Cleanup previous PR

This commit is contained in:
Kovid Goyal
2026-03-24 21:22:30 +05:30
parent 1424c17944
commit 404ee855f1
+18 -14
View File
@@ -16,16 +16,20 @@ def absurl(url):
class BusinessLine(BasicNewsRecipe):
title = 'BusinessLine Print Edition'
__author__ = 'improved'
description = "BusinessLine ePaper (The Hindu Group)"
title = 'The Hindu BusinessLine'
__author__ = 'unkn0wn, Hardik Gupta'
description = (
'The Hindu BusinessLine is known for its credibility, accuracy, in-depth analysis of markets and sober coverage'
' of business news. BusinessLine reduces the daily grind of business to relevant, readable, byte-sized stories.'
' The newspaper is extensively followed by the decision makers and change leaders from the world of business.'
)
def get_cover_url(self):
soup = self.index_to_soup(
'https://www.magzter.com/IN/THG-publishing-pvt-ltd/The-Hindu-Business-Line/Newspaper/'
)
return soup.find('img', id=lambda s: s and 'mgd__lhd__cover' in s.split())['src']
language = 'en_IN'
no_stylesheets = True
@@ -103,7 +107,7 @@ class BusinessLine(BasicNewsRecipe):
if src:
img['src'] = absurl(src)
# -------------------------
# -------------------------
# Fix article images + captions
# -------------------------
for pic in soup.find_all('div', class_='article-picture'):
@@ -119,12 +123,12 @@ class BusinessLine(BasicNewsRecipe):
cap = pic.find('p', class_='caption')
if cap:
caption = cap.get_text(" ", strip=True)
caption = cap.get_text(' ', strip=True)
if not caption:
nxt = pic.find_next_sibling()
if nxt and nxt.name == 'p' and 'caption' in (nxt.get('class') or []):
caption = nxt.get_text(" ", strip=True)
caption = nxt.get_text(' ', strip=True)
nxt.decompose()
if caption:
@@ -155,11 +159,11 @@ class BusinessLine(BasicNewsRecipe):
# -------------------------
# Build clean article
# -------------------------
# 1. Rebuild the header in its original location
if header:
new_header = soup.new_tag('div')
new_header['class'] = 'clean-header' # Optional wrapper
new_header['class'] = 'clean-header' # Optional wrapper
if title:
h1_tag = soup.new_tag('h1')
@@ -190,17 +194,17 @@ class BusinessLine(BasicNewsRecipe):
local_edition = 'bl_chennai'
loc = self.recipe_specific_options.get('location')
# CLI Fallback: If it's still the schema dictionary, extract the default value
if isinstance(loc, dict):
loc = loc.get('default', 'chennai')
if loc:
local_edition = 'bl_' + loc
dt = date.today()
past = self.recipe_specific_options.get('date')
# CLI Fallback: Extract default if it's the schema dictionary (returns None if undefined)
if isinstance(past, dict):
past = past.get('default')
@@ -262,4 +266,4 @@ class BusinessLine(BasicNewsRecipe):
return list(feeds_dict.items())
return []
return []