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
|
# notitles.py - plugin to list pages without titles
#
# Copyright (C) 1998, 1999 Albert Hopkins (marduk)
# Copyright (C) 2002 Mike W. Meyer
# Copyright (C) 2005, 2006, 2011, 2013 Arthur de Jong
#
# 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 2 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, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
#
# The files produced as output from the software do not automatically fall
# under the copyright of the software, unless explicitly stated otherwise.
"""List pages without a title."""
__title__ = 'missing titles'
__author__ = 'Arthur de Jong'
__outputfile__ = 'notitles.html'
from sqlalchemy.sql.functions import char_length
from webcheck.db import Session, Link
from webcheck.output import render
def postprocess(crawler):
"""Add page problems for all pages without a title."""
session = Session()
# get all internal pages without a title
links = session.query(Link).filter_by(is_page=True, is_internal=True)
links = links.filter((char_length(Link.title) == 0) |
(Link.title == None))
for link in links:
link.add_pageproblem('missing title')
session.commit()
session.close()
def generate(crawler):
"""Output the list of pages without a title."""
session = Session()
links = session.query(Link).filter_by(is_page=True, is_internal=True)
links = links.filter((char_length(Link.title) == 0) |
(Link.title == None)).order_by(Link.url)
render(__outputfile__, crawler=crawler, title=__title__,
links=links)
session.close()
|