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 NYTimes

Browse Source
This commit is contained in:
Kovid Goyal 2023-05-08 22:50:55 +05:30
parent 6061b3893f
commit 49ff2bde2d
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 44 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
recipes/nytimes.recipe
View File

@ -197,6 +197,28 @@ class NewYorkTimes(BasicNewsRecipe):
def parse_article_group(self, container): def parse_article_group(self, container):
for li in container.findAll('li'): for li in container.findAll('li'):
article = li.find('article') article = li.find('article')
if article is None:
a = li.find('a', href=True)
if a is not None:
title = self.tag_to_string(li.find('h3'))
url = a['href']
if url.startswith('/'):
url = 'https://www.nytimes.com' + url
desc = ''
p = li.find('p')
if p is not None:
desc = self.tag_to_string(p)
date = ''
d = date_from_url(url)
if d is not None:
date = format_date(d)
today = datetime.date.today()
delta = today - d
if delta.days > oldest_web_edition_article:
self.log.debug('\tSkipping article', title, 'as it is too old')
continue
yield {'title': title, 'url': url, 'description': desc, 'date': date}
continue
h2 = article.find('h2') h2 = article.find('h2')
if h2 is not None: if h2 is not None:
title = self.tag_to_string(h2) title = self.tag_to_string(h2)

22
recipes/nytimes_sub.recipe
View File

@ -197,6 +197,28 @@ class NewYorkTimes(BasicNewsRecipe):
def parse_article_group(self, container): def parse_article_group(self, container):
for li in container.findAll('li'): for li in container.findAll('li'):
article = li.find('article') article = li.find('article')
if article is None:
a = li.find('a', href=True)
if a is not None:
title = self.tag_to_string(li.find('h3'))
url = a['href']
if url.startswith('/'):
url = 'https://www.nytimes.com' + url
desc = ''
p = li.find('p')
if p is not None:
desc = self.tag_to_string(p)
date = ''
d = date_from_url(url)
if d is not None:
date = format_date(d)
today = datetime.date.today()
delta = today - d
if delta.days > oldest_web_edition_article:
self.log.debug('\tSkipping article', title, 'as it is too old')
continue
yield {'title': title, 'url': url, 'description': desc, 'date': date}
continue
h2 = article.find('h2') h2 = article.find('h2')
if h2 is not None: if h2 is not None:
title = self.tag_to_string(h2) title = self.tag_to_string(h2)