.HTTPError, e: # server couldn't fulfill the request - errors.append((url, e.code, \ + errors.append((url, e.code, \ BaseHTTPServer.BaseHTTPRequestHandler.responses[e.code][1])) except urllib2.URLError, e: # failed to reach the server |