calibre/recipes/spectator_magazine.recipe
2022-11-18 08:11:22 +05:30

111 lines
4.0 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe, classes
from calibre import browser
def absurl(url):
if url.startswith('/'):
url = 'https://www.spectator.co.uk' + url
return url
class spectator(BasicNewsRecipe):
title = 'Spectator Magazine'
__author__ = 'unkn0wn'
description = 'The Spectator was established in 1828, and is the best-written and most influential weekly in the English language.'
language = 'en'
no_stylesheets = True
remove_attributes = ['height', 'width', 'style']
ignore_duplicate_articles = {'url'}
masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/c/c7/The_Spectator_logo.svg/320px-The_Spectator_logo.svg.png'
encoding = 'utf-8'
remove_empty_feeds = True
resolve_internal_links = True
extra_css = '''
.author-bio {font-size:small;}
#fig-c {text-align:center; font-size:small;}
blockquote, em {color:#404040;}
'''
keep_only_tags = [
classes(
'entry-header__heading entry-header__thumbnail entry-content__wrapper author-bio'),
]
remove_tags = [
classes(
'entry-header__author entry-header__meta entry-meta insert--most-popular '
'subscribe-ribbon subscription-banner paywall__card'
)
]
def preprocess_html(self, soup):
for fc in soup.findAll('figcaption'):
fc['id'] = 'fig-c'
return soup
def parse_index(self):
soup = self.index_to_soup('https://www.spectator.co.uk/magazine')
self.cover_url = soup.find(**classes(
'magazine-header__container')).img['src'].split('?')[0]
issue = self.tag_to_string(soup.find(**classes(
'magazine-header__title'))).strip()
self.timefmt = ' (' + issue + ') [' + self.tag_to_string(soup.find(**classes(
'magazine-header__date'))).strip() + ']'
self.log('Downloading Issue: ', self.timefmt)
nav_div = soup.find('ul', **classes('archive-entry__nav-list'))
section_list = []
for x in nav_div.findAll(['a']):
section_list.append((
self.tag_to_string(x).strip(), absurl(x['href'])))
feeds = []
# For each section title, fetch the article urls
for section in section_list:
section_title = section[0]
section_url = section[1]
self.log(section_title, section_url)
soup = self.index_to_soup(section_url)
articles = self.articles_from_soup(soup)
if articles:
feeds.append((section_title, articles))
return feeds
def articles_from_soup(self, soup):
ans = []
for div in soup.findAll('div', **classes(
'mosaic__tile mosaic__tile--lead-up'
)):
a = div.find('a', href=True, attrs={'class':'article__title-link'})
url = absurl(a['href'])
title = self.tag_to_string(a).strip()
teaser = div.find('p', **classes('article__excerpt-text'))
desc = ''
if teaser:
desc = self.tag_to_string(teaser).strip()
obj = div.find('a', **classes('article__author article__author--link'))
if obj:
desc = self.tag_to_string(obj).strip() + ' | ' + desc
sec = div.findParent('div').find('a', attrs={'class': 'magazine-issue__entry-link'})
if sec:
desc = self.tag_to_string(sec).strip() + ' | ' + desc
self.log('\t', title, '\n\t', desc, '\n\t\t', url)
ans.append({'title': title, 'description':desc, 'url': url})
return ans
# Spectator changes the content it delivers based on cookies, so the
# following ensures that we send no cookies
def get_browser(self, *args, **kwargs):
return self
def clone_browser(self, *args, **kwargs):
return self.get_browser()
def open_novisit(self, *args, **kwargs):
br = browser()
return br.open_novisit(*args, **kwargs)
open = open_novisit