Add tool to manage RSS/Atom feeds

- weboob.tools.newsfeed a class representing a feed
 - the DLFP backend has been updated to use weboob.tools.newsfeed
This commit is contained in:
Clément Schreiner 2010-10-13 22:39:14 +02:00
commit a5470b9ce6
3 changed files with 57 additions and 62 deletions

View file

@ -18,10 +18,11 @@
from __future__ import with_statement
from weboob.tools.backend import BaseBackend
from weboob.tools.newsfeed import NewsFeed
from weboob.capabilities.messages import ICapMessages, ICapMessagesPost, Message, Thread, CantSendMessage
from .feeds import ArticlesList
from .browser import DLFP
from .tools import id2url, url2id
__all__ = ['DLFPBackend']
@ -41,6 +42,9 @@ class DLFPBackend(BaseBackend, ICapMessages, ICapMessagesPost):
}
STORAGE = {'seen': {}}
BROWSER = DLFP
RSS_TELEGRAMS= "https://linuxfr.org/backend/journaux/rss20.rss"
RSS_NEWSPAPERS = "https://linuxfr.org/backend/news/rss20.rss"
def create_default_browser(self):
return self.create_browser(self.config['username'], self.config['password'])
@ -48,12 +52,13 @@ class DLFPBackend(BaseBackend, ICapMessages, ICapMessagesPost):
def iter_threads(self):
whats = set()
if self.config['get_news']:
whats.add('newspaper')
whats.add(self.RSS_NEWSPAPERS)
if self.config['get_telegrams']:
whats.add('telegram')
whats.add(self.RSS_TELEGRAMS)
for what in whats:
for article in ArticlesList(what).iter_articles():
for article in NewsFeed(what, url2id).iter_entries():
thread = Thread(article.id)
thread.title = article.title
yield thread

View file

@ -1,58 +0,0 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2010 Romain Bignon
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, version 3 of the License.
#
# 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 General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
import feedparser
from datetime import datetime
from .tools import url2id
class Article:
RSS = None
def __init__(self, _id, url, title, author, datetime):
self.id = _id
self.url = url
self.title = title
self.author = author
self.datetime = datetime
class Newspaper(Article):
RSS = 'https://linuxfr.org/backend/news/rss20.rss'
class Telegram(Article):
RSS = 'https://linuxfr.org/backend/journaux/rss20.rss'
class ArticlesList:
RSS = {'newspaper': Newspaper,
'telegram': Telegram
}
def __init__(self, section=None):
self.section = section
self.articles = []
def iter_articles(self):
for section, klass in self.RSS.iteritems():
if self.section and self.section != section:
continue
url = klass.RSS
feed = feedparser.parse(url)
for item in feed['items']:
article = klass(url2id(item['link']), item['link'], item['title'], item['author'], datetime(*item['date_parsed'][:7]))
yield article

48
weboob/tools/newsfeed.py Normal file
View file

@ -0,0 +1,48 @@
import datetime
import feedparser
from weboob.backends.dlfp.tools import url2id
class Entry:
def __init__(self, entry, url2id=None):
if url2id:
self.id = url2id(entry.id)
else:
self.id = entry.id
if entry.has_key("link"):
self.link = entry["link"]
if entry.has_key("title"):
self.title = entry["title"]
else:
self.title = None
if entry.has_key("author"):
self.author = entry["author"]
else:
self.author = None
if entry.has_key("updated_parsed"):
#updated_parsed = entry["updated_parsed"]
self.datetime = datetime.datetime(*entry['updated_parsed'][:7])
else:
self.datetime = None
if entry.has_key("content"):
self.content = entry["content"][0]["value"]
else:
self.content = None
class NewsFeed:
def __init__(self, url, url2id=None):
self.feed = feedparser.parse(url)
self.url2id = url2id
def iter_entries(self):
for entry in self.feed['entries']:
yield Entry(entry, self.url2id)
def get_entry(self, id):
for entry in self.feed['entries']:
if entry.id == id:
return Entry(entry, self.url2id)