calibre/recipes/bighollywood.recipe
2019-03-22 23:47:49 +05:30

61 lines
2.0 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
'''
bighollywood.breitbart.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class BigHollywood(BasicNewsRecipe):
title = 'Big Hollywood'
__author__ = 'Darko Miletic'
description = 'News and articles from the media world'
publisher = 'Big Hollywood'
category = 'news, media, art, literature, movies, politics, USA, Hollywood'
oldest_article = 7
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'en'
remove_empty_feeds = True
publication_type = 'blog'
extra_css = """
body{font-family: Arial,sans-serif }
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
keep_only_tags = [dict(attrs={'class': 'postcontent'})]
remove_tags = [
dict(name=['meta', 'link', 'link', 'iframe', 'embed', 'object']), dict(
name='p', attrs={'class': ['post_meta_links', 'postfooter']})
]
remove_attributes = ['original', 'onclick']
feeds = [(u'Articles', u'http://bighollywood.breitbart.com/feed/')]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('a'):
limg = item.find('img')
if item.string is not None:
str = item.string
item.replaceWith(str)
else:
if limg:
if limg['src'].endswith('BlogPrintButton.png'):
limg.extract()
item.name = 'div'
item.attrs = []
else:
str = self.tag_to_string(item)
item.replaceWith(str)
for item in soup.findAll('img', alt=False):
item['alt'] = 'image'
return soup