mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
65 lines
2.6 KiB
Plaintext
65 lines
2.6 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()
|
|
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']
|
|
|
|
remove_tags = [dict(name='div', attrs={'class':['ppy-caption']})
|
|
,dict(name='div', attrs={'id':['float_corner']})
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for tag in soup.findAll(name='a', attrs={'class':['deflink']}):
|
|
tag.replaceWith(tag.string)
|
|
for tag in soup.findAll(name='a', text=re.compile(r'.*View Metric.*', re.DOTALL)):
|
|
tag.parent.parent.extract()
|
|
for tag in soup.findAll(name='a', text=re.compile(r'.*Add my own photo.*', re.DOTALL)):
|
|
tag.parent.parent.extract()
|
|
for tag in soup.findAll(name='div', attrs={'class':['container']}):
|
|
if tag.find(name='h1'):
|
|
continue
|
|
if tag.find(name='h2', text=re.compile(r'.*Ingredients.*', re.DOTALL)):
|
|
print 'tag found Ingred h2'
|
|
continue
|
|
if tag.find(name='h2', text=re.compile(r'Preparation.*', re.DOTALL)):
|
|
print 'tag found Prep h2'
|
|
continue
|
|
tag.extract()
|
|
return soup
|
|
|
|
feeds = [(u'4 & 5 Star Rated Recipes', u'http://feeds.feedburner.com/Bigovencom-RecipeRaves?format=xml')]
|
|
|
|
|