aboutsummaryrefslogtreecommitdiff
path: root/source/utils.py
blob: a2f3dfb65148e063d0843701d44bb3ecc1d2b12a (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
#! /usr/bin/env python
#-*- coding: utf-8 -*-

# pyAggr3g470r - A Web based news aggregator.
# Copyright (C) 2010-2012  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: 1.3 $"
__date__ = "$Date: 2010/12/07 $"
__revision__ = "$Date: 2012/11/8 $"
__copyright__ = "Copyright (c) Cedric Bonhomme"
__license__ = "GPLv3"

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

import os
import re
import glob
import operator
import urllib.parse
import calendar
import unicodedata
import html.entities

import smtplib
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText

import urllib.request, urllib.error, urllib.parse
import http.server
from bs4 import BeautifulSoup

from datetime import datetime
from collections import Counter

import conf

# 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\\.]+"), \
]

def detect_url_errors(list_of_urls):
    """
    Detect URL errors.
    Return a list of error(s).
    """
    errors = []
    for url in list_of_urls:
        req = urllib.request.Request(url)
        try:
            urllib.request.urlopen(req)
        except urllib.error.HTTPError as e:
            # server couldn't fulfill the request
            errors.append((url, e.code, \
                http.server.BaseHTTPRequestHandler.responses[e.code][1]))
        except urllib.error.URLError as e:
            # failed to reach the server
            errors.append((url, e.reason.errno ,e.reason.strerror))
    return errors

def clear_string(data):
    """
    Clear a string by removing HTML tags, HTML special caracters
    and consecutive white spaces (more that one).
    """
    p = re.compile(b'<[^>]+>') # HTML tags
    q = re.compile(b'\s') # consecutive white spaces
    return p.sub(b'', q.sub(b' ', bytes(data, "utf-8"))).decode("utf-8", "strict")

def unescape(text):
    """
    Removes HTML or XML character references and entities from a text string.
    """
    def fixup(m):
        text = m.group(0)
        if text[:2] == "&#":
            # character reference
            try:
                if text[:3] == "&#x":
                    return chr(int(text[3:-1], 16))
                else:
                    return chr(int(text[2:-1]))
            except ValueError:
                pass
        else:
            # named entity
            try:
                text = chr(html.entities.name2codepoint[text[1:-1]])
            except KeyError:
                pass
        return text # leave as is
    return re.sub("&#?\w+;", fixup, text)

def not_combining(char):
    return unicodedata.category(char) != 'Mn'

def strip_accents(text, encoding):
    """
    Strip accents.

    >>> print strip_accents("déjà", "utf-8")
    deja
    """
    unicode_text= unicodedata.normalize('NFD', text.decode(encoding))
    return filter(not_combining, unicode_text).encode(encoding)

def normalize_filename(name):
    """
    Normalize a file name.
    """
    file_name = re.sub("[,'!?|&]", "", name)
    file_name = re.sub("[\s.]", "_", file_name)
    file_name = file_name.strip('_')
    file_name = file_name.strip('.')
    file_name = strip_accents(file_name, "utf-8")
    return os.path.normpath(file_name)

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

    for stop_wods_list in stop_words_lists:
        with open(stop_wods_list, "r") as stop_wods_file:
            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["article_content"])) if elem.lower() not in stop_words]:
            words[word] += 1
    return words.most_common(n)

def tag_cloud(tags, query="word_count"):
    """
    Generates a tags cloud.
    """
    tags.sort(key=operator.itemgetter(0))
    if query == "word_count":
        # tags cloud from the management page
        return ' '.join([('<font size=%d><a href="/search/?query=%s" title="Count: %s">%s</a></font>\n' % \
                    (min(1 + count * 7 / max([tag[1] for tag in tags]), 7), word, count, word)) \
                        for (word, count) in tags])
    if query == "year":
        # tags cloud for the history
        return ' '.join([('<font size=%d><a href="/history/?query=%s:%s" title="Count: %s">%s</a></font>\n' % \
                        (min(1 + count * 7 / max([tag[1] for tag in tags]), 7), query, word, count, word)) \
                            for (word, count) in tags])
    return ' '.join([('<font size=%d><a href="/history/?query=%s:%s" title="Count: %s">%s</a></font>\n' % \
                        (min(1 + count * 7 / max([tag[1] for tag in tags]), 7), query, word, count, calendar.month_name[int(word)])) \
                            for (word, count) in tags])

