| 1 |
#!/usr/bin/env python |
| 2 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 3 |
|
| 4 |
''' |
| 5 |
Hamilton Spectator Calibre Recipe |
| 6 |
''' |
| 7 |
|
| 8 |
|
| 9 |
def absurl(url): |
| 10 |
if url.startswith('/'): |
| 11 |
return 'https://www.thespec.com' + url |
| 12 |
|
| 13 |
|
| 14 |
class HamiltonSpectator(BasicNewsRecipe): |
| 15 |
title = 'Hamilton Spectator' |
| 16 |
max_articles_per_feed = 50 |
| 17 |
__author__ = 'unkn0wn' |
| 18 |
publisher = 'thespec.com' |
| 19 |
description = 'Ontario Canada Newspaper' |
| 20 |
category = 'News, Ontario, Canada' |
| 21 |
remove_javascript = True |
| 22 |
use_embedded_content = False |
| 23 |
no_stylesheets = True |
| 24 |
language = 'en_CA' |
| 25 |
encoding = 'utf-8' |
| 26 |
remove_attributes = ['style', 'height', 'width'] |
| 27 |
masthead_url = 'https://bloximages.chicago2.vip.townnews.com/thespec.com/content/tncms/custom/image/c0094646-1108-11ee-8af0-b3954ce40e5e.png' |
| 28 |
|
| 29 |
ignore_duplicate_articles = {'title', 'url'} |
| 30 |
|
| 31 |
extra_css = ''' |
| 32 |
.caption { font-size:small; text-align:center; } |
| 33 |
.authorList, .endnote_contrib { font-size:small; } |
| 34 |
''' |
| 35 |
|
| 36 |
keep_only_tags = [classes('headline asset-summary authorList articleMainArt asset-body')] |
| 37 |
|
| 38 |
remove_tags = [ |
| 39 |
dict(name=['svg', 'button']), |
| 40 |
dict(attrs={'id': ['tncms-region-article_instory_top', 'tncms-region-article_bottom', 'asset-video-primary']}), |
| 41 |
classes( |
| 42 |
'tnt-blurred-image share-container subscriber-offers access-offers-in-page ' |
| 43 |
'access-offers-wrapper tnt-ads-container adLabelWrapperManual shareIcons ' |
| 44 |
'articleFeedbackCTA comments-container card-image' |
| 45 |
), |
| 46 |
] |
| 47 |
|
| 48 |
def preprocess_html(self, soup): |
| 49 |
for img in soup.findAll('img', attrs={'data-srcset': True}): |
| 50 |
for x in img['data-srcset'].split(','): |
| 51 |
if '640w' in x.split(): |
| 52 |
img['src'] = x.split()[0] |
| 53 |
return soup |
| 54 |
|
| 55 |
def parse_index(self): |
| 56 |
index = 'https://www.thespec.com/' |
| 57 |
sections = ['news', 'politics', 'opinion', 'business', 'sports', 'life', 'entertainment'] |
| 58 |
feeds = [] |
| 59 |
soup = self.index_to_soup(index) |
| 60 |
for sec in sections: |
| 61 |
section = sec.capitalize() |
| 62 |
self.log(section) |
| 63 |
articles = [] |
| 64 |
for a in soup.findAll('a', attrs={'href': lambda x: x and x.startswith('/' + sec + '/')}): |
| 65 |
url = absurl(a['href'].split('#')[0]) |
| 66 |
if url in {index + sec + '/', index + sec}: |
| 67 |
continue |
| 68 |
if not url.endswith('.html'): |
| 69 |
continue |
| 70 |
title = self.tag_to_string(a) |
| 71 |
self.log('\t', title, '\n\t\t', url) |
| 72 |
articles.append({'title': title, 'url': url}) |
| 73 |
if articles: |
| 74 |
feeds.append((section, articles)) |
| 75 |
return feeds |