calibre/resources/recipes/national_post.recipe
2010-01-17 19:40:31 -07:00

98 lines
3.8 KiB
Plaintext

from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class NYTimes(BasicNewsRecipe):
title = 'National Post'
__author__ = 'Krittika Goyal'
description = 'Canadian national newspaper'
timefmt = ' [%d %b, %Y]'
needs_subscription = False
language = 'en_CA'
no_stylesheets = True
#remove_tags_before = dict(name='h1', attrs={'class':'heading'})
#remove_tags_after = dict(name='td', attrs={'class':'newptool1'})
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':'story-tools'}),
#dict(name='div', attrs={'id':['qrformdiv', 'inSection', 'alpha-inner']}),
#dict(name='form', attrs={'onsubmit':''}),
#dict(name='table', attrs={'cellspacing':'0'}),
]
# def preprocess_html(self, soup):
# table = soup.find('table')
# if table is not None:
# table.extract()
# return soup
#TO GET ARTICLE TOC
def nejm_get_index(self):
return self.index_to_soup('http://www.nationalpost.com/todays-paper/index.html')
# To parse artice toc
def parse_index(self):
soup = self.nejm_get_index()
div = soup.find(id='LegoText4')
current_section = None
current_articles = []
feeds = []
for x in div.findAll(True):
if x.name == 'h4':
# Section found
if current_articles and current_section:
feeds.append((current_section, current_articles))
current_section = self.tag_to_string(x)
current_articles = []
self.log('\tFound section:', current_section)
if current_section is not None and x.name == 'h3':
# Article found
title = self.tag_to_string(x)
a = x.find('a', href=lambda x: x and 'story' in x)
if a is None:
continue
url = a.get('href', False)
if not url or not title:
continue
if url.startswith('story'):
url = 'http://www.nationalpost.com/todays-paper/'+url
self.log('\t\tFound article:', title)
self.log('\t\t\t', url)
current_articles.append({'title': title, 'url':url,
'description':'', 'date':''})
if current_articles and current_section:
feeds.append((current_section, current_articles))
return feeds
def preprocess_html(self, soup):
story = soup.find(name='div', attrs={'class':'triline'})
page2_link = soup.find('p','pagenav')
if page2_link:
atag = page2_link.find('a',href=True)
if atag:
page2_url = atag['href']
if page2_url.startswith('story'):
page2_url = 'http://www.nationalpost.com/todays-paper/'+page2_url
elif page2_url.startswith( '/todays-paper/story.html'):
page2_url = 'http://www.nationalpost.com/'+page2_url
page2_soup = self.index_to_soup(page2_url)
if page2_soup:
page2_content = page2_soup.find('div','story-content')
if page2_content:
full_story = BeautifulSoup('<div></div>')
full_story.insert(0,story)
full_story.insert(1,page2_content)
story = full_story
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
body = soup.find(name='body')
body.insert(0, story)
return soup