mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
42 lines
1.3 KiB
Plaintext
42 lines
1.3 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
|
|
|
class drivelrycom(BasicNewsRecipe):
|
|
title = u'drivelry.com'
|
|
language = 'en'
|
|
description = 'A blog by Mike Abrahams'
|
|
__author__ = 'Krittika Goyal'
|
|
oldest_article = 60 #days
|
|
max_articles_per_feed = 25
|
|
#encoding = 'latin1'
|
|
|
|
remove_stylesheets = True
|
|
#remove_tags_before = dict(name='h1', attrs={'class':'heading'})
|
|
remove_tags_after = dict(name='div', attrs={'id':'bookmark'})
|
|
remove_tags = [
|
|
dict(name='iframe'),
|
|
dict(name='div', attrs={'class':['sidebar']}),
|
|
dict(name='div', attrs={'id':['bookmark']}),
|
|
#dict(name='span', attrs={'class':['related_link', 'slideshowcontrols']}),
|
|
#dict(name='ul', attrs={'class':'articleTools'}),
|
|
]
|
|
|
|
feeds = [
|
|
('drivelry.com',
|
|
'http://feeds.feedburner.com/drivelry'),
|
|
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
story = soup.find(name='div', attrs={'id':'main'})
|
|
#td = heading.findParent(name='td')
|
|
#td.extract()
|
|
soup = BeautifulSoup('''
|
|
<html><head><title>t</title></head><body>
|
|
<p>To donate to this blog: <a href="http://www.drivelry.com/thank-you/">click here</a></p>
|
|
</body></html>
|
|
''')
|
|
body = soup.find(name='body')
|
|
body.insert(0, story)
|
|
return soup
|