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

Changes based on pull request feedback

Browse Source 
* removed inappropriate archive recipe
* added __author__ and encoding attributes to remaining recipe
This commit is contained in:
Ned Letcher 2015-06-21 17:48:25 +10:00
parent e4e3dd04ff
commit ab65bd18c0
2 changed files with 5 additions and 65 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
recipes/slate_star_codex.recipe
View File

@ -4,27 +4,21 @@ from calibre.web.feeds.news import BasicNewsRecipe
import re import re
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2015, Ned Letcher - ned@nedned.net' __copyright__ = '2015, Ned Letcher <ned at nedned.net>'
"""A calibre custom news recipe for creating eBooks of periodic """
updates from the blog Slate Star Codex. calibre recipe for Slate Star Codex.
If calibre is installed on your system you can generate an epub
of recent SSC posts from your command line like so:
$ ebook-convert slate_star_codex.recipe .epub
Author: Ned Letcher
""" """
class SlateStarCodex(BasicNewsRecipe): class SlateStarCodex(BasicNewsRecipe):
title = u'Slate Star Codex' title = u'Slate Star Codex'
description = 'IN A MAD WORLD, ALL BLOGGING IS PSYCHIATRY BLOGGING' description = 'IN A MAD WORLD, ALL BLOGGING IS PSYCHIATRY BLOGGING'
__author__ = 'Ned Letcher'
max_articles_per_feed = 20 max_articles_per_feed = 20
language = 'en' language = 'en'
encoding = 'utf-8'
no_stylesheets = True no_stylesheets = True
# alternative candidate for keep_only_tags: # alternative candidate for keep_only_tags:
# [{'attrs':{'class':['pjgm-posttitle', 'pjgm-postmeta', 'pjgm-postcontent']}}] # [{'attrs':{'class':['pjgm-posttitle', 'pjgm-postmeta', 'pjgm-postcontent']}}]

54
recipes/slate_star_codex_archive.recipe
View File

@ -1,54 +0,0 @@
#!/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]]