mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
78efc02b01
"Al Jazeera in English" is broken currently, it only retrieves titles but no content. So I updated the recipe so content is preserved.
59 lines
1.6 KiB
Plaintext
59 lines
1.6 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
|
|
|
|
'''
|
|
english.aljazeera.net
|
|
'''
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
def has_cls(x):
|
|
return dict(attrs={'class': lambda cls: cls and x in cls.split()})
|
|
|
|
|
|
class AlJazeera(BasicNewsRecipe):
|
|
title = 'Al Jazeera in English'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'News from Middle East'
|
|
language = 'en'
|
|
publisher = 'Al Jazeera'
|
|
category = 'news, politics, middle east'
|
|
delay = 1
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
extra_css = """
|
|
body{font-family: Arial,sans-serif}
|
|
"""
|
|
conversion_options = {
|
|
'comment': description, 'tags': category,
|
|
'publisher': publisher, 'language': language
|
|
}
|
|
keep_only_tags = [
|
|
dict(id='article-page'),
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name=['object', 'link', 'table',
|
|
'meta', 'base', 'iframe', 'embed']),
|
|
]
|
|
|
|
feeds = [(u'Al Jazeera English',
|
|
u'http://www.aljazeera.com/xml/rss/all.xml')]
|
|
|
|
def get_article_url(self, article):
|
|
artlurl = article.get('link', None)
|
|
return artlurl
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
for item in soup.findAll(face=True):
|
|
del item['face']
|
|
for alink in soup.findAll('a'):
|
|
if alink.string is not None:
|
|
tstr = alink.string
|
|
alink.replaceWith(tstr)
|
|
return soup
|