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 2023-08-06 10:20:36 +05:30
parent 009f8f33ad
commit ffd1af3ddb
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 18 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
recipes/nytimes.recipe
View File

@ -200,14 +200,18 @@ class NewYorkTimes(BasicNewsRecipe):
if article is None: if article is None:
a = li.find('a', href=True) a = li.find('a', href=True)
if a is not None: if a is not None:
title = self.tag_to_string(li.find('h3')) title = self.tag_to_string(li.find(['h3', 'h2'])).strip()
paras = li.findAll('p')
if not title:
title = self.tag_to_string(paras[0]).strip()
if not title:
raise ValueError('No title found in article')
url = a['href'] url = a['href']
if url.startswith('/'): if url.startswith('/'):
url = 'https://www.nytimes.com' + url url = 'https://www.nytimes.com' + url
desc = '' desc = ''
p = li.find('p') if len(paras) > 0:
if p is not None: desc = self.tag_to_string(paras[-1])
desc = self.tag_to_string(p)
date = '' date = ''
d = date_from_url(url) d = date_from_url(url)
if d is not None: if d is not None:
@ -219,7 +223,7 @@ class NewYorkTimes(BasicNewsRecipe):
continue continue
yield {'title': title, 'url': url, 'description': desc, 'date': date} yield {'title': title, 'url': url, 'description': desc, 'date': date}
continue continue
h2 = article.find('h2') h2 = article.find(['h2', 'h3'])
if h2 is not None: if h2 is not None:
title = self.tag_to_string(h2) title = self.tag_to_string(h2)
a = h2.find('a', href=True) a = h2.find('a', href=True)

14
recipes/nytimes_sub.recipe
View File

@ -200,14 +200,18 @@ class NewYorkTimes(BasicNewsRecipe):
if article is None: if article is None:
a = li.find('a', href=True) a = li.find('a', href=True)
if a is not None: if a is not None:
title = self.tag_to_string(li.find('h3')) title = self.tag_to_string(li.find(['h3', 'h2'])).strip()
paras = li.findAll('p')
if not title:
title = self.tag_to_string(paras[0]).strip()
if not title:
raise ValueError('No title found in article')
url = a['href'] url = a['href']
if url.startswith('/'): if url.startswith('/'):
url = 'https://www.nytimes.com' + url url = 'https://www.nytimes.com' + url
desc = '' desc = ''
p = li.find('p') if len(paras) > 0:
if p is not None: desc = self.tag_to_string(paras[-1])
desc = self.tag_to_string(p)
date = '' date = ''
d = date_from_url(url) d = date_from_url(url)
if d is not None: if d is not None:
@ -219,7 +223,7 @@ class NewYorkTimes(BasicNewsRecipe):
continue continue
yield {'title': title, 'url': url, 'description': desc, 'date': date} yield {'title': title, 'url': url, 'description': desc, 'date': date}
continue continue
h2 = article.find('h2') h2 = article.find(['h2', 'h3'])
if h2 is not None: if h2 is not None:
title = self.tag_to_string(h2) title = self.tag_to_string(h2)
a = h2.find('a', href=True) a = h2.find('a', href=True)