mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
65 lines
2.4 KiB
Python
65 lines
2.4 KiB
Python
#!/usr/bin/env python
|
|
# encoding: utf-8
|
|
|
|
import re
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
def classes(classes):
|
|
q = frozenset(classes.split(' '))
|
|
return dict(
|
|
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
|
|
)
|
|
|
|
|
|
class AnimalPolitico(BasicNewsRecipe):
|
|
title = u'Animal Político'
|
|
description = u'Noticias Políticas'
|
|
__author__ = 'Jose Ortiz'
|
|
masthead_url = 'https://www.animalpolitico.com/wp-content/themes/animalpolitico-2019/static/assets/logo_black.svg'
|
|
language = 'es_MX'
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
conversion_options = {
|
|
'tags': 'News, Mexico',
|
|
'publisher': 'Animal Politico',
|
|
'comments': description
|
|
}
|
|
|
|
keep_only_tags = [classes('ap_single_first ap_single_content ax_single')]
|
|
remove_tags = [classes('ap_single_sharers_head ap_single_sharers_share')]
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup('http://www.animalpolitico.com/')
|
|
articles = []
|
|
for a in soup(name='a', attrs={
|
|
'href': True, 'title': True,
|
|
'data-author': True, 'data-type': True,
|
|
'data-home-title': True
|
|
}):
|
|
title = a['title']
|
|
url = a['href']
|
|
author = a['data-author']
|
|
self.log('\t', title, ' at ', url)
|
|
|
|
articles.append({'title': title,
|
|
'author': author,
|
|
'url': url})
|
|
ans = {}
|
|
for article in articles:
|
|
if re.match(r'https?://www\.animalpolitico\.com/elsabueso/.', article['url'], re.I):
|
|
ans.setdefault('El Sabueso', []).append(article)
|
|
elif re.match(r'https?://www\.animalpolitico\.com/.', article['url'], re.I):
|
|
ans.setdefault('Noticias', []).append(article)
|
|
elif re.match(r'https?://www\.animalgourmet\.com/.', article['url'], re.I):
|
|
ans.setdefault('Comida', []).append(article)
|
|
|
|
return [(sec, ans[sec]) for sec in sorted(ans)]
|
|
|
|
def populate_article_metadata(self, article, soup, first):
|
|
if re.match(r'https?://www\.animalpolitico\.com/.', article.url, re.I):
|
|
article.formatted_date = self.tag_to_string(
|
|
soup.find(
|
|
**classes('ap_single_first')).find(
|
|
**classes('ap_single_first_info_date')))
|