Update Lomza

Merge branch 'news' of https://github.com/t3d/calibre
This commit is contained in:
Kovid Goyal 2017-10-17 08:24:17 +05:30
commit b36d1704e4
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
5 changed files with 1 additions and 83 deletions

View File

@ -1,52 +0,0 @@
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = u'Łukasz Grąbczewski 2011'
__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 biweekly(BasicNewsRecipe):
__author__ = u'Łukasz Grąbczewski'
title = 'Biweekly'
language = 'en_PL'
publisher = 'National Audiovisual Institute'
publication_type = 'magazine'
description = u'link with culture [English edition of Polish magazine]: literature, theatre, film, art, music, views, talks'
conversion_options = {
'authors': 'Biweekly.pl', 'publisher': publisher, 'language': language, 'comments': description, 'no_default_epub_cover': True, 'preserve_cover_aspect_ratio': True # noqa
}
def build_index(self):
browser = self.get_browser()
browser.open('http://www.biweekly.pl/')
# find the link
epublink = browser.find_link(text_regex=re.compile('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

Binary file not shown.

Before

Width:  |  Height:  |  Size: 355 B

Binary file not shown.

Before

Width:  |  Height:  |  Size: 634 B

View File

@ -13,5 +13,5 @@ class Lomza(BasicNewsRecipe):
max_articles_per_feed = 100
remove_tags = [
dict(name='div', attrs={'class': ['bxbanner', 'drukuj', 'wyslijznajomemu']})]
keep_only_tags = [dict(name='div', attrs={'class': 'wiadomosc'})]
keep_only_tags = [dict(name='div', attrs={'id': 'srodek'})]
feeds = [(u'Łomża', u'http://feeds.feedburner.com/4lomza.pl')]

View File

@ -1,30 +0,0 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Overclock_pl(BasicNewsRecipe):
title = u'Overclock.pl'
oldest_article = 7
max_articles_per_feed = 100
__author__ = 'fenuks'
description = u'Vortal poświęcony tematyce hardware, kładący największy nacisk na podkręcanie / overclocking (włącznie z extreme) i chłodzenie / cooling (air cooling, water cooling, freon cooling, dry ice, liquid nitrogen).' # noqa
category = 'IT'
language = 'pl'
masthead_url = 'http://www.overclock.pl/gfx/logo_m.png'
cover_url = 'http://www.overclock.pl/gfx/logo_m.png'
no_stylesheets = True
remove_empty_feeds = True
preprocess_regexps = [(re.compile(ur'<b>Komentarze do aktualności:.*?</a>', re.DOTALL),
lambda match: ''), (re.compile(ur'<h3>Nawigacja</h3>', re.DOTALL), lambda match: '')]
keep_only_tags = [
dict(name='div', attrs={'class': 'news'}), dict(id='articleContent')]
remove_tags = [dict(name='span', attrs={'class': 'info'}), dict(
attrs={'class': 'shareit'})]
feeds = [(u'Aktualno\u015bci', u'http://www.overclock.pl/rss.news.xml'),
(u'Testy i recenzje', u'http://www.overclock.pl/rss.articles.xml')]
def print_version(self, url):
if 'articles/show' in url:
return url.replace('show', 'showall')
else:
return url