calibre/recipes/big_oven.recipe
2019-04-13 09:17:31 +05:30

70 lines
2.8 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
import re
class BigOven(BasicNewsRecipe):
title = 'BigOven'
__author__ = 'Starson17'
description = 'Recipes for the Foodie in us all. Registration is free. A fake username and password just gives smaller photos.'
language = 'en'
category = 'news, food, recipes, gourmet'
publisher = 'Starson17'
use_embedded_content = False
no_stylesheets = True
oldest_article = 24
remove_javascript = True
remove_empty_feeds = True
cover_url = 'http://www.software.com/images/products/BigOven%20Logo_177_216.JPG'
max_articles_per_feed = 30
needs_subscription = True
conversion_options = {'linearize_tables': True, 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None:
br.open('http://www.bigoven.com/account/login?ReturnUrl=/')
br.select_form(nr=1)
br['Email'] = self.username
br['Password'] = self.password
br.submit()
return br
remove_attributes = ['style', 'font']
def get_article_url(self, article):
url = article.get('feedburner_origlink', article.get('link', None))
front, middle, end = url.partition('comhttp//www.bigoven.com')
url = front + 'com' + end
return url
keep_only_tags = [dict(name='div', attrs={'id': ['nosidebar_main']})]
remove_tags_after = [dict(name='div', attrs={'class': ['display-field']})]
remove_tags = [dict(name='ul', attrs={'class': ['tabs']})]
preprocess_regexps = [
(re.compile(r'Want detailed nutrition information?', re.DOTALL), lambda match: ''),
(re.compile(r'\(You could win \$100 in our ', re.DOTALL), lambda match: ''),
]
def preprocess_html(self, soup):
for tag in soup.findAll(name='a', text=re.compile(r'.*View Metric.*', re.DOTALL)):
tag.parent.parent.extract()
for tag in soup.findAll(text=re.compile(r'.*Try BigOven Pro for Free.*', re.DOTALL)):
tag.extract()
for tag in soup.findAll(text=re.compile(r'.*Add my photo of this recipe.*', re.DOTALL)):
tag.parent.extract()
for tag in soup.findAll(name='a', text=re.compile(r'.*photo contest.*', re.DOTALL)):
tag.parent.extract()
for tag in soup.findAll(name='a', text='Remove ads'):
tag.parent.parent.extract()
for tag in soup.findAll(name='ol', attrs={'class': ['recipe-tags']}):
tag.parent.extract()
return soup
feeds = [(u'Recent Raves', u'http://www.bigoven.com/rss/recentraves'),
(u'Recipe Of The Day', u'http://feeds.feedburner.com/bigovencom-RecipeOfTheDay')]