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

Wrap extraction of cover URL in try/except

Browse Source
This commit is contained in:
Henrik Holm 2025-06-22 14:52:13 +02:00
parent 07b5c98fd0
commit 5dcb777e4f
No known key found for this signature in database
1 changed files with 13 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
recipes/fokus.recipe
View File

@ -53,18 +53,21 @@ class Fokus(BasicNewsRecipe):
figure_tag = a_tag.find('figure')
img_tag = figure_tag.find('img')
# The `srcset` attribute contains a comma-separated list of URLs and their resolutions.
cover_urls = img_tag['srcset'].split(', ')
cover_urls = [src.split(' ') for src in cover_urls]
try:
# The `srcset` attribute contains a comma-separated list of URLs and their resolutions.
cover_urls = img_tag['srcset'].split(', ')
cover_urls = [src.split(' ') for src in cover_urls]
# The second item of each tuple should be the resolution, e.g., '578w' or '821w'. Remove the 'w' suffix, cast
# to an integer and sort in descending order.
cover_urls = [(url, int(resolution[:-1])) for url, resolution in cover_urls]
cover_urls = sorted(cover_urls, key=lambda x: x[1], reverse=True)
# The second item of each tuple should be the resolution, e.g., '578w' or '821w'. Remove the 'w' suffix, cast
# to an integer and sort in descending order.
cover_urls = [(url, int(resolution[:-1])) for url, resolution in cover_urls]
cover_urls = sorted(cover_urls, key=lambda x: x[1], reverse=True)
# The first item of the sorted list is now the URL of the highest-resolution image.
self.cover_url = cover_urls[0][0]
self.log(f"Identified cover URL: '{self.cover_url}'")
# The first item of the sorted list is now the URL of the highest-resolution image.
self.cover_url = cover_urls[0][0]
self.log(f"Identified cover URL: '{self.cover_url}'")
except (KeyError, ValueError) as exc:
self.log.error(f'Failed to extract cover URL! Has the website format changed?\n{exc}')
return