Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2026-04-29 12:10:44 -04:00
Code Issues Packages Projects Releases Wiki Activity

Improve parsing by looking for other HTML tags

Browse Source
This commit is contained in:
Henrik Holm 2025-11-08 23:40:17 +01:00
parent e78b5271f8
commit dbf5dc7e69
No known key found for this signature in database
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
recipes/fokus.recipe
View File

@ -45,7 +45,8 @@ class Fokus(BasicNewsRecipe):
dict(name='p', class_='article-metadata'), # Dynamically created by the recipe.
dict(name='figure', class_='Single__thumbnail'), # Image of "Single" type articles.
dict(name='figure', class_='Longread__thumbnail'), # Image of "Longread" type articles.
dict(name='div', class_='sesamy-protected-content'), # Article body.
dict(name='div', class_='Single__content'), # Article body of "Single" type articles.
dict(name='div', class_='Longread__content'), # Article body of "Longread" type articles.
]
def extract_cover_url(self, a_tag) -> str:
@ -230,7 +231,7 @@ class Fokus(BasicNewsRecipe):
'''
self.log(f'Assigning each of the {len(articles)} articles to a section...')
section_to_articles = {}
for article_url, article_dict in articles.items():
for _, article_dict in articles.items():
section_title = article_dict['category']
if section_title not in section_to_articles:
section_to_articles[section_title] = []