Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update nytfeeds.recipe #2438

Merged
merged 1 commit into from
Sep 18, 2024
Merged

Update nytfeeds.recipe #2438

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
44 changes: 32 additions & 12 deletions recipes/nytfeeds.recipe
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -208,17 +208,27 @@ class nytFeeds(BasicNewsRecipe):
img { display:block; margin:0 auto; }
'''

# https://www.nytimes.com/rss
# https://developer.nytimes.com/docs/rss-api/1/overview
feeds = [
('World', 'https://rss.nytimes.com/services/xml/rss/nyt/World.xml'),
('US', 'https://rss.nytimes.com/services/xml/rss/nyt/US.xml'),
('Business', 'https://rss.nytimes.com/services/xml/rss/nyt/Business.xml'),
('Technology', 'https://rss.nytimes.com/services/xml/rss/nyt/Technology.xml'),
('Science', 'https://rss.nytimes.com/services/xml/rss/nyt/Science.xml'),
('Arts', 'https://rss.nytimes.com/services/xml/rss/nyt/Arts.xml'),
('Fashion & Style', 'https://rss.nytimes.com/services/xml/rss/nyt/FashionandStyle.xml'),
('TMagazine', 'https://rss.nytimes.com/services/xml/rss/nyt/tmagazine.xml'),
('Travel', 'https://www.nytimes.com/services/xml/rss/nyt/Travel.xml'),
('Sunday Review', 'https://rss.nytimes.com/services/xml/rss/nyt/sunday-review.xml'),
# to filter out all opinions from other sections first
'https://rss.nytimes.com/services/xml/rss/nyt/Opinion.xml',

'https://rss.nytimes.com/services/xml/rss/nyt/HomePage.xml',
'https://rss.nytimes.com/services/xml/rss/nyt/World.xml',
'https://rss.nytimes.com/services/xml/rss/nyt/US.xml',
'https://rss.nytimes.com/services/xml/rss/nyt/Business.xml',
'https://rss.nytimes.com/services/xml/rss/nyt/YourMoney.xml',
'https://rss.nytimes.com/services/xml/rss/nyt/Technology.xml',
'https://rss.nytimes.com/services/xml/rss/nyt/Science.xml',
'https://rss.nytimes.com/services/xml/rss/nyt/Climate.xml',
'https://rss.nytimes.com/services/xml/rss/nyt/Health.xml',
'https://rss.nytimes.com/services/xml/rss/nyt/Arts.xml',
'https://rss.nytimes.com/services/xml/rss/nyt/FashionandStyle.xml',
'https://rss.nytimes.com/services/xml/rss/nyt/tmagazine.xml',
'https://rss.nytimes.com/services/xml/rss/nyt/books.xml',
'https://www.nytimes.com/services/xml/rss/nyt/Travel.xml',
'http://nytimes.com/timeswire/feeds/'
]

def get_browser(self, *args, **kwargs):
Expand All @@ -231,6 +241,10 @@ class nytFeeds(BasicNewsRecipe):
return br

def preprocess_raw_html(self, raw_html, url):
if '/interactive/' in url:
return '<html><body><p><em>'\
+ 'This is an interactive article, which is supposed to be read in a browser.'\
+ '</p></em></body></html>'
data = extract_json(raw_html)
return '\n'.join(article_parse(data))

Expand All @@ -239,9 +253,15 @@ class nytFeeds(BasicNewsRecipe):
if w and isinstance(w, str):
res = '-' + w
for img in soup.findAll('img', attrs={'src':True}):
ext = img['src'].split('?')[0].split('.')[-1]
img['src'] = img['src'].rsplit('-article', 1)[0] + res + '.' + ext
if '-article' in img['src']:
ext = img['src'].split('?')[0].split('.')[-1]
img['src'] = img['src'].rsplit('-article', 1)[0] + res + '.' + ext
for c in soup.findAll('div', attrs={'class':'cap'}):
for p in c.findAll(['p', 'div']):
p.name = 'span'
return soup

def get_article_url(self, article):
url = BasicNewsRecipe.get_article_url(self, article)
if not re.search(r'/video/|live|/athletic/', url):
return url
Loading