mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-11-23 06:53:02 -05:00
76 lines
2.4 KiB
Python
76 lines
2.4 KiB
Python
#!/usr/bin/env python
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
|
|
|
|
class Volkskrant(BasicNewsRecipe):
|
|
title = 'Revista 22'
|
|
__author__ = 'Cristi Ghera'
|
|
max_articles_per_feed = 100
|
|
description = 'Revista 22'
|
|
needs_subscription = False
|
|
language = 'ro'
|
|
country = 'RO'
|
|
category = 'news, politics, Romania'
|
|
resolve_internal_links = True
|
|
remove_tags_before = { 'class': 'col-span-8' }
|
|
remove_tags_after = { 'class': 'col-span-8' }
|
|
remove_tags = [
|
|
dict(
|
|
attrs={
|
|
'class': [
|
|
'icons',
|
|
'float-left',
|
|
'samesection',
|
|
]
|
|
}
|
|
),
|
|
dict(
|
|
name=['div'],
|
|
attrs={
|
|
'class': ['mb-2']
|
|
}
|
|
),
|
|
dict(id=['comments']),
|
|
dict(name=['script', 'noscript', 'style']),
|
|
]
|
|
remove_attributes = ["class", "id", "name", "style"]
|
|
encoding = 'utf-8'
|
|
no_stylesheets = True
|
|
ignore_duplicate_articles = {'url'}
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup('https://revista22.ro')
|
|
url = soup.find('div', attrs={'class': 'uppercase'}).find('a').attrs['href']
|
|
if url[0] == '/':
|
|
url = 'https://revista22.ro' + url
|
|
soup = self.index_to_soup(url)
|
|
main_container = soup.find('div', attrs={'class': 'col-span-8'})
|
|
containers = main_container.findAll(attrs={'class': 'mb-4'})
|
|
articles = []
|
|
for container in containers:
|
|
if 'pb-4' not in container.attrs['class']:
|
|
continue
|
|
a = container.find('a')
|
|
url = a['href']
|
|
if url[0] == '/':
|
|
url = 'https://revista22.ro' + url
|
|
article_title = self.tag_to_string(a.find('h3')).strip()
|
|
author = self.tag_to_string(
|
|
container.find('span', attrs={'class': 'text-red'})
|
|
).strip()
|
|
summary = self.tag_to_string(container.find('p')).strip()
|
|
pubdate = self.tag_to_string(a.find('span'))
|
|
description = author + ' - ' + summary
|
|
articles.append(
|
|
dict(
|
|
title=article_title,
|
|
url=url,
|
|
date=pubdate,
|
|
description=description,
|
|
content=''
|
|
)
|
|
)
|
|
|
|
sections = [('Numărul curent', articles)]
|
|
return sections
|