mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-14 16:18:05 -04:00
97 lines
3.6 KiB
Python
97 lines
3.6 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = 'Copyright 2011 Starson17'
|
|
'''
|
|
engadget.com
|
|
'''
|
|
|
|
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 Engadget(BasicNewsRecipe):
|
|
title = u'Engadget'
|
|
__author__ = 'Starson17, modified by epubli'
|
|
__version__ = 'v2.2'
|
|
__date__ = '2024-09-15'
|
|
description = 'Tech news'
|
|
language = 'en'
|
|
oldest_article = 7
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
remove_javascript = True
|
|
remove_empty_feeds = True
|
|
compress_news_images = True
|
|
scale_news_images_to_device = True
|
|
cover_url = 'https://upload.wikimedia.org/wikipedia/commons/b/bb/Engadget-logo.svg'
|
|
|
|
keep_only_tags = [
|
|
classes('caas-content-wrapper caas-title-wrapper'),
|
|
dict(name='figure')
|
|
]
|
|
remove_tags = [
|
|
dict(name='div', attrs={'class':'caas-content-byline-wrapper'}),
|
|
dict(name='div', attrs={'data-component':'ArticleAuthorInfo'}),
|
|
classes('commerce-module caas-header caas-prestige-bottom-share caas-share-buttons caas-da caas-3p-blocked commerce-disclaimer notification-upsell-push article-slideshow athena-button email-form') # noqa: E501
|
|
]
|
|
|
|
feeds = [(u'Posts', u'https://www.engadget.com/rss.xml')]
|
|
|
|
def parse_feeds(self):
|
|
# Call parent's method.
|
|
feeds = BasicNewsRecipe.parse_feeds(self)
|
|
# Loop through all feeds.
|
|
for feed in feeds:
|
|
# Loop through all articles in feed.
|
|
for article in feed.articles[:]:
|
|
# Remove articles with '...' in the url.
|
|
if '/deals/' in article.url:
|
|
print('Removing:',article.title)
|
|
feed.articles.remove(article)
|
|
# Remove articles with '...' in the title.
|
|
elif 'best tech deals' in article.title:
|
|
print('Removing:',article.title)
|
|
feed.articles.remove(article)
|
|
elif 'Podcast' in article.title:
|
|
print('Removing:',article.title)
|
|
feed.articles.remove(article)
|
|
elif 'The Morning After' in article.title:
|
|
print('Removing:',article.title)
|
|
feed.articles.remove(article)
|
|
return feeds
|
|
|
|
def preprocess_html(self, soup):
|
|
for attr in 'data-src data-src-mobile'.split():
|
|
for img in soup.findAll('img'):
|
|
try:
|
|
ds = img[attr].split()[0]
|
|
del img[attr]
|
|
except KeyError:
|
|
continue
|
|
if ds:
|
|
index = ds.rfind('https://')
|
|
if index != -1:
|
|
imgsrc = ds[index:]
|
|
img['src'] = imgsrc
|
|
for divs in soup.findAll('div'):
|
|
try:
|
|
if divs['style'].split()[0].startswith('padding'):
|
|
print('Removing padding')
|
|
del divs['style']
|
|
except KeyError:
|
|
continue
|
|
# Reorder the "title" and "content" elements
|
|
title_div = soup.find('div', {'class': 'caas-title-wrapper'})
|
|
content_div = soup.find('div', {'class': 'caas-content-wrapper'})
|
|
if title_div and content_div:
|
|
soup.body.clear()
|
|
soup.body.append(title_div)
|
|
soup.body.append(content_div)
|
|
return soup
|