aboutsummaryrefslogtreecommitdiff
path: root/pyaggr3g470r/crawler.py
blob: 072a8f25225c24220179558b3b26f12e97c92e79 (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
#! /usr/bin/env python
# -*- coding: utf-8 -

# pyAggr3g470r - A Web based news aggregator.
# Copyright (C) 2010-2014  Cédric Bonhomme - http://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: 2.1 $"
__date__ = "$Date: 2010/09/02 $"
__revision__ = "$Date: 2014/04/13 $"
__copyright__ = "Copyright (c) Cedric Bonhomme"
__license__ = "AGPLv3"

import feedparser
import urllib2
import requests
from requests.exceptions import *
#from requests.packages.urllib3.exceptions import DecodeError
from urlparse import urlparse
from datetime import datetime

import gevent.monkey
#gevent.monkey.patch_socket()
gevent.monkey.patch_all()
from gevent import Timeout

from gevent.pool import Pool

"""
import logging
logging.basicConfig()
logging.getLogger().setLevel(logging.CRITICAL)
requests_log = logging.getLogger("requests.packages.urllib3")
requests_log.setLevel(logging.CRITICAL)
requests_log.propagate = True
"""


import models
import conf
if not conf.ON_HEROKU:
    import search
import utils

if not conf.ON_HEROKU:
    from flask.ext.mail import Message
    from pyaggr3g470r import mail
    
from pyaggr3g470r import app, db
from pyaggr3g470r.models import User, Feed, Article

import log
pyaggr3g470r_log = log.Log("feedgetter")


class TooLong(Exception):
    def __init__(self):
        """
        Log a when greenlet took to long to fetch a resource.
        """
        pyaggr3g470r_log.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 = urllib2.ProxyHandler({})
            self.proxies = {}
        else:
            self.proxy = urllib2.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.
        """
        pyaggr3g470r_log.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 != 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)

        # 3 - Insert articles in the database
        self.insert_database([item.value for item in responses if item.value is not None])
        
        pyaggr3g470r_log.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.
            """
            pyaggr3g470r_log.info("Fetching the feed:" + feed.title)
            a_feed = feedparser.parse(feed.link, handlers = [self.proxy])
            if a_feed['entries'] == []:
                return

            # Feed informations
            if feed.title == "":
                try:
                    feed.title = a_feed.feed.title
                except:
                    feed.title = ""
            if feed.description == "":
                try:
                    feed.description = a_feed.feed.subtitle
                except:
                    feed.description = ""

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

                nice_url = article.link.encode("utf-8")
                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:
                        pyaggr3g470r_log.warning("Timeout when getting the real URL of %s." % (article.link,))
                        continue
                    except Exception as e:
                        pyaggr3g470r_log.warning("Unable to get the real URL of %s. Error: %s" % (article.link, str(e)))
                        continue
                # remove utm_* parameters
                nice_url = utils.clean_url(nice_url)

                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 article %s (%s)" % (article_title, nice_url))
                    article_title = article.title

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

                # 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

        jobs = []
        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.
        """
        pyaggr3g470r_log.info("Database insertion...")
        for feed, articles in elements:

            for article in articles:

                exist = Article.query.filter(Article.user_id == self.user.id, Article.feed_id == feed.id, Article.link == article.link).first()
                if exist != None:
                    pyaggr3g470r_log.error("Article %s (%s) already in the database." % (article.title, article.link))
                    continue

                try:
                    feed.articles.append(article)
                    #db.session.merge(article)
                    db.session.commit()
                    pyaggr3g470r_log.info("New article %s (%s) added." % (article.title, article.link))
                except IntegrityError:
                    pyaggr3g470r_log.error("Article %s (%s) already in the database." % (article.title, article.link))
                    db.session.rollback()
                    continue
                except Exception as e:
                    pyaggr3g470r_log.error("Error when inserting article in database: " + str(e))
                    continue
        db.session.close()
        return True
        
bgstack15