diff --git a/recipes/financial_times.recipe b/recipes/financial_times.recipe
index c8ff6f7e50..a67fbedd5a 100644
--- a/recipes/financial_times.recipe
+++ b/recipes/financial_times.recipe
@@ -16,6 +16,7 @@ class ft(BasicNewsRecipe):
remove_empty_feeds = True
ignore_duplicate_articles = {'url'}
remove_attributes = ['style', 'width', 'height']
+ masthead_url = 'https://im.ft-static.com/m/img/masthead_main.jpg'
def get_cover_url(self):
soup = self.index_to_soup(
@@ -35,7 +36,7 @@ class ft(BasicNewsRecipe):
('Climate', 'https://www.ft.com/climate-capital?format=rss'),
('Opinion', 'https://www.ft.com/opinion?format=rss'),
('Life & Arts', 'https://www.ft.com/life-arts?format=rss'),
- ('how to spend it', 'https://www.ft.com/htsi?format=rss'),
+ ('How to spend it', 'https://www.ft.com/htsi?format=rss'),
]
def preprocess_raw_html(self, raw, *a):
@@ -50,17 +51,25 @@ class ft(BasicNewsRecipe):
title = data['headline']
body = data['articleBody']
body = body.replace('\n\n', '')
- # remove embedded image links
- body = re.sub(r'\[https://\S+?\]', '', body)
author = ''
if 'author' in data:
try:
author = data['author']['name']
except TypeError:
author = ' and '.join(x['name'] for x in data['author'])
- image = desc = ''
+ image = desc = title_image_url = ''
if data.get('image'):
- image = '
'.format(data['image']['url'])
+ title_image_url = data['image']['url']
+ image = '
'.format(title_image_url)
+
+ # embedded image links
+ def insert_image(m):
+ url = m.group()[1:-1]
+ if url == title_image_url:
+ return ''
+ return '
'.format(url)
+
+ body = re.sub(r'\[https://\S+?\]', insert_image, body)
if data.get('description'):
desc = '
' + data['description'] + '
'
html = '' + title + '
' + desc + '' + author + '
' + image + '' + body