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

...

Browse Source
This commit is contained in:
unkn0w7n 2025-03-16 11:40:47 +05:30
parent 26bb850d62
commit cd56b74115
2 changed files with 23 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
recipes/economist_news.recipe
View File

@ -121,7 +121,7 @@ def process_url(url):
class EconomistNews(BasicNewsRecipe):
title = 'The Economist News'
language = 'en'
language = 'en_GB'
encoding = 'utf-8'
masthead_url = 'https://www.livemint.com/lm-img/dev/economist-logo-oneline.png'

25
recipes/economist_search.recipe
View File

@ -12,13 +12,23 @@ from calibre.ebooks.BeautifulSoup import NavigableString, Tag
from calibre.web.feeds.news import BasicNewsRecipe
def process_list(li_node):
li_html = ''
for li in li_node['items']:
if li.get('textHtml'):
li_html += f'<li>{li.get("textHtml")}</li>'
else:
li_html += f'<li>{li.get("text", "")}</li>'
return li_html
def process_node(node):
ntype = node.get('type', '')
if ntype == 'CROSSHEAD':
if node.get('textHtml'):
return f'<h4>{node.get("textHtml")}</h4>'
return f'<h4>{node.get("text", "")}</h4>'
elif ntype == 'PARAGRAPH':
elif ntype in ['PARAGRAPH', 'BOOK_INFO']:
if node.get('textHtml'):
return f'<p>{node.get("textHtml")}</p>'
return f'<p>{node.get("text", "")}</p>'
@ -35,9 +45,15 @@ def process_node(node):
return f'<blockquote>{node.get("text", "")}</blockquote>'
elif ntype == 'DIVIDER':
return '<hr>'
elif ntype == 'INFOGRAPHIC':
if node.get('fallback'):
return process_node(node['fallback'])
elif ntype == 'INFOBOX':
for x in safe_dict(node, 'components'):
return f'<blockquote>{process_node(x)}</blockquote>'
elif ntype == 'UNORDERED_LIST':
if node.get('items'):
return process_list(node)
elif ntype:
print('** ', ntype)
return ''
@ -57,7 +73,10 @@ class JSONHasNoContent(ValueError):
def load_article_from_json(raw):
# open('/t/raw.json', 'w').write(raw)
body = ''
data = json.loads(raw)['props']['pageProps']['cp2Content']
try:
data = json.loads(raw)['props']['pageProps']['cp2Content']
except Exception:
data = json.loads(raw)['props']['pageProps']['content']
body += f'<div style="color: red; font-size:small; font-weight:bold;">{data.get("flyTitle", "")}</div>'
body += f'<h1>{data["headline"]}</h1>'
body += f'<div style="font-style: italic; color:#202020;">{data.get("rubric", "")}</div>'
@ -114,7 +133,7 @@ def process_url(url):
class econ_search(BasicNewsRecipe):
title = 'The Economist - Search'
language = 'en'
language = 'en_GB'
encoding = 'utf-8'
__author__ = 'unkn0wn'
description = (