aboutsummaryrefslogtreecommitdiff
path: root/pyaggr3g470r/utils.py
blob: 1a3f55ffe5b2342a41d96c4b872e91bc096dde75 (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
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
#! /usr/bin/env python
#-*- coding: utf-8 -*-

# pyAggr3g470r - A Web based news aggregator.
# Copyright (C) 2010-2015  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: 1.6 $"
__date__ = "$Date: 2010/12/07 $"
__revision__ = "$Date: 2013/11/17 $"
__copyright__ = "Copyright (c) Cedric Bonhomme"
__license__ = "AGPLv3"

#
# This file provides functions used for:
# - the database management;
# - generation of tags cloud;
# - HTML processing;
# - e-mail notifications.
#

import re
import glob
import opml
import json
import logging
import datetime
import operator
import urllib
import subprocess
try:
    from urlparse import urlparse, parse_qs, urlunparse
except:
    from urllib.parse import urlparse, parse_qs, urlunparse
from bs4 import BeautifulSoup
from collections import Counter
from contextlib import contextmanager

import conf
from pyaggr3g470r import db
from pyaggr3g470r.models import User, Feed, Article

# regular expression to check URL
url_finders = [
    re.compile("([0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}|(((news|telnet|nttp|file|http|ftp|https)://)|(www|ftp)[-A-Za-z0-9]*\\.)[-A-Za-z0-9\\.]+)(:[0-9]*)?/[-A-Za-z0-9_\\$\\.\\+\\!\\*\\(\\),;:@&=\\?/~\\#\\%]*[^]'\\.}>\\),\\\"]"), \
    re.compile("([0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}|(((news|telnet|nttp|file|http|ftp|https)://)|(www|ftp)[-A-Za-z0-9]*\\.)[-A-Za-z0-9\\.]+)(:[0-9]*)?"), \
    re.compile("(~/|/|\\./)([-A-Za-z0-9_\\$\\.\\+\\!\\*\\(\\),;:@&=\\?/~\\#\\%]|\\\\)+"), \
    re.compile("'\\<((mailto:)|)[-A-Za-z0-9\\.]+@[-A-Za-z0-9\\.]+") \
]

logger = logging.getLogger(__name__)


@contextmanager
def opened_w_error(filename, mode="r"):
    try:
        f = open(filename, mode)
    except IOError as err:
        yield None, err
    else:
        try:
            yield f, None
        finally:
            f.close()

def fetch(id, feed_id=None):
    cmd = [conf.PYTHON, conf.basedir+'/fetch.py', str(id), str(feed_id)]
    p = subprocess.Popen(cmd, stdout=subprocess.PIPE)

def import_opml(email, opml_content):
    """
    Import new feeds from an OPML file.
    """
    user = User.query.filter(User.email == email).first()
    try:
        subscriptions = opml.from_string(opml_content)
    except:
        logger.exception("Parsing OPML file failed:")
        raise

    def read(subsubscription, nb=0):
        """
        Parse recursively through the categories and sub-categories.
        """
        for subscription in subsubscription:

            if len(subscription) != 0:
                nb = read(subscription, nb)
            else:

                try:
                    title = subscription.text

                except:
                    title = ""

                try:
                    description = subscription.description
                except:
                    description = ""

                try:
                    link = subscription.xmlUrl
                except:
                    continue

                if None != Feed.query.filter(Feed.user_id == user.id, Feed.link == link).first():
                    continue

                try:
                    site_link = subscription.htmlUrl
                except:
                    site_link = ""

                new_feed = Feed(title=title, description=description,
                                link=link, site_link=site_link,
                                email_notification=False, enabled=True)

                user.feeds.append(new_feed)
                nb += 1
        return nb

    nb = read(subscriptions)
    db.session.commit()
    return nb

def import_json(email, json_content):
    """
    Import an account from a JSON file.
    """
    user = User.query.filter(User.email == email).first()
    json_account = json.loads(json_content)
    nb_feeds, nb_articles = 0, 0

    # Create feeds
    for feed in json_account["result"]:

        if None != Feed.query.filter(Feed.user_id == user.id, Feed.link == feed["link"]).first():
            continue

        new_feed = Feed(title=feed["title"], description="", link=feed["link"], \
                                    site_link=feed["site_link"], email_notification=feed["email_notification"], \
                                    created_date=datetime.datetime.fromtimestamp(int(feed["created_date"])),
                                    enabled=feed["enabled"])
        user.feeds.append(new_feed)
        nb_feeds += 1
    db.session.commit()

