aboutsummaryrefslogtreecommitdiff
path: root/pyaggr3g470r/feedgetter.py
blob: 850f444936368aaafcfe2f0997157ebf5ad2c79e (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
#! /usr/bin/env python
#-*- coding: utf-8 -*-

# pyAggr3g470r - A Web based news aggregator.
# Copyright (C) 2010-2013  Cédric Bonhomme - http://cedricbonhomme.org/
#
# For more information : http://bitbucket.org/cedricbonhomme/pyaggr3g470r/
#
# 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, 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 General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>

__author__ = "Cedric Bonhomme"
__version__ = "$Revision: 1.9 $"
__date__ = "$Date: 2010/09/02 $"
__revision__ = "$Date: 2013/11/05 $"
__copyright__ = "Copyright (c) Cedric Bonhomme"
__license__ = "GPLv3"

import hashlib
import threading

import feedparser
from BeautifulSoup import BeautifulSoup
from datetime import datetime
from contextlib import contextmanager

import models
import conf
import search
import utils

from flask.ext.mail import Message
from pyaggr3g470r import app, mail

#import log
#pyaggr3g470r_log = log.Log()

list_of_threads = []

class FeedGetter(object):
    """
    This class is in charge of retrieving feeds listed in ./var/feed.lst.
    This class uses feedparser module from Mark Pilgrim.
    For each feed a new thread is launched.
    """
    def __init__(self, email):
        """
        Initializes the database connection.
        """
        #feedparser.USER_AGENT = conf.USER_AGENT
        feedparser.USER_AGENT = "pyAggr3g470r"
        self.user = models.User.objects(email=email).first()

    def retrieve_feed(self):
        """
        Parse the file 'feeds.lst' and launch a thread for each RSS feed.
        """
        for feed in self.user.feeds:
            try:
                # launch a new thread for the RSS feed
                thread = threading.Thread(None, self.process, \
                                           None, (feed, ))
                thread.start()
                list_of_threads.append(thread)
            except:
                pass

        # wait for all threads are done
        for th in list_of_threads:
            th.join()

    def process(self, feed):
        """
        Comment
        """
        #a_feed = feedparser.parse(feed_link, handlers = [self.proxy])
        a_feed = feedparser.parse(feed.link)
        if a_feed['entries'] == []:
            return

        articles = []
        for article in a_feed['entries']:

            if models.Article.objects(link=article.link).first() != None:
                # if article already in the database continue with the next article
                continue

            description = ""
            article_title = ""
            try:
                # article content
                description = article.content[0].value
            except AttributeError:
                try:
                    # article description
                    description = article.description
                except Exception:
                    description = ""
            try:
                description = BeautifulSoup(description, "html.parser").decode()
                article_title = BeautifulSoup(article.title, "html.parser").decode()
            except Exception as E:
                #pyaggr3g470r_log.error("Problem when sanitizing the content of the feed: " + feed.link)
                article_title = article.title

            try:
                post_date = datetime(*article.published_parsed[:6])
            except:
                post_date = datetime(*article.updated_parsed[:6])

            article = models.Article(post_date, article.link, article_title, description, False, False)
            article.save()
            articles.append(article)

            """
            # add the article to the Whoosh index
            try:
                search.add_to_index([article], feed)
            except:
                print("Whoosh error.")
                #pyaggr3g470r_log.error("Whoosh error.")
                continue"""

            if conf.MAIL_ENABLED and feed.email_notification:
                # if subscribed to the feed
                with app.app_context():
                    msg = Message('[pyAggr3g470r] ' + feed.title + ' : ' + article.title, \
                                sender = conf.MAIL_FROM, recipients = [conf.MAIL_TO])
                    msg.body = utils.clear_string(description)
                    msg.html = description
                    mail.send(msg)

        feed.articles.extend(articles)
        feed.articles = sorted(feed.articles, key=lambda t: t.date, reverse=True)
        #feed.save()
        self.user.save()


if __name__ == "__main__":
    # Point of entry in execution mode
    feed_getter = FeedGetter()
    # Retrieve all feeds
    feed_getter.retrieve_feed()
bgstack15