-
-
Notifications
You must be signed in to change notification settings - Fork 2.2k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
a904cc3
commit e8cb43b
Showing
1 changed file
with
52 additions
and
56 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,60 +1,56 @@ | ||
__license__ = 'GPL v3' | ||
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>' | ||
''' | ||
techcrunch.com | ||
''' | ||
|
||
#!/usr/bin/env python | ||
# vim:fileencoding=utf-8 | ||
from calibre.web.feeds.news import BasicNewsRecipe | ||
|
||
|
||
class TechCrunch(BasicNewsRecipe): | ||
title = 'TechCrunch' | ||
__author__ = 'Darko Miletic' | ||
description = 'IT News' | ||
publisher = 'AOL Inc.' | ||
category = 'news, IT' | ||
oldest_article = 2 | ||
max_articles_per_feed = 200 | ||
no_stylesheets = True | ||
encoding = 'utf8' | ||
use_embedded_content = False | ||
class AdvancedUserRecipe1718089036(BasicNewsRecipe): | ||
title = 'TechCrunch' | ||
language = 'en' | ||
remove_empty_feeds = True | ||
publication_type = 'newsportal' | ||
masthead_url = 'http://s2.wp.com/wp-content/themes/vip/tctechcrunch2/images/site-logo.png' | ||
extra_css = """ | ||
body{font-family: Helvetica,Arial,sans-serif } | ||
img{margin-bottom: 0.4em; display:block} | ||
""" | ||
|
||
conversion_options = { | ||
'comment': description, 'tags': category, 'publisher': publisher, 'language': language | ||
} | ||
|
||
remove_tags = [dict(name=['meta', 'link'])] | ||
remove_attributes = ['lang'] | ||
keep_only_tags = [ | ||
dict(name='h1', attrs={'class': 'headline'}), dict( | ||
attrs={'class': ['author', 'post-time', 'body-copy']}) | ||
] | ||
|
||
feeds = [(u'News', u'http://feeds.feedburner.com/TechCrunch/')] | ||
__author__ = 'Spicy Poison' | ||
description = 'TechCrunch is an American global online newspaper focusing on topics regarding high-tech and startup companies.' | ||
publisher = 'Yahoo! Inc.' | ||
oldest_article = 30 | ||
max_articles_per_feed = 50 | ||
ignore_duplicate_articles = {'title', 'url'} | ||
encoding = 'utf-8' | ||
masthead_url = 'https://aircoverpr.com/wp-content/uploads/2020/07/techcrunch-logo-png-4.png' | ||
auto_cleanup = True | ||
|
||
def preprocess_html(self, soup): | ||
for item in soup.findAll(style=True): | ||
del item['style'] | ||
for item in soup.findAll('a'): | ||
limg = item.find('img') | ||
if item.string is not None: | ||
str = item.string | ||
item.replaceWith(str) | ||
else: | ||
if limg: | ||
item.name = 'div' | ||
item.attrs = [] | ||
else: | ||
str = self.tag_to_string(item) | ||
item.replaceWith(str) | ||
for item in soup.findAll('img', alt=False): | ||
item['alt'] = 'image' | ||
return soup | ||
feeds = [ | ||
('TechCrunch', 'https://techcrunch.com/feed/'), | ||
#Categories | ||
('Apps', 'https://techcrunch.com/category/apps/feed/'), | ||
('Artificial Intelligence', 'https://techcrunch.com/category/artificial-intelligence/feed/'), | ||
('Biotech', 'https://techcrunch.com/category/biotech-health/feed/'), | ||
('Climate', 'https://techcrunch.com/category/climate/feed/'), | ||
('Commerce', 'https://techcrunch.com/category/commerce/feed/'), | ||
('Crypto', 'https://techcrunch.com/category/cryptocurrency/feed/'), | ||
('Enterprise', 'https://techcrunch.com/category/enterprise/feed/'), | ||
('Fintech', 'https://techcrunch.com/category/fintech/feed'), | ||
('Fundraising', 'https://techcrunch.com/category/fundraising/feed/'), | ||
('Gadgets', 'https://techcrunch.com/category/gadgets/feed/'), | ||
('Gaming', 'https://techcrunch.com/category/gaming/feed/'), | ||
('Hardware', 'https://techcrunch.com/category/hardware/feed/'), | ||
('Media & Entertainment', 'https://techcrunch.com/category/media-entertainment/feed/'), | ||
('Privacy', 'https://techcrunch.com/category/privacy/feed/'), | ||
('Robotics', 'https://techcrunch.com/category/robotics/feed/'), | ||
('Security', 'https://techcrunch.com/category/security/feed/'), | ||
('Social Media', 'https://techcrunch.com/category/social/feed/'), | ||
('Space', 'https://techcrunch.com/category/space/feed/'), | ||
('Startups', 'https://techcrunch.com/category/startups/feed/'), | ||
('Tech Policy & Government', 'https://techcrunch.com/category/government-policy/feed/'), | ||
('Transportation', 'https://techcrunch.com/category/transportation/feed/'), | ||
('Venture Capital', 'https://techcrunch.com/category/venture/feed/'), | ||
#Tags | ||
('Amazon', 'https://techcrunch.com/tag/amazon/feed/'), | ||
('Apple', 'https://techcrunch.com/tag/apple/feed/'), | ||
('Cloud Computing', 'https://techcrunch.com/tag/cloud-computing/feed/'), | ||
('Electric Vehicles', 'https://techcrunch.com/tag/evs/feed/'), | ||
('Google', 'https://techcrunch.com/tag/google/feed/'), | ||
('Instagram', 'https://techcrunch.com/tag/instagram/feed/'), | ||
('Layoffs', 'https://techcrunch.com/tag/layoffs/feed/'), | ||
('Meta', 'https://techcrunch.com/tag/meta/feed/'), | ||
('Microsoft', 'https://techcrunch.com/tag/microsoft/feed/'), | ||
('TikTok', 'https://techcrunch.com/tag/tiktok/feed/'), | ||
#Other | ||
('Events Archive', 'https://techcrunch.com/events/feed/'), | ||
] |