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
|
#! /usr/bin/env python
# -*- coding: utf-8 -
# newspipe - A Web based news aggregator.
# Copyright (C) 2010-2016 Cédric Bonhomme - https://www.cedricbonhomme.org
#
# For more information : https://github.com/Newspipe/Newspipe
#
# 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: 3.3 $"
__date__ = "$Date: 2010/09/02 $"
__revision__ = "$Date: 2015/12/07 $"
__copyright__ = "Copyright (c) Cedric Bonhomme"
__license__ = "AGPLv3"
import asyncio
import logging
import feedparser
import dateutil.parser
from datetime import datetime
from sqlalchemy import or_
import conf
from bootstrap import db
from web.models import User
from web.controllers import FeedController, ArticleController
from web.lib.feed_utils import construct_feed_from, is_parsing_ok
from web.lib.article_utils import construct_article, extract_id, \
get_article_content
logger = logging.getLogger(__name__)
sem = asyncio.Semaphore(5)
import ssl
try:
_create_unverified_https_context = ssl._create_unverified_context
except AttributeError:
# Legacy Python that doesn't verify HTTPS certificates by default
pass
else:
# Handle target environment that doesn't support HTTPS verification
ssl._create_default_https_context = _create_unverified_https_context
async def get(*args, **kwargs):
#kwargs["connector"] = aiohttp.TCPConnector(verify_ssl=False)
try:
data = feedparser.parse(args[0])
return data
except Exception as e:
raise e
async def parse_feed(user, feed):
"""
Fetch a feed.
Update the feed and return the articles.
"""
parsed_feed = None
up_feed = {}
articles = []
with (await sem):
try:
parsed_feed = await get(feed.link)
except Exception as e:
up_feed['last_error'] = str(e)
up_feed['error_count'] = feed.error_count + 1
logger.exception("error when parsing feed: " + str(e))
finally:
up_feed['last_retrieved'] = datetime.now(dateutil.tz.tzlocal())
if parsed_feed is None:
try:
FeedController().update({'id': feed.id}, up_feed)
except Exception as e:
logger.exception('something bad here: ' + str(e))
return
if not is_parsing_ok(parsed_feed):
up_feed['last_error'] = str(parsed_feed['bozo_exception'])
up_feed['error_count'] = feed.error_count + 1
FeedController().update({'id': feed.id}, up_feed)
return
if parsed_feed['entries'] != []:
articles = parsed_feed['entries']
up_feed['error_count'] = 0
up_feed['last_error'] = ""
# Feed informations
construct_feed_from(feed.link, parsed_feed).update(up_feed)
if feed.title and 'title' in up_feed:
# do not override the title set by the user
del up_feed['title']
FeedController().update({'id': feed.id}, up_feed)
return articles
async def insert_database(user, feed):
articles = await parse_feed(user, feed)
if None is articles:
return []
logger.info('Inserting articles for {}'.format(feed.title))
new_articles = []
art_contr = ArticleController(user.id)
for article in articles:
try:
existing_article_req = art_contr.read(feed_id=feed.id,
**extract_id(article))
except Exception as e:
logger.exception("existing_article_req: " + str(e))
continue
exist = existing_article_req.count() != 0
if exist:
# if the article has been already retrieved, we only update
# the content or the title
logger.debug('Article already in the database: '. \
format(article['title']))
existing_article = existing_article_req.first()
new_updated_date = None
try:
new_updated_date = dateutil.parser.parse(article['updated'])
except Exception as e:
new_updated_date = existing_article.date
logger.exception('new_updated_date failed: {}'.format(e))
if None is existing_article.updated_date:
existing_article.updated_date = new_updated_date.replace(tzinfo=None)
if existing_article.updated_date.strftime('%Y-%m-%dT%H:%M:%S') != \
new_updated_date.strftime('%Y-%m-%dT%H:%M:%S'):
logger.info('article updated')
existing_article.updated_date = \
new_updated_date.replace(tzinfo=None)
if existing_article.title != article['title']:
existing_article.title = article['title']
content = get_article_content(article)
if existing_article.content != content:
existing_article.content = content
existing_article.readed = False
art_contr.update({'entry_id': existing_article.entry_id},
existing_article.dump())
continue
# insertion of the new article
article = construct_article(article, feed)
try:
new_articles.append(art_contr.create(**article))
logger.info('New article added: {}'.format(article['link']))
except Exception:
logger.exception('Error when inserting article in database:')
continue
return new_articles
async def init_process(user, feed):
# Fetch the feed and insert new articles in the database
try:
articles = await insert_database(user, feed)
logger.debug('inserted articles for %s', feed.title)
return articles
except Exception as e:
logger.exception('init_process: ' + str(e))
def retrieve_feed(loop, user, feed_id=None):
"""
Launch the processus.
"""
logger.info('Starting to retrieve feeds for {}'.format(user.nickname))
# Get the list of feeds to fetch
filters = {}
filters['user_id'] = user.id
if feed_id is not None:
filters['id'] = feed_id
filters['enabled'] = True
filters['error_count__lt'] = conf.DEFAULT_MAX_ERROR
feeds = FeedController().read(**filters).all()
if feeds == []:
return
# Launch the process for all the feeds
tasks = [asyncio.ensure_future(init_process(user, feed)) for feed in feeds]
try:
loop.run_until_complete(asyncio.wait(tasks))
except Exception:
logger.exception('an error occured')
finally:
logger.info('Articles retrieved for {}'.format(user.nickname))
|
