| 1 |
#!/usr/bin/env python |
| 2 |
|
| 3 |
__license__ = 'GPL v3' |
| 4 |
__copyright__ = 'Copyright 2011 Starson17' |
| 5 |
''' |
| 6 |
engadget.com |
| 7 |
''' |
| 8 |
|
| 9 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 10 |
|
| 11 |
|
| 12 |
def classes(classes): |
| 13 |
q = frozenset(classes.split(' ')) |
| 14 |
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) |
| 15 |
|
| 16 |
|
| 17 |
class Engadget(BasicNewsRecipe): |
| 18 |
title = 'Engadget' |
| 19 |
__author__ = 'Starson17, modified by epubli' |
| 20 |
__version__ = 'v2.2' |
| 21 |
__date__ = '2024-09-15' |
| 22 |
description = 'Tech news' |
| 23 |
language = 'en' |
| 24 |
oldest_article = 7 |
| 25 |
max_articles_per_feed = 100 |
| 26 |
no_stylesheets = True |
| 27 |
use_embedded_content = False |
| 28 |
remove_javascript = True |
| 29 |
remove_empty_feeds = True |
| 30 |
compress_news_images = True |
| 31 |
scale_news_images_to_device = True |
| 32 |
cover_url = 'https://upload.wikimedia.org/wikipedia/commons/b/bb/Engadget-logo.svg' |
| 33 |
|
| 34 |
keep_only_tags = [classes('caas-content-wrapper caas-title-wrapper'), dict(name='figure')] |
| 35 |
remove_tags = [ |
| 36 |
dict(name='div', attrs={'class': 'caas-content-byline-wrapper'}), |
| 37 |
dict(name='div', attrs={'data-component': 'ArticleAuthorInfo'}), |
| 38 |
classes( |
| 39 |
'commerce-module caas-header caas-prestige-bottom-share caas-share-buttons caas-da' |
| 40 |
' caas-3p-blocked commerce-disclaimer notification-upsell-push' |
| 41 |
' article-slideshow athena-button email-form' |
| 42 |
), |
| 43 |
] |
| 44 |
|
| 45 |
feeds = [('Posts', 'https://www.engadget.com/rss.xml')] |
| 46 |
|
| 47 |
def parse_feeds(self): |
| 48 |
# Call parent's method. |
| 49 |
feeds = BasicNewsRecipe.parse_feeds(self) |
| 50 |
# Loop through all feeds. |
| 51 |
for feed in feeds: |
| 52 |
# Loop through all articles in feed. |
| 53 |
for article in feed.articles[:]: |
| 54 |
# Remove articles with '...' in the url. |
| 55 |
if '/deals/' in article.url: |
| 56 |
print('Removing:', article.title) |
| 57 |
feed.articles.remove(article) |
| 58 |
# Remove articles with '...' in the title. |
| 59 |
elif 'best tech deals' in article.title: |
| 60 |
print('Removing:', article.title) |
| 61 |
feed.articles.remove(article) |
| 62 |
elif 'Podcast' in article.title: |
| 63 |
print('Removing:', article.title) |
| 64 |
feed.articles.remove(article) |
| 65 |
elif 'The Morning After' in article.title: |
| 66 |
print('Removing:', article.title) |
| 67 |
feed.articles.remove(article) |
| 68 |
return feeds |
| 69 |
|
| 70 |
def preprocess_html(self, soup): |
| 71 |
for attr in 'data-src data-src-mobile'.split(): |
| 72 |
for img in soup.findAll('img'): |
| 73 |
try: |
| 74 |
ds = img[attr].split()[0] |
| 75 |
del img[attr] |
| 76 |
except KeyError: |
| 77 |
continue |
| 78 |
if ds: |
| 79 |
index = ds.rfind('https://') |
| 80 |
if index != -1: |
| 81 |
imgsrc = ds[index:] |
| 82 |
img['src'] = imgsrc |
| 83 |
for divs in soup.findAll('div'): |
| 84 |
try: |
| 85 |
if divs['style'].split()[0].startswith('padding'): |
| 86 |
print('Removing padding') |
| 87 |
del divs['style'] |
| 88 |
except KeyError: |
| 89 |
continue |
| 90 |
# Reorder the "title" and "content" elements |
| 91 |
title_div = soup.find('div', {'class': 'caas-title-wrapper'}) |
| 92 |
content_div = soup.find('div', {'class': 'caas-content-wrapper'}) |
| 93 |
if title_div and content_div: |
| 94 |
soup.body.clear() |
| 95 |
soup.body.append(title_div) |
| 96 |
soup.body.append(content_div) |
| 97 |
return soup |