Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update strange_horizons.recipe

Browse Source
This commit is contained in:
unkn0w7n 2025-02-14 09:43:00 +05:30
parent 417c05ea41
commit 539e87ec28
1 changed files with 34 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

80
recipes/strange_horizons.recipe
View File

@ -1,12 +1,15 @@
import re
from collections import defaultdict
#!/usr/bin/env python
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'
description = (
'Strange Horizons is a weekly magazine of and about speculative fiction. '
'We publish fiction, poetry, reviews, essays, interviews, roundtable '
'discussions, and art.'
)
__author__ = 'unkn0wn'
no_stylesheets = True
use_embedded_content = False
@ -14,55 +17,40 @@ class StrangeHorizons(BasicNewsRecipe):
language = 'en'
remove_attributes = ['style', 'height', 'width']
masthead_url = 'http://strangehorizons.com/wordpress/wp-content/themes/strangehorizons/images/sh-logo.jpg'
ignore_duplicate_articles = {'url'}
resolve_internal_links = True
oldest_article = 7
extra_css = '''
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;}
'''
img {display:block; margin:0 auto;}
"""
recipe_specific_options = {
'days': {
'short': 'Oldest article to download from this news source. In days ',
'long': 'For example, 0.5, gives you articles from the past 12 hours',
'default': str(oldest_article),
}
}
def __init__(self, *args, **kwargs):
BasicNewsRecipe.__init__(self, *args, **kwargs)
d = self.recipe_specific_options.get('days')
if d and isinstance(d, str):
self.oldest_article = float(d)
ignore_duplicate_articles = {'url'}
keep_only_tags = [
classes('post-container')
]
keep_only_tags = remove_tags_after = [dict(name='div', attrs={'class': 'post'})]
remove_tags = [
dict(name='button'),
classes('font-size sharedaddy comments-form-row')
]
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'])
def preprocess_html(self, soup):
h1 = soup.find(attrs={'class': 'title'})
if h1 and h1.find('a'):
h1.a.name = 'h1'
return soup
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 list(feeds_dict.items())
feeds = [('Articles', 'http://strangehorizons.com/wordpress/feed/')]