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 Hindu Business Line Print Edition

Browse Source
This commit is contained in:
Kovid Goyal 2022-12-12 16:22:18 +05:30
parent fd6a222665
commit de77bfa3be
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 14 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
recipes/hindu_business_line_print_edition.recipe
View File

@ -1,6 +1,7 @@
import json import json
import re import re
from collections import defaultdict from collections import defaultdict
from datetime import date
from calibre.web.feeds.news import BasicNewsRecipe, classes from calibre.web.feeds.news import BasicNewsRecipe, classes
@ -10,6 +11,10 @@ def absurl(url):
return url return url
local_edition = None
# Chennai is default edition, for other editions use 'bl_hyderabad', 'bl_bangalore', 'bl_mumbai'
class BusinessLine(BasicNewsRecipe): class BusinessLine(BasicNewsRecipe):
title = 'The Hindu BusinessLine | Print Edition' title = 'The Hindu BusinessLine | Print Edition'
__author__ = 'unkn0wn' __author__ = 'unkn0wn'
@ -24,7 +29,8 @@ class BusinessLine(BasicNewsRecipe):
remove_attributes = ['style', 'height', 'width'] remove_attributes = ['style', 'height', 'width']
extra_css = '.caption{font-size:small; text-align:center;}'\ extra_css = '.caption{font-size:small; text-align:center;}'\
'.author{font-size:small; font-weight:bold;}'\ '.author{font-size:small; font-weight:bold;}'\
'.subhead{font-weight:bold;}' '.subhead, .subhead_lead {font-weight:bold;}'\
'img {display:block; margin:0 auto;}'
ignore_duplicate_articles = {'url'} ignore_duplicate_articles = {'url'}
@ -43,14 +49,14 @@ class BusinessLine(BasicNewsRecipe):
img['src'] = img['data-original'] img['src'] = img['data-original']
return soup return soup
def populate_article_metadata(self, article, soup, first):
if first and hasattr(self, 'add_toc_thumbnail'):
image = soup.find('img')
if image is not None:
self.add_toc_thumbnail(article, image['src'])
def parse_index(self): def parse_index(self):
url = 'https://www.thehindubusinessline.com/todays-paper/' if local_edition:
yr = str(date.today().year)
mn = date.today().strftime('%m')
dy = date.today().strftime('%d')
url = absurl('/todays-paper/' + yr + '-' + mn + '-' + dy + '/' + local_edition + '/')
else:
url = 'https://www.thehindubusinessline.com/todays-paper/'
raw = self.index_to_soup(url, raw=True) raw = self.index_to_soup(url, raw=True)
soup = self.index_to_soup(raw) soup = self.index_to_soup(raw)
ans = self.hindu_parse_index(soup) ans = self.hindu_parse_index(soup)