Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Implement #3519 (A recipe for Guardian print edition)

Browse Source
This commit is contained in:
Kovid Goyal 2009-11-04 10:09:20 -07:00
parent 3c66674bd8
commit d07738ccd2
1 changed files with 88 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

108
resources/recipes/guardian.recipe
View File

@ -15,8 +15,8 @@ class Guardian(BasicNewsRecipe):
__author__ = 'Seabound and Sujata Raman'
language = 'en_GB'
oldest_article = 7
max_articles_per_feed = 20
#oldest_article = 7
#max_articles_per_feed = 100
remove_javascript = True
timefmt = ' [%a, %d %b %Y]'
@ -45,26 +45,94 @@ class Guardian(BasicNewsRecipe):
feeds = [
('Front Page', 'http://www.guardian.co.uk/rss'),
('Business', 'http://www.guardian.co.uk/business/rss'),
('Sport', 'http://www.guardian.co.uk/sport/rss'),
('Culture', 'http://www.guardian.co.uk/culture/rss'),
('Money', 'http://www.guardian.co.uk/money/rss'),
('Life & Style', 'http://www.guardian.co.uk/lifeandstyle/rss'),
('Travel', 'http://www.guardian.co.uk/travel/rss'),
('Environment', 'http://www.guardian.co.uk/environment/rss'),
('Comment','http://www.guardian.co.uk/commentisfree/rss'),
]
# feeds = [
# ('Front Page', 'http://www.guardian.co.uk/rss'),
# ('Business', 'http://www.guardian.co.uk/business/rss'),
# ('Sport', 'http://www.guardian.co.uk/sport/rss'),
# ('Culture', 'http://www.guardian.co.uk/culture/rss'),
# ('Money', 'http://www.guardian.co.uk/money/rss'),
# ('Life & Style', 'http://www.guardian.co.uk/lifeandstyle/rss'),
# ('Travel', 'http://www.guardian.co.uk/travel/rss'),
# ('Environment', 'http://www.guardian.co.uk/environment/rss'),
# ('Comment','http://www.guardian.co.uk/commentisfree/rss'),
# ]
def get_article_url(self, article):
url = article.get('guid', None)
if '/video/' in url or '/flyer/' in url or '/quiz/' in url or \
'/gallery/' in url or 'ivebeenthere' in url or \
'pickthescore' in url or 'audioslideshow' in url :
url = None
return url
# def get_article_url(self, article):
# url = article.get('guid', None)
# if '/video/' in url or '/flyer/' in url or '/quiz/' in url or \
# '/gallery/' in url or 'ivebeenthere' in url or \
# 'pickthescore' in url or 'audioslideshow' in url :
# url = None
# return url
def parse_index(self):
articles = []
soup = self.index_to_soup('http://www.guardian.co.uk/theguardian')
# find cover pic
img = soup.find( 'img',attrs ={'alt':'Guardian digital edition'})
if img is not None:
self.cover_url = img['src']
# end find cover pic
for li in soup.findAll( 'li'):
if li.a and li.a.has_key('href'):
url = li.a['href']
if 'mainsection' in url:
#find the articles in the Main Section
soup = self.index_to_soup(url)
for tag in soup.findAll('h3'):
for a in tag.findAll('a'):
if a and a.has_key('href'):
url2 = a['href']
else:
url2 =''
title = self.tag_to_string(a)
#eliminate duplicates
if len(articles) == 0:
desc = 'Main Section'
date = ''
articles.append({
'title':title,
'date':date,
'url':url2,
'description':desc,
})
else:
if len(articles) > 0:
if {'title':title,'date':date,'url':url2,'description':desc} in articles:
ulrl2 = ''
#eliminate duplicates
else:
desc = 'Main Section'
date = ''
articles.append({
'title':title,
'date':date,
'url':url2,
'description':desc,
})
#find the articles in the Main Section
else:
url =''
return [('Current Issue', articles)]
def preprocess_html(self, soup):