#! /usr/bin/env python
#-*- coding: utf-8 -*-
# pyAggr3g470r - A Web based news aggregator.
# Copyright (C) 2010-2013 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
This archive has been generated with pyAggr3g470r. A software under GPLv3 license. You are welcome to copy, modify or redistribute the source code according to the GPLv3 license.
""" CSS = """body { font:normal medium 'Gill Sans','Gill Sans MT',Verdana,sans-serif; margin:1.20em auto; width:80%; line-height:1.75; } blockquote { font-size:small; line-height:2.153846; margin:2.153846em 0; padding:0;font-style:oblique; border-left:1px dotted; margin-left:2.153846em; padding-left:2.153846em; } blockquote p{ margin:2.153846em 0; } p+br { display:none; } h1 { font-size:large; } h2,h3 { font-size:medium; } hr { border-style:dotted; height:1px; border-width: 1px 0 0 0; margin:1.45em 0 1.4em; padding:0; } a { text-decoration:none; color:#00008B; } #footer { clear:both; text-align:center; font-size:small; } img { border:0; } .horizontal,.simple li { margin:0; padding:0; list-style:none; display:inline } .simple li:before { content:"+ "; } .simple > li:first-child:before { content:""; } .author { text-decoration:none; display:block; float:right; margin-left:2em; font-size:small; } .content { margin:1.00em 1.00em; }""" def export_html(feeds): """ Export the articles given in parameter in a simple Webzine. """ nb_articles = format(len(models.Article.objects()), ",d") index = HTML_HEADER("News archive") index += "%s articles.
\n%s articles.
\n""" % (format(len(feed.articles), ",d"),) for article in feed.articles: post_file_name = os.path.normpath(feed_folder + "/" + str(article.id) + ".html") feed_index = os.path.normpath(feed_folder + "/index.html") posts += article.date.ctime() + " - " + """%s""" % \ (article.id, article.title[:150]) + "" + time.strftime("Generated on %d %b %Y at %H:%M.") + "
\n" index += HTML_FOOTER with open(conf.PATH + "/pyaggr3g470r/var/export/webzine/" + "index.html", "w") as f: f.write(index.encode("utf-8")) with open(conf.PATH + "/pyaggr3g470r/var/export/webzine/" + "style.css", "w") as f: f.write(CSS.encode("utf-8")) with tarfile.open(conf.PATH + "/pyaggr3g470r/var/export.tar.gz", "w:gz") as tar: tar.add(conf.PATH + "/pyaggr3g470r/var/export/webzine/", arcname=os.path.basename(conf.PATH + "/pyaggr3g470r/var/export/webzine/")) 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()) try: os.makedirs(folder) except OSError: # directories already exists (not a problem) pass for article in mongo_db.get_articles(feed_id=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)