    # Create articles
    for feed in json_account["result"]:
        user_feed = Feed.query.filter(Feed.user_id == user.id, Feed.link == feed["link"]).first()
        if None != user_feed:
            for article in feed["articles"]:

                if None == Article.query.filter(Article.user_id == user.id,
                                        Article.feed_id == user_feed.id,
                                        Article.link == article["link"]).first():

                    new_article = Article(link=article["link"], title=article["title"], \
                                            content=article["content"], readed=article["readed"], like=article["like"], \
                                            retrieved_date=datetime.datetime.fromtimestamp(int(article["retrieved_date"])),
                                            date=datetime.datetime.fromtimestamp(int(article["date"])),
                                            user_id=user.id, feed_id=user_feed.id)

                    user_feed.articles.append(new_article)
                    nb_articles += 1
    db.session.commit()

    return nb_feeds, nb_articles


def clean_url(url):
    """
    Remove utm_* parameters
    """
    return url
    parsed_url = urlparse(url)
    qd = parse_qs(parsed_url.query, keep_blank_values=True)
    filtered = dict((k, v) for k, v in qd.items()
                                        if not k.startswith('utm_'))
    return urlunparse([
        parsed_url.scheme,
        parsed_url.netloc,
        urllib.quote(urllib.unquote(parsed_url.path)),
        parsed_url.params,
        urllib.urlencode(filtered, doseq=True),
        parsed_url.fragment
    ]).rstrip('=')


def open_url(url):
    """
    Open an URL with the proxy and the user-agent
    specified in the configuration file.
    """
    if conf.HTTP_PROXY == "":
        proxy = {}
    else:
        proxy = {"http" : conf.HTTP_PROXY}
    opener = urllib.request.FancyURLopener(proxy)
    try:
        opener = urllib.request.build_opener()
        opener.addheaders = [('User-agent', conf.USER_AGENT)]
        return (True, opener.open(url))
    except urllib.error.HTTPError as e:
        # server couldn't fulfill the request
        error = (url, e.code, \
                        http.server.BaseHTTPRequestHandler.responses[e.code][1])
        #pyaggr3g470r_log.error(url + " " + str(e.code) + " " + http.server.BaseHTTPRequestHandler.responses[e.code][1])
        return (False, error)
    except urllib.error.URLError as e:
        # failed to reach the server
        if type(e.reason) == str:
            error = (url, e.reason, e.reason)
            #pyaggr3g470r_log.error(url + " " + e.reason)
        else:
            error = (url, e.reason.errno, e.reason.strerror)
            #pyaggr3g470r_log.error(url + " " + str(e.reason.errno) + " " + e.reason.strerror)
        return (False, error)


def clear_string(data):
    """
    Clear a string by removing HTML tags, HTML special caracters
    and consecutive white spaces (more that one).
    """
    p = re.compile('<[^>]+>') # HTML tags
    q = re.compile('\s') # consecutive white spaces
    return p.sub('', q.sub(' ', data))


def load_stop_words():
    """
    Load the stop words and return them in a list.
    """
    stop_words_lists = glob.glob('./pyaggr3g470r/var/stop_words/*.txt')
    stop_words = []

    for stop_wods_list in stop_words_lists:
        with opened_w_error(stop_wods_list, "r") as (stop_wods_file, err):
            if err:
                stop_words = []
            else:
                stop_words += stop_wods_file.read().split(";")
    return stop_words


def top_words(articles, n=10, size=5):
    """
    Return the n most frequent words in a list.
    """
    stop_words = load_stop_words()
    words = Counter()
    wordre = re.compile(r'\b\w{%s,}\b' % size, re.I)
    for article in articles:
        for word in [elem.lower() for elem in
                wordre.findall(clear_string(article.content)) \
                if elem.lower() not in stop_words]:
            words[word] += 1
    return words.most_common(n)


def tag_cloud(tags):
    """
    Generates a tags cloud.
    """
    tags.sort(key=operator.itemgetter(0))
    return '\n'.join([('<font size=%d><a href="/search/?query=%s" title="Count: %s">%s</a></font>' % \
                    (min(1 + count * 7 / max([tag[1] for tag in tags]), 7), word, format(count, ',d'), word)) \
                        for (word, count) in tags])


def search_feed(url):
    """
    Search a feed in a HTML page.
    """
    soup, page = None, None
    try:
        result = open_url(url)
        if result[0] == True:
            page = open_url(url)[1]
        else:
            return None
        soup = BeautifulSoup(page)
    except:
        return None
    feed_links = soup('link', type='application/atom+xml')
    feed_links.extend(soup('link', type='application/rss+xml'))
    for feed_link in feed_links:
        #if url not in feed_link['href']:
            #return urllib.parse.urljoin(url, feed_link['href'])
        return feed_link['href']
    return None


if __name__ == "__main__":
    import_opml("root@pyAggr3g470r.localhost", "./var/feeds_test.opml")
    #import_opml("root@pyAggr3g470r.localhost", "./var/pyAggr3g470r.opml")
bgstack15