mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
59 lines
2.2 KiB
Python
59 lines
2.2 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2010, Starson17'
|
|
'''
|
|
www.epicurious.com
|
|
'''
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class Epicurious(BasicNewsRecipe):
|
|
title = u'Epicurious'
|
|
__author__ = 'Starson17'
|
|
description = 'Food and Recipes from Epicurious'
|
|
cover_url = 'http://up6.podbean.com/image-logos/21849_logo.jpg'
|
|
publisher = 'Epicurious'
|
|
tags = 'news, food, gourmet, recipes'
|
|
language = 'en'
|
|
use_embedded_content = False
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
recursions = 3
|
|
oldest_article = 14
|
|
max_articles_per_feed = 20
|
|
|
|
keep_only_tags = [dict(name='div', attrs={'class':['mainconsolewrapper','videoheader','content_unit','entry-content','see_more_block']}),
|
|
dict(name='div', attrs={'id':['headline','introBlock','ingredients','preparation','articleContent','in_categories_block']})
|
|
]
|
|
|
|
remove_tags = [{'id':['printShoppingList','addnoteLnk','btnUploadVideo','enlarge_image']},
|
|
{'class':['subLnk','sbmWrapper','detail_division','entry-footer','comment-footer']},
|
|
dict(name='div', attrs={'class':['tagged','comments']})
|
|
]
|
|
|
|
remove_tags_after = [dict(name='div', attrs={'class':'entry-content'})]
|
|
|
|
feeds = [
|
|
(u'Recipes: Healthy dinner ', u'http://feeds.epicurious.com/healthy_recipes'),
|
|
(u'New Recipes ', u'http://feeds.epicurious.com/newrecipes'),
|
|
(u'Features ', u'http://feeds.epicurious.com/latestfeatures'),
|
|
(u'Blogs ', u'http://feeds.feedburner.com/epicurious/epiblog')
|
|
]
|
|
|
|
match_regexps = [
|
|
r'http://www.epicurious.com/.*recipes/.*/views'
|
|
]
|
|
|
|
preprocess_regexps = [
|
|
(re.compile(r'/\n', re.DOTALL|re.IGNORECASE), lambda match: '/'),
|
|
(re.compile(r'_116.jpg', re.DOTALL|re.IGNORECASE), lambda match: '.jpg'),
|
|
(re.compile('<div class=\"comments\".*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>')
|
|
]
|
|
|
|
def postprocess_html(self, soup, first_fetch):
|
|
for t in soup.findAll(['table', 'tr', 'td']):
|
|
t.name = 'div'
|
|
return soup
|
|
|