calibre/recipes/joop.recipe

104 lines
3.5 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
import re
def new_tag(soup, name, attrs=()):
impl = getattr(soup, 'new_tag', None)
if impl is not None:
return impl(name, attrs=dict(attrs))
return Tag(soup, name, attrs=attrs or None)
class JoopRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'kwetal'
language = 'nl'
country = 'NL'
version = 1
title = u'Joop'
publisher = u'Vara'
category = u'News, Politics, Discussion'
description = u'Political blog from the Netherlands'
oldest_article = 7
max_articles_per_feed = 100
use_embedded_content = False
no_stylesheets = True
remove_javascript = True
keep_only_tags = []
keep_only_tags.append(
dict(name='div', attrs={'class': 'author_head clearfix photo'}))
keep_only_tags.append(
dict(name='h2', attrs={'class': 'columnhead smallline'}))
keep_only_tags.append(
dict(name='div', attrs={'class': re.compile('article.*')}))
extra_css = '''
body {font-family: verdana, arial, helvetica, geneva, sans-serif;}
img {margin-right: 0.4em;}
h3 {font-size: medium; font-style: italic; font-weight: normal;}
h2 {font-size: xx-large; font-weight: bold}
sub {color: #666666; font-size: x-small; font-weight: normal;}
div.joop_byline {font-size: large}
div.joop_byline_job {font-size: small; color: #696969;}
div.joop_date {font-size: x-small; font-style: italic; margin-top: 0.6em}
'''
INDEX = 'http://www.joop.nl'
conversion_options = {'comments': description, 'tags': category, 'language': language,
'publisher': publisher}
def parse_index(self):
sections = ['Politiek', 'Wereld', 'Economie',
'Groen', 'Media', 'Leven', 'Show', 'Opinies']
soup = self.index_to_soup(self.INDEX)
answer = []
div = soup.find('div', attrs={'id': 'footer'})
for section in sections:
articles = []
h2 = div.find(lambda tag: tag.name ==
'h2' and tag.renderContents().decode('utf-8') == section)
if h2:
ul = h2.findNextSibling('ul', 'linklist')
if ul:
for li in ul.findAll('li'):
title = self.tag_to_string(li.a)
url = self.INDEX + li.a['href']
articles.append(
{'title': title, 'date': None, 'url': url, 'description': ''})
answer.append((section, articles))
return answer
def preprocess_html(self, soup):
div = soup.find('div', 'author_head clearfix photo')
if div:
h2 = soup.find('h2')
if h2:
h2.name = 'div'
h2['class'] = 'joop_byline'
span = h2.find('span')
if span:
span.name = 'div'
span['class'] = 'joop_byline_job'
div.replaceWith(h2)
h2 = soup.find('h2', attrs={'class': 'columnhead smallline'})
if h2:
txt = None
span = h2.find('span', 'info')
if span:
txt = span.find(text=True)
div = new_tag(soup, 'div', attrs=[('class', 'joop_date')])
div.append(txt)
h2.replaceWith(div)
return soup