Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Engadget

Browse Source
This commit is contained in:
Kovid Goyal 2024-09-15 17:02:49 +05:30
parent b9cb69ae6e
commit 0b0b2491f1
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 21 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
recipes/endgadget.recipe
View File

@ -8,7 +8,6 @@ engadget.com
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes): def classes(classes):
q = frozenset(classes.split(' ')) q = frozenset(classes.split(' '))
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
@ -17,8 +16,8 @@ def classes(classes):
class Engadget(BasicNewsRecipe): class Engadget(BasicNewsRecipe):
title = u'Engadget' title = u'Engadget'
__author__ = 'Starson17, modified by epubli' __author__ = 'Starson17, modified by epubli'
__version__ = 'v2.1' __version__ = 'v2.2'
__date__ = '2023-09-19' __date__ = '2024-09-15'
description = 'Tech news' description = 'Tech news'
language = 'en' language = 'en'
oldest_article = 7 oldest_article = 7
@ -32,16 +31,13 @@ class Engadget(BasicNewsRecipe):
cover_url = 'https://upload.wikimedia.org/wikipedia/commons/b/bb/Engadget-logo.svg' cover_url = 'https://upload.wikimedia.org/wikipedia/commons/b/bb/Engadget-logo.svg'
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'class':'caas-content-wrapper'}), classes('caas-content-wrapper caas-title-wrapper'),
dict(name='figure', attrs={'data-component':'DefaultLede'}),
dict(name='div', attrs={'data-component':'ArticleHeader'}),
dict(name='div', attrs={'class':['article-text','article-text c-gray-1 no-review']}),
dict(name='figure') dict(name='figure')
] ]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class':'caas-content-byline-wrapper'}), dict(name='div', attrs={'class':'caas-content-byline-wrapper'}),
dict(name='div', attrs={'data-component':'ArticleAuthorInfo'}), dict(name='div', attrs={'data-component':'ArticleAuthorInfo'}),
classes('caas-3p-blocked commerce-disclaimer notification-upsell-push article-slideshow athena-button email-form') 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')
] ]
feeds = [(u'Posts', u'https://www.engadget.com/rss.xml')] feeds = [(u'Posts', u'https://www.engadget.com/rss.xml')]
@ -53,8 +49,12 @@ class Engadget(BasicNewsRecipe):
for feed in feeds: for feed in feeds:
# Loop through all articles in feed. # Loop through all articles in feed.
for article in feed.articles[:]: 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. # Remove articles with '...' in the title.
if 'best tech deals' in article.title: elif 'best tech deals' in article.title:
print('Removing:',article.title) print('Removing:',article.title)
feed.articles.remove(article) feed.articles.remove(article)
elif 'Podcast' in article.title: elif 'Podcast' in article.title:
@ -74,7 +74,10 @@ class Engadget(BasicNewsRecipe):
except KeyError: except KeyError:
continue continue
if ds: if ds:
img['src'] = ds index = ds.rfind('https://')
if index != -1:
imgsrc = ds[index:]
img['src'] = imgsrc
for divs in soup.findAll('div'): for divs in soup.findAll('div'):
try: try:
if divs['style'].split()[0].startswith('padding'): if divs['style'].split()[0].startswith('padding'):
@ -82,6 +85,13 @@ class Engadget(BasicNewsRecipe):
del divs['style'] del divs['style']
except KeyError: except KeyError:
continue continue
# Reorder the "title" and "content" elements
body_tag = soup.find('body')
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 return soup