mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
37 lines
1.1 KiB
Plaintext
37 lines
1.1 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class AdvancedUserRecipe1282101454(BasicNewsRecipe):
|
|
title = 'How To Geek'
|
|
language = 'en'
|
|
__author__ = 'TonytheBookworm, PatStapleton (update 2020-05-20)'
|
|
description = 'Daily Computer Tips and Tricks'
|
|
publisher = 'Howtogeek'
|
|
category = 'PC,tips,tricks'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
linearize_tables = True
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
use_embedded_content = False
|
|
|
|
keep_only_tags = [
|
|
dict(id='main')
|
|
]
|
|
remove_tags_after = dict(classes='affiliate-disclosure')
|
|
remove_tags = [
|
|
dict(name='a', attrs={'target': ['_blank']}),
|
|
dict(name='table', attrs={'id': ['articleTable']}),
|
|
dict(name='div', attrs={'class': ['feedflare', 'article-share-widgets', 'related-articles', 'comments', 'nextup']}),
|
|
]
|
|
|
|
feeds = [
|
|
('How-to Geek', 'https://www.howtogeek.com/feed/')
|
|
|
|
]
|
|
|
|
def preprocess_html(self, soup, *a):
|
|
for img in soup.findAll('img', attrs={'data-pagespeed-lazy-src': True}):
|
|
img['src'] = img['data-pagespeed-lazy-src']
|
|
return soup
|