aboutsummaryrefslogtreecommitdiff
path: root/pyaggr3g470r/crawler.py
blob: 2e07e844275fd3d420af2d889470a52f6144a61e (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
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
#! /usr/bin/env python
# -*- coding: utf-8 -

# pyAggr3g470r - A Web based news aggregator.
# Copyright (C) 2010-2014  Cédric Bonhomme - https://www.cedricbonhomme.org
#
# For more information : https://bitbucket.org/cedricbonhomme/pyaggr3g470r/
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero 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 Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

__author__ = "Cedric Bonhomme"
__version__ = "$Revision: 2.2 $"
__date__ = "$Date: 2010/09/02 $"
__revision__ = "$Date: 2014/07/13 $"
__copyright__ = "Copyright (c) Cedric Bonhomme"
__license__ = "AGPLv3"

import re
import socket
import logging
import feedparser
try:
    # Python 3
    from urllib.request import ProxyHandler
except:
    # Python 2
    from urllib2 import ProxyHandler
import requests
import dateutil.parser
from bs4 import BeautifulSoup
from datetime import datetime
from sqlalchemy.exc import IntegrityError
from requests.exceptions import *

import gevent.monkey
gevent.monkey.patch_all()
from gevent import Timeout
from gevent.pool import Pool

from pyaggr3g470r import utils
from pyaggr3g470r import conf
from pyaggr3g470r import notifications
from pyaggr3g470r import db
from pyaggr3g470r.models import User, Article
if not conf.ON_HEROKU:
    import pyaggr3g470r.search as fastsearch


logger = logging.getLogger(__name__)

socket.setdefaulttimeout(5.0)

class TooLong(Exception):
    def __init__(self):
        """
        Log a when greenlet took to long to fetch a resource.
        """
        logger.warning("Greenlet took to long")


class FeedGetter(object):
    """
    This class is in charge of retrieving the feeds.
    """
    def __init__(self, email):
        """
        Initialization.
        """
        feedparser.USER_AGENT = conf.USER_AGENT
        if conf.HTTP_PROXY == "":
            self.proxy = ProxyHandler({})
            self.proxies = {}
        else:
            self.proxy = ProxyHandler({"http": conf.HTTP_PROXY,
                                               "https": conf.HTTP_PROXY})
            self.proxies = {
                            "http": "http://" + conf.HTTP_PROXY,
                            "https": "http://" + conf.HTTP_PROXY
                           }
        feedparser.USER_AGENT = conf.USER_AGENT
        self.user = User.query.filter(User.email == email).first()

    def retrieve_feed(self, feed_id=None):
        """
        Launch the processus.
        """
        logger.info("Starting to retrieve feeds.")

        # 1 - Get the list of feeds to fetch
        user = User.query.filter(User.email == self.user.email).first()
        feeds = [feed for feed in user.feeds if feed.enabled]
        if feed_id is not None:
            feeds = [feed for feed in feeds if feed.id == feed_id]

        # 2 - Fetch the feeds.
        # 'responses' contains all the jobs returned by
        # the function retrieve_async()
        responses = self.retrieve_async(feeds)
        elements = [item.value for item in responses if item.value is not None]

        # 3 - Insert articles in the database
        new_articles = self.insert_database(elements)

        # 4 - Indexation
        if not conf.ON_HEROKU:
            self.index(new_articles)

        # 5 - Mail notification
        if not conf.ON_HEROKU and conf.NOTIFICATION_ENABLED:
            self.mail_notification(new_articles)

        logger.info("All articles retrieved. End of the processus.")

    def retrieve_async(self, feeds):
        """
        Spawn different jobs in order to retrieve a list of feeds.
        Returns a list of jobs.
        """
        def fetch(feed):
            """
            Fetch a feed.
            """
            logger.info("Fetching the feed: " + feed.title)
            a_feed = feedparser.parse(feed.link, handlers=[self.proxy])
            print(a_feed)
            if a_feed['bozo'] == 1:
                logger.error(a_feed['bozo_exception'])
            if a_feed['entries'] == []:
                return

