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 Fortune Magazine

Browse Source
This commit is contained in:
Kovid Goyal 2020-09-04 22:07:25 +05:30
parent 9f12a097cc
commit 5059025a18
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 6 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
recipes/fortune_magazine.recipe
View File

@ -30,9 +30,7 @@ class Fortune(BasicNewsRecipe):
category = 'news'
encoding = 'UTF-8'
keep_only_tags = [
prefix_classes('articleHeader__title-- centerAligned__meta-- featuredMedia__imageWrapper-- articleBody__wrapper--'),
classes('lead-media longform-bylines longform-timestamps author'),
dict(id=['article-body', 'longform-body']),
classes('amp-wp-title amp-wp-dek amp-header-meta amp-wp-article-featured-image amp-wp-article-content'),
]
no_javascript = True
@ -50,11 +48,8 @@ class Fortune(BasicNewsRecipe):
return br
def preprocess_html(self, soup, *a):
for div in soup.findAll(attrs={'class': lambda x: x and 'lazy-image' in x.split()}):
a = div.find('a', href=True)
if a is not None:
a.name = 'img'
a['src'] = a['href']
for ai in soup.findAll(name='amp-img'):
ai.name = 'img'
return soup
def parse_index(self):
@ -66,9 +61,11 @@ class Fortune(BasicNewsRecipe):
for li in soup.findAll('li', attrs={'class': lambda x: x and 'termArchiveContentList__item--' in x}):
a = li.find('a', href=True)
url = a['href']
url = a['href'].rstrip('/') + '/amp'
div = li.find(attrs={'class': lambda x: x and 'termArchiveContentListItem__title--' in x})
title = self.tag_to_string(div)
if title.startswith('Magazine'):
title = title[len('Magazine'):]
desc = ''
div = li.find(attrs={'class': lambda x: x and 'termArchiveContentListItem__excerpt--' in x})
if div is not None: