| 1 |
__license__ = 'GPL v3' |
| 2 |
__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>' |
| 3 |
''' |
| 4 |
nspm.rs |
| 5 |
''' |
| 6 |
|
| 7 |
import re |
| 8 |
|
| 9 |
from calibre.ebooks.BeautifulSoup import NavigableString, Tag |
| 10 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 11 |
|
| 12 |
|
| 13 |
def new_tag(soup, name, attrs=()): |
| 14 |
impl = getattr(soup, 'new_tag', None) |
| 15 |
if impl is not None: |
| 16 |
return impl(name, attrs=dict(attrs)) |
| 17 |
return Tag(soup, name, attrs=attrs or None) |
| 18 |
|
| 19 |
|
| 20 |
class Nspm(BasicNewsRecipe): |
| 21 |
title = 'Nova srpska politicka misao' |
| 22 |
__author__ = 'Darko Miletic' |
| 23 |
description = 'Casopis za politicku teoriju i drustvena istrazivanja' |
| 24 |
publisher = 'NSPM' |
| 25 |
category = 'news, politics, Serbia' |
| 26 |
oldest_article = 7 |
| 27 |
max_articles_per_feed = 100 |
| 28 |
no_stylesheets = True |
| 29 |
use_embedded_content = False |
| 30 |
INDEX = 'http://www.nspm.rs/?alphabet=l' |
| 31 |
encoding = 'utf-8' |
| 32 |
language = 'sr' |
| 33 |
remove_empty_feeds = True |
| 34 |
publication_type = 'magazine' |
| 35 |
masthead_url = 'http://www.nspm.rs/templates/jsn_epic_pro/images/logol.jpg' |
| 36 |
extra_css = ''' @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} |
| 37 |
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} |
| 38 |
body{font-family: "Times New Roman", serif1, serif} |
| 39 |
.article_description{font-family: Arial, sans1, sans-serif} |
| 40 |
img{margin-top:0.5em; margin-bottom: 0.7em; display: block} |
| 41 |
.author{color: #990000; font-weight: bold} |
| 42 |
.author,.createdate{font-size: 0.9em} ''' |
| 43 |
|
| 44 |
conversion_options = {'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'pretty_print': True} |
| 45 |
|
| 46 |
preprocess_regexps = [(re.compile('\u0110'), lambda match: '\u00d0')] # noqa: RUF039 |
| 47 |
remove_tags = [dict(name=['link', 'script', 'meta', 'base', 'img'])] |
| 48 |
remove_attributes = ['width', 'height', 'lang', 'xmlns:fb', 'xmlns:og', 'vspace', 'hspace', 'type', 'start', 'size'] |
| 49 |
|
| 50 |
def get_browser(self): |
| 51 |
br = BasicNewsRecipe.get_browser(self) |
| 52 |
br.open(self.INDEX) |
| 53 |
return br |
| 54 |
|
| 55 |
feeds = [ |
| 56 |
('Rubrike', 'http://www.nspm.rs/rubrike/feed/rss.html'), |
| 57 |
('Debate', 'http://www.nspm.rs/debate/feed/rss.html'), |
| 58 |
('Reci i misli', 'http://www.nspm.rs/reci-i-misli/feed/rss.html'), |
| 59 |
('Samo smeh srbina spasava', 'http://www.nspm.rs/samo-smeh-srbina-spasava/feed/rss.html'), |
| 60 |
('Polemike', 'http://www.nspm.rs/polemike/feed/rss.html'), |
| 61 |
('Prikazi', 'http://www.nspm.rs/prikazi/feed/rss.html'), |
| 62 |
('Prenosimo', 'http://www.nspm.rs/prenosimo/feed/rss.html'), |
| 63 |
('Hronika', 'http://www.nspm.rs/tabela/hronika/feed/rss.html'), |
| 64 |
] |
| 65 |
|
| 66 |
def preprocess_html(self, soup): |
| 67 |
atitle = soup.body.find('a', attrs={'class': 'contentpagetitle'}) |
| 68 |
if atitle: |
| 69 |
cleanTitle = new_tag(soup, 'h1', [('class', 'contentpagetitle')]) |
| 70 |
cnt = NavigableString(self.tag_to_string(atitle)) |
| 71 |
cleanTitle.append(cnt) |
| 72 |
|
| 73 |
author = soup.body.find('span', attrs={'class': 'author'}) |
| 74 |
if author: |
| 75 |
author.extract() |
| 76 |
author.name = 'div' |
| 77 |
|
| 78 |
crdate = soup.body.find('td', attrs={'class': 'createdate'}) |
| 79 |
if crdate: |
| 80 |
cleanCrdate = new_tag(soup, 'div', [('class', 'createdate')]) |
| 81 |
cnt = NavigableString(self.tag_to_string(crdate)) |
| 82 |
cleanCrdate.append(cnt) |
| 83 |
|
| 84 |
# get the dependant element |
| 85 |
artText = new_tag(soup, 'div', [('class', 'text')]) |
| 86 |
textHolderp = crdate.parent |
| 87 |
textHolder = textHolderp.nextSibling |
| 88 |
while textHolder and (not isinstance(textHolder, Tag) or (textHolder.name != textHolderp.name)): |
| 89 |
textHolder = textHolder.nextSibling |
| 90 |
if textHolder.td: |
| 91 |
artText = textHolder.td |
| 92 |
artText.name = 'div' |
| 93 |
artText.attrs = [] |
| 94 |
artText['class'] = 'text' |
| 95 |
artText.extract() |
| 96 |
|
| 97 |
soup.body.contents = [] |
| 98 |
|
| 99 |
soup.body.append(cleanTitle) |
| 100 |
soup.body.append(author) |
| 101 |
soup.body.append(cleanCrdate) |
| 102 |
soup.body.append(artText) |
| 103 |
|
| 104 |
for item in soup.findAll('a'): |
| 105 |
limg = item.find('img') |
| 106 |
if item.string is not None: |
| 107 |
str = item.string |
| 108 |
item.replaceWith(str) |
| 109 |
elif limg: |
| 110 |
item.name = 'div' |
| 111 |
item.attrs = [] |
| 112 |
else: |
| 113 |
str = self.tag_to_string(item) |
| 114 |
item.replaceWith(str) |
| 115 |
for item in soup.findAll('img', alt=False): |
| 116 |
item['alt'] = 'image' |
| 117 |
return soup |