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

Merge branch 'master' of https://github.com/unkn0w7n/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2023-12-06 16:35:04 +05:30
commit 60e3be881f
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
recipes/economist.recipe
View File

@ -126,6 +126,7 @@ class Economist(BasicNewsRecipe):
title = 'The Economist'
language = 'en'
encoding = 'utf-8'
masthead_url = 'https://www.livemint.com/lm-img/dev/economist-logo-oneline.png'
__author__ = "Kovid Goyal"
description = (
@ -156,6 +157,7 @@ class Economist(BasicNewsRecipe):
font-size: smaller;
color: red;
}
img {display:block; margin:0 auto;}
'''
oldest_article = 7.0
resolve_internal_links = True
@ -251,6 +253,11 @@ class Economist(BasicNewsRecipe):
x.text = x.text.upper()
x.tag = 'span'
x.set('style', 'font-variant: small-caps')
for x in root.xpath('//figcaption'):
x.set('style', 'text-align:center; font-size:small;')
for x in root.xpath('//cite'):
x.tag = 'blockquote'
x.set('style', 'color:#404040;')
raw = etree.tostring(root, encoding='unicode')
return raw
@ -295,6 +302,8 @@ class Economist(BasicNewsRecipe):
if script_tag is not None:
data = json.loads(script_tag.string)
# open('/t/raw.json', 'w').write(json.dumps(data, indent=2, sort_keys=True))
self.title = 'The Economist | ' + safe_dict(data, "props", "pageProps", "content", "image", "main", "headline")
self.timefmt = ' [' + safe_dict(data, "props", "pageProps", "content", "datePublishedString") + ']'
self.cover_url = safe_dict(data, "props", "pageProps", "content", "image", "main", "url", "canonical")
self.log('Got cover:', self.cover_url)

6
recipes/scientific_american.recipe
View File

@ -44,6 +44,12 @@ class ScientificAmerican(BasicNewsRecipe):
dict(name=['button', 'svg', 'iframe', 'source'])
]
def preprocess_html(self, soup):
for fig in soup.findAll('figcaption'):
for p in fig.findAll('p'):
p.name = 'span'
return soup
def get_browser(self, *args):
br = BasicNewsRecipe.get_browser(self)
if self.username and self.password: