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

Update Financial Times Print Edition

Browse Source
This commit is contained in:
Kovid Goyal 2022-08-26 19:31:21 +05:30
parent 5978c9fab7
commit 2a90da87ec
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 20 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
recipes/financial_times_print_edition.recipe
View File

@ -2,6 +2,7 @@ import json
import re import re
from datetime import date from datetime import date
from calibre.web.feeds.news import BasicNewsRecipe, classes from calibre.web.feeds.news import BasicNewsRecipe, classes
from urllib.parse import quote
class ft(BasicNewsRecipe): class ft(BasicNewsRecipe):
@ -71,9 +72,9 @@ class ft(BasicNewsRecipe):
'url': url, 'url': url,
'description': desc 'description': desc
}) })
self.log('\t\t', desc) self.log('\t', desc)
self.log('\t\tFound article:', title) self.log('\t', title)
self.log('\t\t\t', url) self.log('\t\t', url)
if articles: if articles:
feeds.append((secname, articles)) feeds.append((secname, articles))
return feeds return feeds
@ -101,16 +102,26 @@ class ft(BasicNewsRecipe):
author = ' and '.join(x['name'] for x in data['author']) author = ' and '.join(x['name'] for x in data['author'])
image = desc = title_image_url = '' image = desc = title_image_url = ''
if data.get('image'):
title_image_url = data['image']['url']
image = '<p><img src="{}">'.format(title_image_url)
def resize_img(img):
a = 'https://www.ft.com/__origami/service/image/v2/images/raw/'
b = quote(img, safe='')
c = '?dpr=2&fit=scale-down&quality=medium&source=next&width=300'
# use width = 200, 300, 400,.. 700...
return a + b + c
if data.get('image'):
image_url = data['image']['url']
if body.__contains__(image_url) is False:
title_image_url = resize_img(image_url)
image = '<p><img src="{}">'.format(title_image_url)
# embedded image links # embedded image links
def insert_image(m): def insert_image(m):
url = m.group()[1:-1] url = m.group()[1:-1]
if url == title_image_url: if url.__contains__('studio') is False:
return '' url = resize_img(url)
return '<p><img src="{}">'.format(url) return '<p> <img src="{}">'.format(url)
body = re.sub(r'\[https://\S+?\]', insert_image, body) body = re.sub(r'\[https://\S+?\]', insert_image, body)