Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update The New Zealand Herald

Browse Source
This commit is contained in:
Kovid Goyal 2018-09-29 10:32:33 +05:30
parent f38c453eaf
commit 6b69b78ead
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 19 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
recipes/nzherald.recipe
View File

@ -1,5 +1,10 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
import re
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class NewZealandHerald(BasicNewsRecipe):
@ -11,6 +16,15 @@ class NewZealandHerald(BasicNewsRecipe):
language = 'en_NZ'
oldest_article = 2.5
keep_only_tags = [
classes('article-header'),
dict(id='article-content'),
]
remove_tags = [
classes('ad-container pb-f-video-video-player pb-f-article-related-articles social-shares')
]
feeds = [
('Business',
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000003.xml'),
@ -36,8 +50,7 @@ class NewZealandHerald(BasicNewsRecipe):
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000008.xml'),
]
def print_version(self, url):
m = re.search(r'objectid=(\d+)', url)
if m is None:
return url
return 'http://www.nzherald.co.nz/news/print.cfm?pnum=1&objectid=' + m.group(1)
def preprocess_html(self, soup, *a):
for img in soup.findAll('img', attrs={'data-srcset': True}):
img['src'] = img['data-srcset'].split()[0]
return soup