calibre/recipes/strange_horizons.recipe
2024-03-30 13:03:29 +05:30

69 lines
2.6 KiB
Python

import re
from collections import defaultdict
from calibre.web.feeds.news import BasicNewsRecipe, classes
class StrangeHorizons(BasicNewsRecipe):
title = 'Strange Horizons'
description = 'A magazine of speculative fiction and related nonfiction. Best downloaded on weekends'
__author__ = 'unkn0wn'
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = 'en'
remove_attributes = ['style', 'height', 'width']
masthead_url = 'http://strangehorizons.com/wordpress/wp-content/themes/strangehorizons/images/sh-logo.jpg'
extra_css = '''
.author-biographies, .content-warning-container-ltr, .category {font-size:small; font-style:italic; font-color:#404040;}
.byline {font-size:small; font-color:#202020;}
.title {font-size:large; text-align:center;}
'''
ignore_duplicate_articles = {'url'}
keep_only_tags = [
classes('post-container')
]
remove_tags = [
dict(name = 'button'),
classes('font-size sharedaddy comments-form-row')
]
def parse_index(self):
main = self.index_to_soup('http://strangehorizons.com/issue/')
issue = main.find(attrs={'class':lambda x: x and 'current-issue-widget' in x.split()})
current = issue.find('a', href=lambda x: x and x.startswith('http://strangehorizons.com/issue/'))
date = issue.find(**classes('date'))
self.timefmt = ' [' + self.tag_to_string(date) + ']'
self.log('Downloading Issue:', self.timefmt, current['href'])
soup = self.index_to_soup(current['href'])
feeds_dict = defaultdict(list)
for art in soup.findAll('div', attrs={'class':'article'}):
for ti in art.findAll(**classes('title')):
if a := ti.find('a', href=True):
url = a['href']
title = self.tag_to_string(ti).strip()
sec = 'Articles'
if cat := art.find(**classes('category')):
sec = self.tag_to_string(cat).strip()
desc = ''
if exp := ti.find_next_sibling(**classes('excerpt')):
desc = self.tag_to_string(exp) + desc
desc = re.sub(r"\d{5} ", "", desc)
if auth := ti.find_next_sibling(**classes('author')):
desc = self.tag_to_string(auth) + ' | ' + desc
if not title or not url:
continue
self.log(sec, '\n\t', title, '\n\t', desc, '\n\t\t', url)
feeds_dict[sec].append({"title": title, "url": url, "description": desc})
return [(section, articles) for section, articles in feeds_dict.items()]