aboutsummaryrefslogtreecommitdiff
path: root/feedgetter.py
blob: cc4fb5ca9eb42b9f6270d0768954eafbfbb75218 (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
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
#! /usr/bin/env python
#-*- coding: utf-8 -*-

# pyAggr3g470r - A Web based news aggregator.
# Copyright (C) 2010  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: 1.0 $"
__date__ = "$Date: 2010/09/02 $"
__copyright__ = "Copyright (c) Cedric Bonhomme"
__license__ = "GPLv3"

import os.path
import traceback
import sqlite3
import threading
import feedparser
from BeautifulSoup import BeautifulSoup

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.
    This class uses feedparser module from Mark Pilgrim.
    For each feed a new thread is launched.
    """
    def __init__(self):
        """
        Initializes the base and variables.
        """
        # Create the base if not exists.
        utils.create_base()

        # MongoDB connections
        self.articles = mongodb.Articles()

        # mutex to protect the SQLite base
        self.locker = threading.Lock()

    def retrieve_feed(self):
        """
        Parse the file 'feeds.lst' and launch a thread for each RSS feed.
        """
        with open("./var/feed.lst") as f:
            for a_feed in f:
                # test if the URL is well formed
                for url_regexp in utils.url_finders:
                    if url_regexp.match(a_feed):
                        the_good_url = url_regexp.match(a_feed).group(0).replace("\n", "")
                        try:
                            # launch a new thread for the RSS feed
                            thread = threading.Thread(None, self.process, \
                                                None, (the_good_url,))
                            thread.start()
                            list_of_threads.append(thread)
                        except:
                            pass
                        break

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

    def process(self, the_good_url):
        """Request the URL

        Executed in a thread.
        SQLite objects created in a thread can only be used in that same thread !
        """
        # Protect this part of code.
        self.locker.acquire()

        self.conn = sqlite3.connect(utils.sqlite_base, isolation_level = None)
        self.c = self.conn.cursor()

        if utils.detect_url_errors([the_good_url]) == []:
            # if ressource is available add the articles in the base.
            self.add_into_sqlite(the_good_url)

            self.conn.commit()
        self.c.close()

        # Release this part of code.
        self.locker.release()

    def add_into_sqlite(self, feed_link):
        """
        Add the articles of the feed 'a_feed' in the SQLite base.
        """
        a_feed = feedparser.parse(feed_link)
        if a_feed['entries'] == []:
            return
        try:
            feed_image = a_feed.feed.image.href
        except:
            feed_image = "/img/feed-icon-28x28.png"

        collection_dic = {"collection_id": feed_link,\
                            "feed_image": feed_image, \
                            "feed_title": utils.clear_string(a_feed.feed.title.encode('utf-8')), \
                            "feed_link": feed_link, \
                            "site_title": a_feed.feed.link.encode('utf-8'), \
                            "mail": False \
                        }
            
        self.articles.add_collection(collection_dic)

        articles = []
        for article in a_feed['entries']:
            description = ""
            try:
                # article content
                description = article.content[0].value
            except AttributeError:
                try:
                    # article description
                    description = article.description
                except Exception, e:
                    description = ""
            description = str(BeautifulSoup(description))
            article_title = str(BeautifulSoup(article.title))

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


            article = {"article_id": article.link.encode('utf-8'), \
                    "article_date": post_date, \
                    "article_link": article.link.encode('utf-8'), \
                    "article_title": article_title, \
                    "article_content": description, \
                    "article_readed": False, \
                    "article_like": False \
                    }
                
            articles.append(article)

        self.articles.add_articles(articles, feed_link)

        # send new articles by e-mail if desired.
        #threading.Thread(None, utils.send_mail, None, (utils.mail_from, utils.mail_to, \
                            #a_feed.feed.title.encode('utf-8'), \
                            #article_title, description) \
                        #).start()



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