mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Update various Polish News sources
Merge branch 'master' of https://github.com/t3d/calibre
This commit is contained in:
Kovid Goyal
commit
3aac652c0b
@ -1,55 +0,0 @@
|
||||
#!/usr/bin/env python2
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = u'Łukasz Grąbczewski 2011-2013'
|
||||
__version__ = '2.0'
|
||||
|
||||
import re
|
||||
import os
|
||||
from calibre import walk
|
||||
from calibre.utils.zipfile import ZipFile
|
||||
from calibre.ptempfile import PersistentTemporaryFile
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class jazzpress(BasicNewsRecipe):
|
||||
__author__ = u'Łukasz Grąbczewski'
|
||||
title = 'JazzPRESS'
|
||||
language = 'pl'
|
||||
publisher = 'Fundacja Popularyzacji Muzyki Jazzowej EuroJAZZ'
|
||||
publication_type = 'magazine'
|
||||
description = u'Internetowa gazeta poświęcona muzyce improwizowanej'
|
||||
|
||||
conversion_options = {
|
||||
'authors': 'Fundacja Popularyzacji Muzyki Jazzowej EuroJAZZ',
|
||||
'publisher': publisher, 'language': language,
|
||||
'preserve_cover_aspect_ratio': True, 'remove_first_image': True
|
||||
}
|
||||
|
||||
def build_index(self):
|
||||
browser = self.get_browser()
|
||||
browser.open('http://radiojazz.fm/')
|
||||
|
||||
# find the link
|
||||
epublink = browser.find_link(
|
||||
url_regex=re.compile(r'e_jazzpress\d\d\d\d\_epub'))
|
||||
|
||||
# download ebook
|
||||
self.report_progress(0, _('Downloading ePUB'))
|
||||
response = browser.follow_link(epublink)
|
||||
book_file = PersistentTemporaryFile(suffix='.epub')
|
||||
book_file.write(response.read())
|
||||
book_file.close()
|
||||
|
||||
# convert
|
||||
self.report_progress(0.2, _('Converting to OEB'))
|
||||
oeb = self.output_dir + '/INPUT/'
|
||||
if not os.path.exists(oeb):
|
||||
os.makedirs(oeb)
|
||||
with ZipFile(book_file.name) as f:
|
||||
f.extractall(path=oeb)
|
||||
|
||||
for f in walk(oeb):
|
||||
if f.endswith('.opf'):
|
||||
return f # convert
|
||||
@ -14,7 +14,7 @@ class km_blog(BasicNewsRecipe):
|
||||
__author__ = 'teepel <teepel44@gmail.com>'
|
||||
language = 'pl'
|
||||
description = 'Wiadomości z bloga korwin-mikke.pl/blog'
|
||||
INDEX = 'http://korwin-mikke.pl/blog'
|
||||
INDEX = 'https://korwin-mikke.pl/blog'
|
||||
remove_empty_feeds = True
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
@ -22,16 +22,8 @@ class km_blog(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
remove_empty_feeds = True
|
||||
|
||||
feeds = [(u'blog', u'http://korwin-mikke.pl/blog/rss')]
|
||||
feeds = [(u'blog', u'https://korwin-mikke.pl/blog/rss')]
|
||||
|
||||
keep_only_tags = []
|
||||
# this line should show title of the article, but it doesnt work
|
||||
keep_only_tags.append(dict(name='div', attrs={'class': 'posts view'}))
|
||||
keep_only_tags.append(dict(name='div', attrs={'class': 'text'}))
|
||||
keep_only_tags.append(dict(name='h1'))
|
||||
keep_only_tags = [dict(name='div', attrs={'class': ['header-standard header-classic single-header', 'post-image', 'post-entry blockquote-style-1']})]
|
||||
|
||||
remove_tags = []
|
||||
remove_tags.append(dict(name='p', attrs={'class': 'float_right'}))
|
||||
remove_tags.append(dict(name='p', attrs={'class': 'date'}))
|
||||
|
||||
remove_tags_after = [(dict(name='div', attrs={'class': 'text'}))]
|
||||
remove_tags = [dict(name='div', attrs={'class': 'penci-hide-tagupdated'})]
|
||||
|
||||
@ -11,43 +11,19 @@ class KrytykaPolitycznaRecipe(BasicNewsRecipe):
|
||||
category = u'News'
|
||||
description = u' Lewicowe pismo zaangażowane w bieg spraw publicznych w Polsce.'
