mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-02-07 11:33:30 -05:00
55 lines
1.7 KiB
Python
55 lines
1.7 KiB
Python
#!/usr/bin/env python2
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
import re
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2015, Ned Letcher - ned@nedned.net'
|
|
|
|
|
|
"""A calibre custom news recipe for creating eBooks of *all* posts
|
|
from the blog Slate Star Codex.
|
|
|
|
If calibre is installed on your system you can generate an epub of the
|
|
entire SSC archive from your command line like so:
|
|
|
|
$ ebook-convert slate_star_codex.recipe .epub
|
|
|
|
Author: Ned Letcher
|
|
|
|
"""
|
|
|
|
|
|
class SlateStarCodexArchive(BasicNewsRecipe):
|
|
title = u'Slate Star Codex (Complete Archive)'
|
|
description = 'IN A MAD WORLD, ALL BLOGGING IS PSYCHIATRY BLOGGING'
|
|
simultaneous_downloads = 10
|
|
max_articles_per_feed = 1000
|
|
reverse_article_order = True
|
|
language = 'en'
|
|
no_stylesheets = True
|
|
# alternative candidate for keep_only_tags:
|
|
# [{'attrs':{'class':['pjgm-posttitle', 'pjgm-postmeta', 'pjgm-postcontent']}}]
|
|
keep_only_tags = [dict(name='div', attrs={'class':re.compile(r'\bpost\b')})]
|
|
remove_tags = [dict(name='div', attrs={'class':re.compile(r'\bsharedaddy\b')})]
|
|
|
|
def get_archived_posts(self):
|
|
soup = self.index_to_soup('http://slatestarcodex.com/archives/')
|
|
entries = soup.findAll(attrs={'class':'sya_postcontent'})
|
|
|
|
posts = []
|
|
for entry in entries:
|
|
atag = entry.find('a')
|
|
url = atag['href']
|
|
post = {
|
|
'title' : atag.contents[0],
|
|
'url' : url,
|
|
'date' : "-".join(url.strip('/').split('/')[-4:-1]),
|
|
}
|
|
posts.append(post)
|
|
return posts
|
|
|
|
def parse_index(self):
|
|
posts = self.get_archived_posts()
|
|
return [[self.title, posts]]
|