calibre/recipes/private_eye.recipe
2021-10-15 19:37:18 +05:30

50 lines
1.7 KiB
Plaintext

import re
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1359406781(BasicNewsRecipe):
title = u'Private Eye'
publication_type = 'magazine'
description = u'Private Eye is a fortnightly British satirical and current affairs magazine, edited by Ian Hislop'
oldest_article = 13
max_articles_per_feed = 100
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
ignore_duplicate_articles = {'title'}
language = 'en_GB'
encoding = 'utf-8'
__author__ = u'Martyn Pritchard'
__copyright__ = '2020, Martyn Pritchard <MPritchard2k9@gmail.com>'
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup('https://www.private-eye.co.uk')
for citem in soup.findAll('img'):
if citem['src'].endswith('big.jpg'):
return citem['src']
return cover_url
remove_tags_before = {'class': "article"}
remove_tags_after = {'class': "article"}
remove_tags = [dict(name='div', attrs={'id': 'sections-sidebar'})]
remove_tags = {'class': "sub-nav-bar"}
remove_tags = [dict(name='a', attrs={'class': 'twitter-share-button'})]
remove_tags = [dict(name='div', attrs={'id': 'nav-box-sections-mobile'})]
preprocess_regexps = [
(
re.compile(
r'<a href="https://www.subscription.*?</a>',
re.DOTALL | re.IGNORECASE
), lambda match: ''
),
(
re.compile(
r'<a class="twitter-share-button.*?</a>', re.DOTALL | re.IGNORECASE
), lambda match: ''
),
]
feeds = [(u'http://bodybuilder3d.eu5.org/PrivateEyeStat.xml')]