Finished first version of newsfeed backend.
- Several feeds tested with QBoobMsg and apparently working correctly. - NewsfeedBackend.set_message_read() untested, but should be working. - weboob.tools.newsfeed provides content even when not provided as such by the feed, using the "summary" instead.
This commit is contained in:
parent
a47b19a8b5
commit
11ad4ac948
5 changed files with 89 additions and 73 deletions
|
|
@ -18,7 +18,7 @@
|
|||
from __future__ import with_statement
|
||||
|
||||
from weboob.tools.backend import BaseBackend
|
||||
from weboob.tools.newsfeed import NewsFeed
|
||||
from weboob.tools.newsfeed import Newsfeed
|
||||
from weboob.capabilities.messages import ICapMessages, ICapMessagesPost, Message, Thread, CantSendMessage
|
||||
|
||||
from .browser import DLFP
|
||||
|
|
@ -58,7 +58,7 @@ class DLFPBackend(BaseBackend, ICapMessages, ICapMessagesPost):
|
|||
|
||||
|
||||
for what in whats:
|
||||
for article in NewsFeed(what, url2id).iter_entries():
|
||||
for article in Newsfeed(what, url2id).iter_entries():
|
||||
thread = Thread(article.id)
|
||||
thread.title = article.title
|
||||
yield thread
|
||||
|
|
|
|||
|
|
@ -16,6 +16,6 @@
|
|||
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||
|
||||
|
||||
from .backend import NewsFeedBackend
|
||||
from .backend import NewsfeedBackend
|
||||
|
||||
__all__ = ['NewsFeedBackend']
|
||||
__all__ = ['NewsfeedBackend']
|
||||
|
|
|
|||
|
|
@ -1,74 +1,41 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2010 Clément Schreiner
|
||||
#
|
||||
# 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.
|
||||
|
||||
|
||||
from weboob.tools.backend import BaseBackend
|
||||
from weboob.capabilities.messages import ICapMessages, Message, Thread
|
||||
import datetime
|
||||
import feedparser
|
||||
|
||||
|
||||
|
||||
class Article:
|
||||
def __init__(self, entry):
|
||||
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(updated_parsed.tm_year,
|
||||
updated_parsed.tm_mon,
|
||||
updated_parsed.tm_mday,
|
||||
updated_parsed.tm_hour,
|
||||
updated_parsed.tm_min,
|
||||
updated_parsed.tm_sec)
|
||||
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):
|
||||
self.feed = feedparser.parse(url)
|
||||
|
||||
|
||||
|
||||
|
||||
def iter_articles(self):
|
||||
for entry in self.feed['entries']:
|
||||
yield Article(entry)
|
||||
|
||||
def get_article(self, id):
|
||||
for entry in self.feed['entries']:
|
||||
if entry.id == id:
|
||||
return Article(entry)
|
||||
|
||||
from weboob.tools.newsfeed import Newsfeed
|
||||
|
||||
|
||||
|
||||
|
||||
class NewsFeedBackend(BaseBackend, ICapMessages):
|
||||
class NewsfeedBackend(BaseBackend, ICapMessages):
|
||||
NAME = 'newsfeed'
|
||||
MAINTAINER = "Clement Schreiner"
|
||||
MAINTAINER = u"Clément Schreiner"
|
||||
EMAIL = "clemux@clemux.info"
|
||||
VERSION = "0.1"
|
||||
DESCRIPTION = "News feeds"
|
||||
DESCRIPTION = "Loads RSS and Atom feeds from any websites"
|
||||
LICENSE = "GPLv3"
|
||||
CONFIG = {'url': BaseBackend.ConfigField(description='URL to the feed'),}
|
||||
STORAGE = {'seen': {}}
|
||||
CONFIG = {'url': BaseBackend.ConfigField(description="Atom/RSS feed's url"),}
|
||||
STORAGE = {'seen': []}
|
||||
|
||||
|
||||
|
||||
def iter_threads(self):
|
||||
for article in NewsFeed(self.config["url"]).iter_articles():
|
||||
for article in Newsfeed(self.config["url"]).iter_entries():
|
||||
thread = Thread(article.id)
|
||||
thread.title = article.title
|
||||
yield thread
|
||||
|
|
@ -81,19 +48,24 @@ class NewsFeedBackend(BaseBackend, ICapMessages):
|
|||
id = thread.id
|
||||
else:
|
||||
thread = Thread(id)
|
||||
article = NewsFeed(self.config["url"]).get_article(id)
|
||||
flags = 0
|
||||
if not thread.id in self.storage.get('seen', default={}):
|
||||
entry = Newsfeed(self.config["url"]).get_entry(id)
|
||||
flags = Message.IS_HTML
|
||||
if not thread.id in self.storage.get('seen', default=[]):
|
||||
flags |= Message.IS_UNREAD
|
||||
thread.title = article.title
|
||||
if len(entry.content):
|
||||
content = entry.content[0]
|
||||
else:
|
||||
content = None
|
||||
thread.title = entry.title
|
||||
thread.root = Message(thread=thread,
|
||||
id=0,
|
||||
title=article.title,
|
||||
sender=article.author,
|
||||
title=entry.title,
|
||||
sender=entry.author,
|
||||
receiver=None,
|
||||
date=article.datetime,
|
||||
date=entry.datetime,
|
||||
parent=None,
|
||||
content=article.content,
|
||||
content=content,
|
||||
children=[],
|
||||
flags=flags)
|
||||
return thread
|
||||
|
||||
|
|
@ -107,5 +79,5 @@ class NewsFeedBackend(BaseBackend, ICapMessages):
|
|||
|
||||
|
||||
def set_message_read(self, message):
|
||||
self.storage.set('seen', message.thread.id)
|
||||
self.storage.get('seen', default=[]).append(message.id)
|
||||
self.storage.save()
|
||||
|
|
|
|||
27
weboob/backends/newsfeed/test.py
Normal file
27
weboob/backends/newsfeed/test.py
Normal file
|
|
@ -0,0 +1,27 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2010 Clément Schreiner
|
||||
#
|
||||
# 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.
|
||||
|
||||
|
||||
from weboob.tools.test import BackendTest
|
||||
|
||||
class NewsfeedTest(BackendTest):
|
||||
BACKEND = 'newsfeed'
|
||||
|
||||
def test_newsfeed(self):
|
||||
for message in self.backend.iter_unread_messages():
|
||||
pass
|
||||
|
||||
|
|
@ -25,28 +25,45 @@ class Entry:
|
|||
self.id = url2id(entry.id)
|
||||
else:
|
||||
self.id = entry.id
|
||||
|
||||
if entry.has_key("link"):
|
||||
self.link = entry["link"]
|
||||
else:
|
||||
self.link = None
|
||||
|
||||
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("summary"):
|
||||
self.summary = entry["summary"]
|
||||
else:
|
||||
self.summary = None
|
||||
|
||||
self.content = []
|
||||
if entry.has_key("content"):
|
||||
self.content = entry["content"][0]["value"]
|
||||
for i in entry["content"]:
|
||||
self.content.append(i.value)
|
||||
elif self.summary:
|
||||
self.content.append(self.summary)
|
||||
else:
|
||||
self.content = None
|
||||
|
||||
|
||||
|
||||
|
||||
class NewsFeed:
|
||||
class Newsfeed:
|
||||
def __init__(self, url, url2id=None):
|
||||
self.feed = feedparser.parse(url)
|
||||
self.url2id = url2id
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue