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
|
#! /usr/bin/env python
#-*- coding: utf-8 -*-
# pyAggr3g470r - A Web based news aggregator.
# Copyright (C) 2010 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: 0.1 $"
__date__ = "$Date: 2011/10/24 $"
__copyright__ = "Copyright (c) Cedric Bonhomme"
__license__ = "GPLv3"
#
# This file contains the export functions of pyAggr3g470r. Indeed
# it is possible to export the database of articles in different formats:
# - simple HTML webzine;
# - text file;
# - ePub file;
# - PDF file.
#
import os
import hashlib
import conf
import utils
htmlheader = '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">\n' + \
'<head>' + \
'\n\t<title>pyAggr3g470r - News aggregator</title>\n' + \
'\t<link rel="stylesheet" type="text/css" href="/css/style.css" />' + \
'\n\t<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>\n' + \
'</head>\n'
htmlfooter = '<p>This software is under GPLv3 license. You are welcome to copy, modify or' + \
' redistribute the source code according to the' + \
' <a href="http://www.gnu.org/licenses/gpl-3.0.txt">GPLv3</a> license.</p></div>\n' + \
'</body>\n</html>'
def export_html(mongo_db):
"""
Export the articles given in parameter in a simple Webzine.
"""
feeds = mongo_db.get_all_feeds()
index = htmlheader
index += "<br />\n<ul>"
for feed in feeds:
# creates a folder for each stream
feed_folder = conf.path + "/var/export/webzine/" + \
utils.normalize_filename(feed["feed_id"])
try:
os.makedirs(feed_folder)
except OSError:
# directories already exists (not a problem)
pass
index += """<li><a href="%s">%s</a></a></li>\n""" % \
(feed["feed_id"], feed["feed_title"])
posts = htmlheader
for article in mongo_db.get_articles_from_collection(feed["feed_id"]):
post_file_name = os.path.normpath(feed_folder + "/" + article["article_id"] + ".html")
feed_index = os.path.normpath(feed_folder + "/index.html")
posts += article["article_date"].ctime() + " - " + \
"""<a href="./%s.html">%s</a>""" % \
(article["article_id"], article["article_title"][:150]) + "<br />\n"
a_post = htmlheader
a_post += '\n<div style="width: 50%; overflow:hidden; text-align: justify; margin:0 auto">\n'
a_post += """<h1><a href="%s">%s</a></h1><br />""" % \
(article["article_link"], article["article_title"])
a_post += article["article_content"]
a_post += "</div>\n<hr />\n"
a_post += """<br />\n<a href="%s">Complete story</a>\n<br />\n""" % (article["article_link"],)
a_post += "<hr />\n" + htmlfooter
with open(post_file_name, "w") as f:
f.write(a_post.encode('utf-8'))
posts += htmlfooter
with open(feed_index, "w") as f:
f.write(posts.encode('utf-8'))
index += "\n</ul>\n<br />"
index += htmlfooter
with open(conf.path + "/var/export/webzine/" + "index.html", "w") as f:
f.write(index.encode('utf-8'))
def export_txt(mongo_db):
"""
Export the articles given in parameter in text files.
"""
feeds = mongo_db.get_all_feeds()
for feed in feeds:
# creates folder for each stream
folder = conf.path + "/var/export/txt/" + \
utils.normalize_filename(feed["feed_title"].strip().replace(':', '').lower().encode('utf-8'))
try:
os.makedirs(folder)
except OSError:
# directories already exists (not a problem)
pass
for article in mongo_db.get_articles_from_collection(feed["feed_id"]):
name = article["article_date"].ctime().strip().replace(' ', '_')
name = os.path.normpath(folder + "/" + name + ".txt")
content = "Title: " + article["article_title"] + "\n\n\n"
content += utils.clear_string(article["article_content"])
with open(name, "w") as f:
f.write(content.encode('utf-8'))
def export_epub(feeds):
"""
Export the articles given in parameter in ePub files.
"""
from epub import ez_epub
for feed in feeds.values():
# creates folder for each stream
folder = utils.path + "/var/export/epub/" + \
utils.normalize_filename(feed.feed_title.strip().replace(':', '').lower())
try:
os.makedirs(folder)
except OSError:
# directories already exists (not a problem)
pass
for article in feed.articles.values():
name = article.article_date.strip().replace(' ', '_')
name = os.path.normpath(folder + "/" + name + ".epub")
section = ez_epub.Section()
section.title = article.article_title.decode('utf-8')
section.paragraphs = [utils.clear_string(article.article_description).decode('utf-8')]
ez_epub.makeBook(article.article_title.decode('utf-8'), [feed.feed_title.decode('utf-8')], [section], \
name, lang='en-US', cover=None)
def export_pdf(feeds):
"""
Export the articles given in parameter in PDF files.
"""
from xhtml2pdf import pisa
import cStringIO as StringIO
for feed in feeds.values():
# creates folder for each stream
folder = utils.path + "/var/export/pdf/" + \
utils.normalize_filename(feed.feed_title.strip().replace(':', '').lower())
try:
os.makedirs(folder)
except OSError:
# directories already exists (not a problem)
pass
for article in feed.articles.values():
name = article.article_date.strip().replace(' ', '_')
name = os.path.normpath(folder + "/" + name + ".pdf")
content = htmlheader
content += '\n<div style="width: 50%; overflow:hidden; text-align: justify; margin:0 auto">\n'
content += """<h1><a href="%s">%s</a></h1><br />""" % \
(article.article_link, article.article_title)
content += article.article_description
content += "</div>\n<hr />\n"
content += htmlfooter
try:
pdf = pisa.CreatePDF(StringIO.StringIO(content), file(name, "wb"))
except:
pass
|
