mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
85 lines
3.0 KiB
Python
85 lines
3.0 KiB
Python
#!/usr/bin/env python
|
|
from datetime import date
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
def absurl(url):
|
|
if url.startswith('/'):
|
|
return 'https://www.afr.com' + url
|
|
|
|
class afr(BasicNewsRecipe):
|
|
title = 'Australian Financial Review'
|
|
__author__ = 'unkn0wn'
|
|
description = (
|
|
'For more than 65 years The Australian Financial Review has been the authority on business,'
|
|
' finance and investment news in Australia. It has a reputation for independent, award-winning '
|
|
'journalism and is essential reading for Australia\'s business and investor community.'
|
|
)
|
|
masthead_url = 'https://www.nineforbrands.com.au/wp-content/uploads/2020/08/AFR-DHOSP-Logo-black-RGB.png'
|
|
encoding = 'utf-8'
|
|
language = 'en_AU'
|
|
|
|
use_embedded_content = False
|
|
timefmt = ' [%d %b %Y]'
|
|
max_articles_per_feed = 25
|
|
no_stylesheets = True
|
|
remove_empty_feeds = True
|
|
remove_attributes = ['style', 'height', 'width']
|
|
|
|
keep_only_tags = [
|
|
dict(name=['article', 'main'], attrs={'id':'content'})
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(attrs={'data-testid': [
|
|
'ArticleTools', 'ArticleBreadcrumb-Links', 'ad-wrapper', 'ArticleFooter', 'ArticleTags',
|
|
'beyondwords-player-wrapper'
|
|
]}),
|
|
dict(name=['button', 'aside', 'svg']),
|
|
]
|
|
|
|
remove_tags_after= [ dict(name='aside', attrs={'id':'stickyContainer'})]
|
|
|
|
extra_css = '''
|
|
#img-cap {font-size:small; text-align:center;}
|
|
[data-testid="AuthorNames"], [data-testid="ArticleTimestamp"] {font-size:small;}
|
|
'''
|
|
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
resolve_internal_links = True
|
|
remove_empty_feeds = True
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'data-src':True}):
|
|
img['src'] = img['data-src']
|
|
for fig in soup.findAll('figcaption'):
|
|
fig['id'] = 'img-cap'
|
|
return soup
|
|
|
|
def parse_index(self):
|
|
index = 'https://www.afr.com/'
|
|
sections = [
|
|
'companies', 'market', 'politics', 'policy', 'world', 'wealth', 'street-talk',
|
|
'chaticleer', 'rear-window', 'life-and-luxury', 'technology', 'property',
|
|
'work-and-careers',
|
|
]
|
|
feeds = []
|
|
soup = self.index_to_soup(index)
|
|
for sec in sections:
|
|
section = sec.capitalize()
|
|
self.log(section)
|
|
articles = []
|
|
for a in soup.findAll('a', attrs={'href':lambda x: x and x.startswith('/' + sec + '/')}):
|
|
url = absurl(a['href'].split('?')[0])
|
|
if url in {index + sec + '/', index + sec}:
|
|
continue
|
|
if date.today().strftime('%Y') not in url:
|
|
continue
|
|
title = self.tag_to_string(a)
|
|
self.log('\t', title, '\n\t\t', url)
|
|
articles.append({'title': title, 'url': url})
|
|
if articles:
|
|
feeds.append((section, articles))
|
|
return feeds
|