mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
69 lines
2.4 KiB
Python
69 lines
2.4 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
# License: GPLv3 Copyright: 2020, Kovid Goyal <kovid at kovidgoyal.net>
|
|
|
|
from __future__ import absolute_import, division, print_function, unicode_literals
|
|
|
|
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 AdvancedUserRecipe1282101454(BasicNewsRecipe):
|
|
title = 'Popular Science'
|
|
language = 'en'
|
|
__author__ = 'Kovid Goyal'
|
|
description = 'Popular Science'
|
|
publisher = 'Popular Science'
|
|
max_articles_per_feed = 100
|
|
ignore_duplicate_articles = {'url'}
|
|
no_stylesheets = True
|
|
keep_only_tags = [
|
|
classes('Article-header Article-excerpt Article-author Article-thumbnail Article-bodyText article-title article-dek article-paragraph articlebody'),
|
|
]
|
|
remove_tags = [
|
|
dict(name='section', attrs={'class': ['recurrent-share']})
|
|
]
|
|
|
|
def parse_section_index(self, slug):
|
|
url = 'https://www.popsci.com/{}/'.format(slug)
|
|
self.log('Section:', url)
|
|
soup = self.index_to_soup(url)
|
|
main = soup.find(**classes('category-content-wrapper lg:pb-12'))
|
|
if main is None:
|
|
return
|
|
for div in main.findAll(**classes('card-post')):
|
|
a = div.find('a', href=True, **classes('card-post-image-link'))
|
|
url = a['href']
|
|
tdiv = div.find(**classes('card-post-title')).find(**classes('mobile'))
|
|
title = self.tag_to_string(tdiv)
|
|
desc = ''
|
|
dek = div.find(**classes('card-post-excerpt'))
|
|
if dek is not None:
|
|
desc = self.tag_to_string(dek)
|
|
self.log(' ', title, url)
|
|
yield {'title': title, 'url': url, 'description': desc}
|
|
|
|
def parse_index(self):
|
|
sections = []
|
|
for slug, title in {
|
|
'science': 'Science',
|
|
'technology': 'Technology',
|
|
'diy': 'DIY',
|
|
'reviews': 'Reviews',
|
|
}.items():
|
|
self.log('slug:', slug)
|
|
articles = list(self.parse_section_index(slug))
|
|
if articles:
|
|
sections.append((title, articles))
|
|
return sections
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'data-medsrc': True}):
|
|
img['src'] = img['data-medsrc']
|
|
return soup
|