Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Scientific American

Browse Source
This commit is contained in:
Kovid Goyal 2022-06-02 13:00:37 +05:30
parent 8f30c16e98
commit fc1a064525
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 8 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
recipes/scientific_american.recipe
View File

@ -1,7 +1,7 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe, classes
from css_selectors import Select
@ -11,11 +11,6 @@ def absurl(url):
return url
keep_classes = {'article-header', 'article-content',
'article-media', 'article-author', 'article-text'}
remove_classes = {'aside-banner', 'moreToExplore', 'article-footer'}
class ScientificAmerican(BasicNewsRecipe):
title = u'Scientific American'
description = u'Popular Science. Monthly magazine. Should be downloaded around the middle of each month.'
@ -31,12 +26,12 @@ class ScientificAmerican(BasicNewsRecipe):
needs_subscription = 'optional'
keep_only_tags = [
dict(attrs={'class': lambda x: x and bool(
set(x.split()).intersection(keep_classes))}),
classes(
'article-header article-content article-media article-author article-text feature-article--header'
' feature-article--header-title opinion-article__header-title author-bio'),
]
remove_tags = [
dict(attrs={'class': lambda x: x and bool(
set(x.split()).intersection(remove_classes))}),
classes('aside-banner moreToExplore article-footer flex-column--25 article-author__suggested'),
dict(id=['seeAlsoLinks']),
]
@ -55,12 +50,14 @@ class ScientificAmerican(BasicNewsRecipe):
root = self.index_to_soup(
'https://www.scientificamerican.com/sciammag/', as_tree=True)
select = Select(root)
self.cover_url = [x.get('src', '') for x in select('main .store-listing__img img')][0]
url = [x.get('href', '') for x in select('main .store-listing__img a')][0]
url = absurl(url)
self.cover_url = [x.get('src', '') for x in select('main .store-listing__img img')][0]
# Now parse the actual issue to get the list of articles
select = Select(self.index_to_soup(url, as_tree=True))
self.cover_url = [x.get('src', '') for x in select('main .product-detail__image img')][0].split('?')[0]
self.cover_url += '?w=800'
feeds = []
for i, section in enumerate(select('#sa_body .toc-articles')):
if i == 0: