| 1 |
#!/usr/bin/env python |
| 2 |
from datetime import date |
| 3 |
|
| 4 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 5 |
|
| 6 |
|
| 7 |
def absurl(url): |
| 8 |
if url.startswith('/'): |
| 9 |
return 'https://www.afr.com' + url |
| 10 |
|
| 11 |
|
| 12 |
class afr(BasicNewsRecipe): |
| 13 |
title = 'Australian Financial Review' |
| 14 |
__author__ = 'unkn0wn' |
| 15 |
description = ( |
| 16 |
'For more than 65 years The Australian Financial Review has been the authority on business,' |
| 17 |
' finance and investment news in Australia. It has a reputation for independent, award-winning ' |
| 18 |
"journalism and is essential reading for Australia's business and investor community." |
| 19 |
) |
| 20 |
masthead_url = 'https://www.nineforbrands.com.au/wp-content/uploads/2020/08/AFR-DHOSP-Logo-black-RGB.png' |
| 21 |
encoding = 'utf-8' |
| 22 |
language = 'en_AU' |
| 23 |
|
| 24 |
use_embedded_content = False |
| 25 |
timefmt = ' [%d %b %Y]' |
| 26 |
max_articles_per_feed = 25 |
| 27 |
no_stylesheets = True |
| 28 |
remove_attributes = ['style', 'height', 'width'] |
| 29 |
|
| 30 |
keep_only_tags = [dict(name=['article', 'main'], attrs={'id': 'content'})] |
| 31 |
|
| 32 |
remove_tags = [ |
| 33 |
dict(attrs={'data-testid': ['ArticleTools', 'ArticleBreadcrumb-Links', 'ad-wrapper', 'ArticleFooter', 'ArticleTags', 'beyondwords-player-wrapper']}), |
| 34 |
dict(name=['button', 'aside', 'svg']), |
| 35 |
] |
| 36 |
|
| 37 |
remove_tags_after = [dict(name='aside', attrs={'id': 'stickyContainer'})] |
| 38 |
|
| 39 |
extra_css = ''' |
| 40 |
#img-cap {font-size:small; text-align:center;} |
| 41 |
[data-testid="AuthorNames"], [data-testid="ArticleTimestamp"] {font-size:small;} |
| 42 |
''' |
| 43 |
|
| 44 |
ignore_duplicate_articles = {'title', 'url'} |
| 45 |
resolve_internal_links = True |
| 46 |
remove_empty_feeds = True |
| 47 |
|
| 48 |
def preprocess_html(self, soup): |
| 49 |
for img in soup.findAll('img', attrs={'data-src': True}): |
| 50 |
img['src'] = img['data-src'] |
| 51 |
for fig in soup.findAll('figcaption'): |
| 52 |
fig['id'] = 'img-cap' |
| 53 |
return soup |
| 54 |
|
| 55 |
def parse_index(self): |
| 56 |
index = 'https://www.afr.com/' |
| 57 |
sections = [ |
| 58 |
'companies', |
| 59 |
'market', |
| 60 |
'politics', |
| 61 |
'policy', |
| 62 |
'world', |
| 63 |
'wealth', |
| 64 |
'street-talk', |
| 65 |
'chaticleer', |
| 66 |
'rear-window', |
| 67 |
'life-and-luxury', |
| 68 |
'technology', |
| 69 |
'property', |
| 70 |
'work-and-careers', |
| 71 |
] |
| 72 |
feeds = [] |
| 73 |
soup = self.index_to_soup(index) |
| 74 |
for sec in sections: |
| 75 |
section = sec.capitalize() |
| 76 |
self.log(section) |
| 77 |
articles = [] |
| 78 |
for a in soup.findAll('a', attrs={'href': lambda x: x and x.startswith('/' + sec + '/')}): |
| 79 |
url = absurl(a['href'].split('?')[0]) |
| 80 |
if url in {index + sec + '/', index + sec}: |
| 81 |
continue |
| 82 |
if date.today().strftime('%Y') not in url: |
| 83 |
continue |
| 84 |
title = self.tag_to_string(a) |
| 85 |
self.log('\t', title, '\n\t\t', url) |
| 86 |
articles.append({'title': title, 'url': url}) |
| 87 |
if articles: |
| 88 |
feeds.append((section, articles)) |
| 89 |
return feeds |