mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
Command used: futurize --no-diffs -f libfuturize.fixes.fix_print_with_import -f lib2to3.fixes.fix_throw -f lib2to3.fixes.fix_numliterals -f lib2to3.fixes.fix_except -f lib2to3.fixes.fix_exec -f lib2to3.fixes.fix_raise -f lib2to3.fixes.fix_tuple_params -f lib2to3.fixes.fix_ne -j20 -w -n setup recipes src manual setup.py recipes/*.recipe And manual adjustments of print((...)) -> print(...)
69 lines
2.5 KiB
Plaintext
69 lines
2.5 KiB
Plaintext
from __future__ import print_function
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
import re
|
|
|
|
|
|
class DrawAndCook(BasicNewsRecipe):
|
|
title = 'DrawAndCook'
|
|
__author__ = 'Starson17'
|
|
__version__ = 'v1.10'
|
|
__date__ = '13 March 2011'
|
|
description = 'Drawings of recipes!'
|
|
language = 'en'
|
|
publisher = 'Starson17'
|
|
category = 'news, food, recipes'
|
|
use_embedded_content = False
|
|
no_stylesheets = True
|
|
oldest_article = 24
|
|
remove_javascript = True
|
|
remove_empty_feeds = True
|
|
cover_url = 'http://farm5.static.flickr.com/4043/4471139063_4dafced67f_o.jpg'
|
|
INDEX = 'http://www.theydrawandcook.com'
|
|
max_articles_per_feed = 30
|
|
|
|
remove_attributes = ['style', 'font']
|
|
|
|
def parse_index(self):
|
|
feeds = []
|
|
for title, url in [
|
|
("They Draw and Cook", "http://www.theydrawandcook.com/")
|
|
]:
|
|
articles = self.make_links(url)
|
|
if articles:
|
|
feeds.append((title, articles))
|
|
print('feeds are: ', feeds)
|
|
return feeds
|
|
|
|
def make_links(self, url):
|
|
soup = self.index_to_soup(url)
|
|
title = ''
|
|
date = ''
|
|
current_articles = []
|
|
soup = self.index_to_soup(url)
|
|
featured_major_slider = soup.find(
|
|
name='div', attrs={'id': 'featured_major_slider'})
|
|
recipes = featured_major_slider.findAll(
|
|
'li', attrs={'data-id': re.compile(r'artwork_entry_\d+', re.DOTALL)})
|
|
for recipe in recipes:
|
|
page_url = self.INDEX + recipe.a['href']
|
|
print('page_url is: ', page_url)
|
|
title = recipe.find('strong').string
|
|
print('title is: ', title)
|
|
current_articles.append(
|
|
{'title': title, 'url': page_url, 'description': '', 'date': date})
|
|
return current_articles
|
|
|
|
keep_only_tags = [dict(name='h1', attrs={'id': 'page_title'}), dict(name='section', attrs={'id': 'artwork'})
|
|
]
|
|
|
|
remove_tags = [dict(name='article', attrs={'id': ['recipe_actions', 'metadata']})
|
|
]
|
|
|
|
extra_css = '''
|
|
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
|
|
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
|
|
img {max-width:100%; min-width:100%;}
|
|
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
|
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
|
|
'''
|