I have tried to modify the current built-in recipe to return all pictures in articles, it gets some but not all. Here is the recipe I have -
------------------------------------------
#!/usr/bin/env python2
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
from calibre.web.feeds.news import BasicNewsRecipe
# from telegraph.uk not changed
def classes(classes):
q = frozenset(classes.split(' '))
return dict(
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
)
# end from telegraph uk
class FoxNews(BasicNewsRecipe):
title = 'FOX News'
__author__ = 'Darko Miletic'
description = 'Breaking News from FOX'
publisher = 'FOXNews.com'
category = 'news, breaking news, latest news, current news, world news, national news, USA'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
compress_news_images = True
# compress_news_images_auto_size = 8
language = 'en'
publication_type = 'newsportal'
remove_empty_feeds = True
extra_css = """
body{font-family: Arial,sans-serif }
.caption{font-size: x-small}
.author,.dateline{font-size: small}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
remove_attributes = ['xmlns','lang']
ignore_duplicate_articles = {'title', 'url'}
keep_only_tags = [
#classes command below based on from telegraph uk
dict(itemprop=['headline', 'articleBody']),
dict(name='h1'),
classes('byline author'),
classes('date source'),
dict(attrs={'class':'article-info article-body'.split()}),
]
feeds = [
(u'Latest Headlines', u'http://feeds.foxnews.com/foxnews/latest' )
,(u'National' , u'http://feeds.foxnews.com/foxnews/national' )
,(u'World' , u'http://feeds.foxnews.com/foxnews/world')
,(u'Politics' , u'http://feeds.foxnews.com/foxnews/politics')
,(u'Opinion' , u'http://feeds.foxnews.com/foxnews/opinion')
,(u'Science' , u'http://feeds.foxnews.com/foxnews/science')
,(u'Technology' , u'http://feeds.foxnews.com/foxnews/tech')
,(u'Health' , u'http://feeds.foxnews.com/foxnews/health')
,(u'Lifestyle' , u'http://feeds.foxnews.com/foxnews/section/lifestyle')
,(u'Travel' , u'http://feeds.foxnews.com/foxnews/internal/travel/mixed')
]
--------------------------
As example, here is the link location of one article picture (from web view of the article in the web rss section) which was not included in the mobi output -
http://a57.foxnews.com/images.foxnew....jpg?ve=1&tl=1
Could you kindly look at this for all pictures?
NB, I was able to change built in to get the articles to include the author, publish date, and publisher just after the heading. Thanks.