| 1 |
#!/usr/bin/env python |
| 2 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 3 |
|
| 4 |
|
| 5 |
def classes(classes): |
| 6 |
q = frozenset(classes.split(' ')) |
| 7 |
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) |
| 8 |
|
| 9 |
|
| 10 |
class NewZealandHerald(BasicNewsRecipe): |
| 11 |
title = 'New Zealand Herald' |
| 12 |
__author__ = 'unkn0wn' |
| 13 |
description = 'Daily news' |
| 14 |
timefmt = ' [%d %b, %Y]' |
| 15 |
language = 'en_NZ' |
| 16 |
oldest_article = 1 |
| 17 |
remove_attributes = ['style', 'height', 'width'] |
| 18 |
use_embedded_content = False |
| 19 |
encoding = 'utf-8' |
| 20 |
ignore_duplicate_articles = {'url'} |
| 21 |
no_stylesheets = True |
| 22 |
resolve_internal_links = True |
| 23 |
remove_empty_feeds = True |
| 24 |
|
| 25 |
def get_cover_url(self): |
| 26 |
soup = self.index_to_soup('https://www.frontpages.com/new-zealand-newspapers/') |
| 27 |
for img in soup.findAll('img', src=True): |
| 28 |
if 'new-zealand-herald' in img['src']: |
| 29 |
return 'https://www.frontpages.com' + img['src'] |
| 30 |
|
| 31 |
extra_css = ''' |
| 32 |
[data-test-ui="author--text--body"], .article-media__caption {font-size: small;} |
| 33 |
''' |
| 34 |
|
| 35 |
keep_only_tags = [ |
| 36 |
dict( |
| 37 |
attrs={ |
| 38 |
'data-test-ui': [ |
| 39 |
'article__heading', |
| 40 |
'author--text--body', |
| 41 |
'article-top-body', |
| 42 |
'article-bottom-body', |
| 43 |
] |
| 44 |
} |
| 45 |
), |
| 46 |
] |
| 47 |
|
| 48 |
remove_tags = [classes('related-articles article__ad-wrapper article__action-bar')] |
| 49 |
|
| 50 |
feeds = [ |
| 51 |
('Business', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000003.xml'), |
| 52 |
('World', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000002.xml'), |
| 53 |
('National', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000001.xml'), |
| 54 |
('Entertainment', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_001501119.xml'), |
| 55 |
('Travel', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000007.xml'), |
| 56 |
('Opinion', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000466.xml'), |
| 57 |
('Life & Style', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000006.xml'), |
| 58 |
('Technology', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000005.xml'), |
| 59 |
('Sport', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000004.xml'), |
| 60 |
('Motoring', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000009.xml'), |
| 61 |
('Property', 'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000008.xml'), |
| 62 |
] |
| 63 |
|
| 64 |
def preprocess_html(self, soup, *a): |
| 65 |
for img in soup.findAll('img', attrs={'data-srcset': True}): |
| 66 |
for x in img['data-srcset'].split(','): |
| 67 |
if '768w' in x: |
| 68 |
img['src'] = x.split()[0] |
| 69 |
break |
| 70 |
else: |
| 71 |
img['src'] = img['data-srcset'].split(',')[-1].split()[0] |
| 72 |
return soup |