mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
80 lines
2.7 KiB
Python
80 lines
2.7 KiB
Python
#!/usr/bin/env python
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
'''
|
|
Hamilton Spectator Calibre Recipe
|
|
'''
|
|
|
|
def absurl(url):
|
|
if url.startswith('/'):
|
|
return 'https://www.thespec.com' + url
|
|
|
|
class HamiltonSpectator(BasicNewsRecipe):
|
|
title = u'Hamilton Spectator'
|
|
max_articles_per_feed = 50
|
|
__author__ = u'unkn0wn'
|
|
publisher = u'thespec.com'
|
|
description = u'Ontario Canada Newspaper'
|
|
category = u'News, Ontario, Canada'
|
|
remove_javascript = True
|
|
use_embedded_content = False
|
|
no_stylesheets = True
|
|
language = 'en_CA'
|
|
encoding = 'utf-8'
|
|
remove_attributes = ['style', 'height', 'width']
|
|
masthead_url = 'https://bloximages.chicago2.vip.townnews.com/thespec.com/content/tncms/custom/image/c0094646-1108-11ee-8af0-b3954ce40e5e.png'
|
|
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
|
|
extra_css = '''
|
|
.caption { font-size:small; text-align:center; }
|
|
.authorList, .endnote_contrib { font-size:small; }
|
|
'''
|
|
|
|
keep_only_tags = [
|
|
classes(
|
|
'headline asset-summary authorList articleMainArt asset-body'
|
|
)
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name=['svg', 'button']),
|
|
dict(attrs={'id':['tncms-region-article_instory_top', 'tncms-region-article_bottom', 'asset-video-primary']}),
|
|
classes(
|
|
'tnt-blurred-image share-container subscriber-offers access-offers-in-page '
|
|
'access-offers-wrapper tnt-ads-container adLabelWrapperManual shareIcons '
|
|
'articleFeedbackCTA comments-container card-image'
|
|
)
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'data-srcset':True}):
|
|
for x in img['data-srcset'].split(','):
|
|
if '640w' in x.split():
|
|
img['src'] = x.split()[0]
|
|
return soup
|
|
|
|
def parse_index(self):
|
|
index = 'https://www.thespec.com/'
|
|
sections = [
|
|
'news', 'politics', 'opinion', 'business', 'sports', 'life', 'entertainment'
|
|
]
|
|
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 not url.endswith('.html'):
|
|
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
|