| 1 |
from __future__ import print_function |
| 2 |
|
| 3 |
import re |
| 4 |
|
| 5 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 6 |
|
| 7 |
|
| 8 |
class DrawAndCook(BasicNewsRecipe): |
| 9 |
title = 'DrawAndCook' |
| 10 |
__author__ = 'Starson17' |
| 11 |
__version__ = 'v1.10' |
| 12 |
__date__ = '13 March 2011' |
| 13 |
description = 'Drawings of recipes!' |
| 14 |
language = 'en' |
| 15 |
publisher = 'Starson17' |
| 16 |
category = 'news, food, recipes' |
| 17 |
use_embedded_content = False |
| 18 |
no_stylesheets = True |
| 19 |
oldest_article = 24 |
| 20 |
remove_javascript = True |
| 21 |
remove_empty_feeds = True |
| 22 |
cover_url = 'http://farm5.static.flickr.com/4043/4471139063_4dafced67f_o.jpg' |
| 23 |
INDEX = 'http://www.theydrawandcook.com' |
| 24 |
max_articles_per_feed = 30 |
| 25 |
|
| 26 |
remove_attributes = ['style', 'font'] |
| 27 |
|
| 28 |
def parse_index(self): |
| 29 |
feeds = [] |
| 30 |
for title, url in [('They Draw and Cook', 'http://www.theydrawandcook.com/')]: |
| 31 |
articles = self.make_links(url) |
| 32 |
if articles: |
| 33 |
feeds.append((title, articles)) |
| 34 |
print('feeds are: ', feeds) |
| 35 |
return feeds |
| 36 |
|
| 37 |
def make_links(self, url): |
| 38 |
soup = self.index_to_soup(url) |
| 39 |
title = '' |
| 40 |
date = '' |
| 41 |
current_articles = [] |
| 42 |
soup = self.index_to_soup(url) |
| 43 |
featured_major_slider = soup.find(name='div', attrs={'id': 'featured_major_slider'}) |
| 44 |
recipes = featured_major_slider.findAll('li', attrs={'data-id': re.compile(r'artwork_entry_\d+', re.DOTALL)}) |
| 45 |
for recipe in recipes: |
| 46 |
page_url = self.INDEX + recipe.a['href'] |
| 47 |
print('page_url is: ', page_url) |
| 48 |
title = recipe.find('strong').string |
| 49 |
print('title is: ', title) |
| 50 |
current_articles.append({'title': title, 'url': page_url, 'description': '', 'date': date}) |
| 51 |
return current_articles |
| 52 |
|
| 53 |
keep_only_tags = [dict(name='h1', attrs={'id': 'page_title'}), dict(name='section', attrs={'id': 'artwork'})] |
| 54 |
|
| 55 |
remove_tags = [dict(name='article', attrs={'id': ['recipe_actions', 'metadata']})] |
| 56 |
|
| 57 |
extra_css = ''' |
| 58 |
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;} |
| 59 |
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;} |
| 60 |
img {max-width:100%; min-width:100%;} |
| 61 |
p{font-family:Arial,Helvetica,sans-serif;font-size:small;} |
| 62 |
body{font-family:Helvetica,Arial,sans-serif;font-size:small;} |
| 63 |
''' |