mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-11-23 06:53:02 -05:00
98 lines
3.5 KiB
Python
98 lines
3.5 KiB
Python
'''
|
|
www.theweek.com
|
|
'''
|
|
from urllib.parse import quote
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
class TheWeek(BasicNewsRecipe):
|
|
title = 'The Week'
|
|
__author__ = 'unkn0wn'
|
|
description = (
|
|
'The Week is for readers who want to know what\'s going on in the world, without having to read '
|
|
'several daily newspapers or get wrapped up in the endless news cycle. For every important story, '
|
|
'our editors carefully select commentary from all sides of the debate and artfully stitch them together '
|
|
'into one concise read. By showing you every perspective, we enable you to form your own opinion.'
|
|
)
|
|
language = 'en_GB'
|
|
encoding = 'utf-8'
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
remove_attributes = ['width', 'height', 'style']
|
|
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
remove_empty_feeds = True
|
|
resolve_internal_links = True
|
|
simultaneous_downloads = 1
|
|
oldest_article = 7 # days
|
|
web_url = ''
|
|
|
|
extra_css = '''
|
|
img {display:block; margin:0 auto;}
|
|
.caption__text--hero, .credit { font-size:small; text-align:center; }
|
|
.header__strapline, em, i { color:#202020; }
|
|
.article-type__breadcrumb { color:grey; }
|
|
.author-byline__author-text {font-size:small; }
|
|
'''
|
|
|
|
def get_cover_url(self):
|
|
import json
|
|
url = 'https://ukmagazine.theweek.com/timelines.json'
|
|
data = json.loads(self.index_to_soup(url, raw=True))
|
|
for x in data['timelines'][:5]:
|
|
if 'image' in x:
|
|
if '-cover-' in x['image']:
|
|
return 'https://ukmagazine.theweek.com' + x['image'][1:]
|
|
|
|
articles_are_obfuscated = True
|
|
|
|
def get_obfuscated_article(self, url):
|
|
br = self.get_browser()
|
|
soup = self.index_to_soup(url)
|
|
link = soup.a['href']
|
|
skip_sections =[ # add sections you want to skip
|
|
'/video/', '/videos/', '/multimedia/',
|
|
]
|
|
if any(x in link for x in skip_sections):
|
|
self.abort_article('skipping video links ', link)
|
|
self.web_url = link
|
|
html = br.open(link).read()
|
|
return ({ 'data': html, 'url': link })
|
|
|
|
keep_only_tags = [
|
|
classes('article-type__breadcrumb header__title header__strapline image image--hero author-byline__author-text article__body')
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name=['aside', 'source']),
|
|
classes(
|
|
'blueconic-article__wrapper ad-unit van_vid_carousel tag-links'
|
|
)
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'data-pin-media':True}):
|
|
img['src'] = img['data-pin-media'].replace('.jpg', '-768-80.jpg')
|
|
return soup
|
|
|
|
feeds = []
|
|
when = oldest_article*24
|
|
index = 'https://theweek.com/'
|
|
sections = [
|
|
'politics', 'news', 'cartoons', 'tech', 'science', 'health',
|
|
'culture-life', 'business', 'travel', 'arts-life', 'history'
|
|
]
|
|
for sec in sections:
|
|
a = 'https://news.google.com/rss/search?q=when:{}h+allinurl:{}&hl=en-GB&gl=GB&ceid=GB:en'
|
|
feeds.append((sec.capitalize(), a.format(when, quote(index + sec, safe=''))))
|
|
feeds.append(('Others', a.format(when, quote(index, safe=''))))
|
|
|
|
def populate_article_metadata(self, article, soup, first):
|
|
article.title = article.title.replace(' - The Week', '')
|
|
desc = soup.find(**classes('header__strapline'))
|
|
if desc:
|
|
article.summary = self.tag_to_string(desc)
|
|
article.text_summary = article.summary
|
|
article.url = self.web_url
|