mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
83 lines
3.1 KiB
Python
83 lines
3.1 KiB
Python
#!/usr/bin/env python
|
|
|
|
__author__ = 'Darko Spasovski'
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2011, Darko Spasovski <darko.spasovski at gmail.com>'
|
|
'''
|
|
utrinski.com.mk
|
|
'''
|
|
|
|
import re
|
|
import datetime
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
|
from calibre import browser
|
|
|
|
|
|
class UtrinskiVesnik(BasicNewsRecipe):
|
|
|
|
INDEX = 'http://www.utrinski.com.mk/'
|
|
title = 'Utrinski Vesnik'
|
|
description = 'Daily Macedonian newspaper'
|
|
masthead_url = 'http://www.utrinski.com.mk/images/LogoTop.jpg'
|
|
language = 'mk'
|
|
remove_javascript = True
|
|
publication_type = 'newspaper'
|
|
category = 'news, Macedonia'
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
preprocess_regexps = [(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
|
|
[
|
|
# Remove anything before the start of the article.
|
|
(r'<body.*?Article start-->', lambda match: '<body>'),
|
|
|
|
# Remove anything after the end of the article.
|
|
(r'<!--Article end.*?</body>', lambda match: '</body>'),
|
|
]
|
|
]
|
|
extra_css = """
|
|
body{font-family: Arial,Helvetica,sans-serif}
|
|
.WB_UTRINSKIVESNIK_Naslov{FONT-WEIGHT: bold; FONT-SIZE: 18px; FONT-FAMILY: Arial, Verdana, Tahoma; TEXT-DECORATION: none}
|
|
"""
|
|
|
|
conversion_options = {
|
|
'comment': description,
|
|
'tags': category,
|
|
'language': language,
|
|
'linearize_tables': True
|
|
}
|
|
|
|
def parse_index(self):
|
|
feeds = []
|
|
# open main page
|
|
soup = self.index_to_soup(self.INDEX)
|
|
# find all anchors with class attribute equal to
|
|
# 'WB_UTRINSKIVESNIK_MainMenu'
|
|
for section in soup.findAll('a', attrs={'class': 'WB_UTRINSKIVESNIK_MainMenu'}):
|
|
sectionTitle = section.contents[0].string
|
|
sectionUrl = self.INDEX + section['href'].strip()
|
|
# open the anchor link
|
|
raw = browser().open_novisit(sectionUrl).read()
|
|
sectionSoup = BeautifulSoup(raw)
|
|
# find all anchors with class attribute equal to
|
|
# 'WB_UTRINSKIVESNIK_ONLINEArticleTitle'
|
|
sectionArticles = sectionSoup.findAll(
|
|
'a', attrs={'class': 'WB_UTRINSKIVESNIK_ONLINEArticleTitle'})
|
|
articles = []
|
|
for sectionArticle in sectionArticles:
|
|
# article title = anchor's contents, article url = anchor's
|
|
# href
|
|
articleTitle = sectionArticle.contents[0].string.strip()
|
|
articleUrl = self.INDEX + sectionArticle['href'].strip()
|
|
articleDate = datetime.datetime.today().strftime('%d.%m.%Y')
|
|
articles.append(
|
|
{'title': articleTitle, 'url': articleUrl, 'description': '', 'date': articleDate})
|
|
if articles:
|
|
feeds.append((sectionTitle, articles))
|
|
return feeds
|
|
|
|
def get_cover_url(self):
|
|
datum = datetime.datetime.today().strftime('%d_%m_%Y')
|
|
return 'http://www.utrinski.com.mk/WBStorage/Files/' + datum + '.jpg'
|