|
||||
cover_url = ''
|
||||
masthead_url = 'https://krytykapolityczna.pl/file/2015/09/krytyka-logo.png'
|
||||
remove_empty_feeds = True
|
||||
no_stylesheets = True
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100000
|
||||
max_articles_per_feed = 50
|
||||
recursions = 0
|
||||
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
simultaneous_downloads = 3
|
||||
|
||||
keep_only_tags = []
|
||||
keep_only_tags.append(dict(name='h1', attrs={'class': 'print-title'}))
|
||||
keep_only_tags.append(dict(name='div', attrs={'class': 'print-content'}))
|
||||
keep_only_tags = [(dict(name='h1')),
|
||||
(dict(name='div', attrs={'class': ['entry-meta','post-preview','entry-details', 'entry-content']}))]
|
||||
|
||||
remove_tags = []
|
||||
remove_tags.append(dict(attrs={'class': ['field field-type-text field-field-story-switch', 'field field-type-filefield field-field-story-temp',
|
||||
'field field-type-text field-field-story-author', 'field field-type-text field-field-story-lead-switch']}))
|
||||
remove_tags = [(dict(attrs={'class': ['_ning_zone_inner','book-item site-commerc','wp-embedded-content',
|
||||
'read-also','meta-date-modified updated', 'textwidget']}))]
|
||||
|
||||
extra_css = '''
|
||||
body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
|
||||
td.contentheading{font-size: large; font-weight: bold;}
|
||||
'''
|
||||
|
||||
feeds = [
|
||||
('Wszystkie', 'http://www.krytykapolityczna.pl/rss.xml')
|
||||
]
|
||||
|
||||
def print_version(self, url):
|
||||
soup = self.index_to_soup(url)
|
||||
print_ico = soup.find(attrs={'class': 'print-page'})
|
||||
print_uri = print_ico['href']
|
||||
self.log('PRINT', print_uri)
|
||||
return 'http://www.krytykapolityczna.pl/' + print_uri
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for alink in soup.findAll('a'):
|
||||
if alink.string is not None:
|
||||
tstr = alink.string
|
||||
alink.replaceWith(tstr)
|
||||
return soup
|
||||
feeds = [('Wszystkie', 'https://www.krytykapolityczna.pl/rss')]
|
||||
|
||||
@ -6,12 +6,9 @@ class Kresy(BasicNewsRecipe):
|
||||
__author__ = 'fenuks'
|
||||
description = u'portal społeczności kresowej'
|
||||
language = 'pl'
|
||||
masthead_url = 'http://www.kresy.pl/public/img/logo.png'
|
||||
cover_url = 'http://www.kresy.pl/public/img/logo.png'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
keep_only_tags = [dict(id='artykul')]
|
||||
remove_tags = [
|
||||
dict(attrs={'class': ['twitter-share-button', 'likefbborder', 'tagi']})]
|
||||
feeds = [(u'Wszystkie', u'http://www.kresy.pl/rss')]
|
||||
keep_only_tags = [dict(name='div', attrs={'class': ['big-slider big-preview single-big', 'entry-content-wrapper clearfix standard-content']})]
|
||||
remove_tags = [dict(attrs={'class': ['entry-footer', 'kresy_donate']})]
|
||||
feeds = [(u'Wszystkie', u'https://www.kresy.pl/rss')]
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user