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
|
# This file is part of GNU TALER.
# Copyright (C) 2014-2016 INRIA
#
# TALER is free software; you can redistribute it and/or modify it under the
# terms of the GNU Lesser General Public License as published by the Free Software
# Foundation; either version 2.1, or (at your option) any later version.
#
# TALER 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 Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public License along with
# GNU TALER; see the file COPYING. If not, see <http://www.gnu.org/licenses/>
#
# @author Florian Dold
"""
Define content and associated metadata that is served on the blog.
"""
from collections import OrderedDict, namedtuple
import logging
import os
import re
from bs4 import BeautifulSoup
from pkg_resources import resource_stream, resource_filename
LOGGER = logging.getLogger(__name__)
NOISY_LOGGER = logging.getLogger("chardet.charsetprober")
NOISY_LOGGER.setLevel(logging.INFO)
Article = namedtuple("Article", "slug title teaser main_file extra_files")
ARTICLES = OrderedDict()
def add_article(slug, title, teaser, main_file, extra_files):
ARTICLES[slug] = Article(slug, title, teaser, main_file, extra_files)
def get_image_file(image):
filex = resource_filename("talerblog", os.path.join("blog/data/", image))
return os.path.abspath(filex)
def get_article_file(article):
filex = resource_filename("talerblog", article.main_file)
return os.path.basename(filex)
def add_from_html(resource_name, teaser_paragraph=0, title=None):
"""
Extract information from article html.
"""
res = resource_stream("talerblog", resource_name)
soup = BeautifulSoup(res, 'html.parser')
res.close()
if title is None:
title_el = soup.find("h1", attrs={"class":["chapter", "unnumbered"]})
if title_el is None:
LOGGER.warning("Can't extract title from '%s'", resource_name)
title = resource_name
else:
title = title_el.get_text().strip()
slug = title.replace(" ", "_")
paragraphs = soup.find_all("p")
teaser = soup.find("p", attrs={"id":["teaser"]})
if teaser is None:
teaser = str(paragraphs[teaser_paragraph])
else:
teaser = teaser.get_text()
re_proc = re.compile("^/essay/[^/]+/data/[^/]+$")
imgs = soup.find_all("img")
extra_files = []
for img in imgs:
# We require that any image whose access is regulated is src'd
# as "<slug>/data/img.png". We also need to check if the <slug>
# component actually matches the article's slug
if re_proc.match(img['src']):
if img['src'].split(os.sep)[2] == slug:
LOGGER.info("extra file for %s is %s" % (slug, os.path.basename(img['src'])))
extra_files.append(os.path.basename(img['src']))
else:
LOGGER.warning("Image src and slug don't match: '%s' != '%s'" \
% (img['src'].split(os.sep)[2], slug))
add_article(slug, title, teaser, resource_name, extra_files)
add_from_html("blog/articles/scrap1_U.0.html", 0)
add_from_html("blog/articles/scrap1_U.1.html", 0)
add_from_html("blog/articles/scrap1_1.html", 1)
add_from_html("blog/articles/scrap1_2.html")
add_from_html("blog/articles/scrap1_3.html")
add_from_html("blog/articles/scrap1_4.html")
add_from_html("blog/articles/scrap1_5.html")
add_from_html("blog/articles/scrap1_6.html")
add_from_html("blog/articles/scrap1_7.html")
add_from_html("blog/articles/scrap1_8.html")
add_from_html("blog/articles/scrap1_9.html")
add_from_html("blog/articles/scrap1_10.html")
add_from_html("blog/articles/scrap1_11.html")
add_from_html("blog/articles/scrap1_12.html")
add_from_html("blog/articles/scrap1_13.html", 1)
add_from_html("blog/articles/scrap1_14.html")
add_from_html("blog/articles/scrap1_15.html")
add_from_html("blog/articles/scrap1_16.html")
add_from_html("blog/articles/scrap1_17.html")
add_from_html("blog/articles/scrap1_18.html")
add_from_html("blog/articles/scrap1_19.html")
add_from_html("blog/articles/scrap1_20.html", 1)
add_from_html("blog/articles/scrap1_21.html")
add_from_html("blog/articles/scrap1_22.html")
add_from_html("blog/articles/scrap1_23.html")
add_from_html("blog/articles/scrap1_24.html")
add_from_html("blog/articles/scrap1_25.html", 1)
add_from_html("blog/articles/scrap1_26.html", 1)
add_from_html("blog/articles/scrap1_27.html")
add_from_html("blog/articles/scrap1_28.html", 1)
add_from_html("blog/articles/scrap1_29.html")
add_from_html("blog/articles/scrap1_30.html", 1)
add_from_html("blog/articles/scrap1_31.html", 1)
add_from_html("blog/articles/scrap1_32.html")
add_from_html("blog/articles/scrap1_33.html")
add_from_html("blog/articles/scrap1_34.html")
add_from_html("blog/articles/scrap1_35.html")
add_from_html("blog/articles/scrap1_36.html")
add_from_html("blog/articles/scrap1_37.html")
add_from_html("blog/articles/scrap1_38.html")
add_from_html("blog/articles/scrap1_39.html")
add_from_html("blog/articles/scrap1_40.html")
add_from_html("blog/articles/scrap1_41.html")
add_from_html("blog/articles/scrap1_42.html")
add_from_html("blog/articles/scrap1_43.html", 2)
add_from_html("blog/articles/scrap1_46.html", 1)
add_from_html("blog/articles/scrap1_47.html")
|