            # Feed informations
            if feed.title == "":
                try:
                    feed.title = a_feed.feed.title
                except:
                    feed.title = "No title"
            if feed.link == "":
                try:
                    feed.link = a_feed.feed.link
                except:
                    feed.link = ""
            if feed.description == "":
                try:
                    feed.description = a_feed.feed.subtitle
                except:
                    feed.description = ""

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

                try:
                    nice_url = article.link.encode("utf-8")
                except:
                    # if not able to get the link of the article, continue
                    continue
                if conf.RESOLVE_ARTICLE_URL:
                    try:
                        # resolves URL behind proxies
                        # (like feedproxy.google.com)
                        r = requests.get(article.link, timeout=5.0,
                                            proxies=self.proxies)
                        nice_url = r.url.encode("utf-8")
                    except Timeout:
                        logger.warning(
                                "Timeout when getting the real URL of %s.",
                                article.link)
                        continue
                    except Exception as error:
                        logger.warning(
                                "Unable to get the real URL of %s. Error: %s",
                                article.link, error)
                        continue
                # remove utm_* parameters
                nice_url = utils.clean_url(nice_url)

                description = ""
                article_title = article.get('title', '')
                try:
                    # article content
                    description = article.content[0].value
                except AttributeError:
                    # article description
                    description = article.get('description', '')

                try:
                    description = BeautifulSoup(description, "lxml").decode()
                except:
                    logger.error("Problem when sanitizing the content of the article %s (%s)",
                                           article_title, nice_url)

                post_date = None
                for date_key in ('published_parsed', 'published',
                                 'updated_parsed', 'updated'):
                    if not date_key in article:
                        continue

                    try:
                        post_date = dateutil.parser.parse(article[date_key],
                                dayfirst=True)
                        break
                    except:
                        try:  # trying to clean date field from letters
                            post_date = dateutil.parser.parse(
                                        re.sub('[A-z]', '', article[date_key]),
                                        dayfirst=True)
                            break
                        except:
                            pass

                # create the models.Article object and append it to the list of articles
                article = Article(link=nice_url, title=article_title,
                                content=description, readed=False, like=False,
                                date=post_date, user_id=self.user.id,
                                feed_id=feed.id)
                articles.append(article)

            # return the feed with the list of retrieved articles
            return feed, articles

        pool = Pool(20)
        jobs = [pool.spawn(fetch, feed) for feed in feeds]
        pool.join()

        return jobs

    def insert_database(self, elements):
        """
        Insert articles in the database.
        """
        logger.info("Database insertion...")
        new_articles = []
        query1 = Article.query.filter(Article.user_id == self.user.id)
        for feed, articles in elements:
            query2 = query1.filter(Article.feed_id == feed.id)
            for article in articles:
                exist = query2.filter(Article.link == article.link).count() != 0
                if exist:
                    logger.debug("Article %r (%r) already in the database.",
                                 article.title, article.link)
                    continue
                if article.date is None:
                    article.date = datetime.now(dateutil.tz.tzlocal())

                new_articles.append(article)

                try:
                    feed.articles.append(article)
                    #db.session.merge(article)
                    db.session.commit()
                    logger.info("New article %r (%r) added.", article.title,
                                article.link)
                except Exception as e:
                    logger.error("Error when inserting article in database: " + str(e))
                    continue
        #db.session.close()
        return new_articles

    def index(self, new_articles):
        """
        Index new articles.
        """
        logger.info("Indexing new articles.")
        for element in new_articles:
            article = Article.query.filter(Article.user_id == self.user.id,
                                    Article.link == element.link).first()
            try:
                fastsearch.add_to_index(self.user.id, [article],
                                            article.source)
            except:
                logger.exception("Problem during indexation:")
        return True

    def mail_notification(self, new_articles):
        """
        Mail notification.
        """
        logger.info("Starting mail notification.")
        for element in new_articles:
            if element.source.email_notification:
                notifications.new_article_notification(self.user, element.source, element)
        return True
bgstack15