def send_mail(mfrom, mto, feed_title, article_title, description):
    """
    Send the article via mail.
    """
    # Create the body of the message (a plain-text and an HTML version).
    html = """<html>\n<head>\n<title>%s</title>\n</head>\n<body>\n%s\n</body>\n</html>""" % \
                (feed_title + ": " + article_title, description)
    text = clear_string(description)

    # Create message container - the correct MIME type is multipart/alternative.
    msg = MIMEMultipart('alternative')
    msg['Subject'] = '[pyAggr3g470r] ' + feed_title + ": " + article_title
    msg['From'] = mfrom
    msg['To'] = mto

    # Record the MIME types of both parts - text/plain and text/html.
    part1 = MIMEText(text, 'plain')
    part2 = MIMEText(html, 'html')

    # Attach parts into message container.
    # According to RFC 2046, the last part of a multipart message, in this case
    # the HTML message, is best and preferred.
    msg.attach(part1)
    msg.attach(part2)

    # Send the message via local SMTP server.
    s = smtplib.SMTP(conf.smtp_server)
    s.login(conf.username, conf.password)
    # sendmail function takes 3 arguments: sender's address, recipient's address
    # and message to send - here it is sent as one string.
    s.sendmail(mfrom, mto, msg.as_string())
    s.quit()

def string_to_datetime(stringtime):
    """
    Convert a string to datetime.
    """
    date, time = stringtime.split(' ')
    year, month, day = date.split('-')
    hour, minute, second = time.split(':')
    return datetime(year=int(year), month=int(month), day=int(day), \
        hour=int(hour), minute=int(minute), second=int(second))

def compare(stringtime1, stringtime2):
    """
    Compare two dates in the format 'yyyy-mm-dd hh:mm:ss'.
    """
    datetime1 = string_to_datetime(stringtime1)
    datetime2 = string_to_datetime(stringtime2)
    if datetime1 < datetime2:
        return -1
    elif datetime1 > datetime2:
        return 1
    return 0

def add_feed(feed_url):
    """
    Add the URL feed_url in the file feed.lst.
    """
    if os.path.exists("./var/feed.lst"):
        for line in open("./var/feed.lst", "r"):
            if feed_url in line:
                # if the feed is already in the file
                return False
    with open("./var/feed.lst", "a") as f:
        f.write(feed_url + "\n")
    return True

def change_feed_url(old_feed_url, new_feed_url):
    """
    Change the URL of a feed given in parameter.
    """
    # Replace the URL in the text file
    with open("./var/feed.lst", "r") as f:
        lines = f.readlines()
    lines = list(map(str.strip, lines))
    try:
        lines[lines.index(old_feed_url)] = new_feed_url
    except:
        return
    with open("./var/feed.lst", "w") as f:
        f.write("\n".join(lines))

def remove_feed(feed_url):
    """
    Remove a feed from the file feed.lst and from the SQLite base.
    """
    feeds = []
    # Remove the URL from the file feed.lst
    if os.path.exists("./var/feed.lst"):
        for line in open("./var/feed.lst", "r"):
            if feed_url not in line:
                feeds.append(line.replace("\n", ""))
        with open("./var/feed.lst", "w") as f:
            f.write("\n".join(feeds) + "\n")

def search_feed(url):
    """
    Search a feed in a HTML page.
    """
    soup = None
    try:
        page = urllib.request.urlopen(url)
        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
bgstack15