Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-31 14:33:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

The Observer by jbambridge

Browse Source
This commit is contained in:
Kovid Goyal 2010-05-23 09:29:15 -06:00
parent 16a1bc3588
commit ad64823512
1 changed files with 148 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

148
resources/recipes/observer_gb.recipe Normal file
View File

@ -0,0 +1,148 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
'''
http://www.guardian.co.uk/theobserver
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Guardian(BasicNewsRecipe):
title = u'The Observer'
__author__ = 'jbambridge'
language = 'en_GB'
simultaneous_downloads = 5
oldest_article = 7
max_articles_per_feed = 100
remove_javascript = True
timefmt = ' [%a, %d %b %Y]'
filter_regexps = [r'r\.kelkoo\.com']
keep_only_tags = [
dict(name='div', attrs={'id':["content","article_header","main-article-info",]}),
]
remove_tags = [
dict(name='div', attrs={'class':["video-content","videos-third-column"]}),
dict(name='div', attrs={'id':["article-toolbox","subscribe-feeds",]}),
dict(name='div', attrs={'class':["promo-component bookshop-books-promo bookshop-books"]}),
dict(name='ul', attrs={'class':["pagination"]}),
dict(name='ul', attrs={'id':["content-actions"]}),
dict(name='li', attrs={'id':["product-image"]}),
]
use_embedded_content = False
no_stylesheets = True
extra_css = '''
.article-attributes{font-size: x-small; font-family:Arial,Helvetica,sans-serif;}
.h1{font-size: large ;font-family:georgia,serif; font-weight:bold;}
.stand-first-alone{color:#666666; font-size:small; font-family:Arial,Helvetica,sans-serif;}
.caption{color:#666666; font-size:x-small; font-family:Arial,Helvetica,sans-serif;}
#article-wrapper{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
.main-article-info{font-family:Arial,Helvetica,sans-serif;}
#full-contents{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
#match-stats-summary{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
'''
feeds = [
(u'Main Section', u'feed://www.guardian.co.uk/theobserver/news/uknews/rss'),
(u'News', u'feed://www.guardian.co.uk/theobserver/news/rss'),
(u'World News', u'feed://www.guardian.co.uk/theobserver/news/worldnews/rss'),
(u'In Focus', u'feed://www.guardian.co.uk/theobserver/news/focus/rss'),
(u'7 Days', u'feed://www.guardian.co.uk/theobserver/news/7days/rss'),
(u'Seven Days', u'feed://www.guardian.co.uk/theobserver/news/seven-days/rss'),
(u'Media', u'feed://www.guardian.co.uk/theobserver/news/media/rss'),
(u'Business', u'feed://www.guardian.co.uk/theobserver/businessandmedia/rss'),
(u'Cash', u'feed://www.guardian.co.uk/theobserver/news/cash/rss'),
(u'Money', u'feed://feeds.guardian.co.uk/theguardian/money/rss'),
(u'Comment', u'feed://www.guardian.co.uk/theobserver/news/comment/rss'),
(u'Travel', u'feed://www.guardian.co.uk/theobserver/escape/rss'),
(u'Culture', u'feed://www.guardian.co.uk/theobserver/review/rss'),
(u'Money', u'feed://feeds.guardian.co.uk/theguardian/money/rss'),
(u'TV & Radio', u'feed://www.guardian.co.uk/tv-and-radio/rss'),
(u'New Review', u'feed://www.guardian.co.uk/theobserver/new-review/rss'),
(u'Agenda', u'feed://www.guardian.co.uk/theobserver/new-review/agenda/rss'),
(u'Critics', u'feed://www.guardian.co.uk/theobserver/new-review/critics/rss'),
(u'Features', u'feed://www.guardian.co.uk/theobserver/new-review/features/rss'),
(u'Discover', u'feed://www.guardian.co.uk/theobserver/new-review/discover/rss'),
(u'Books', u'feed://www.guardian.co.uk/theobserver/new-review/books/rss'),
(u'Magazine', u'feed://www.guardian.co.uk/theobserver/magazine/rss'),
(u'Regulars', u'feed://www.guardian.co.uk/theobserver/magazine/regulars/rss'),
(u'Life & Style', u'feed://www.guardian.co.uk/theobserver/magazine/life-and-style/rss'),
(u'Mag Features', u'feed://www.guardian.co.uk/theobserver/magazine/features2/rss'),
(u'Sport', u'feed://www.guardian.co.uk/theobserver/sport/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 preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(face=True):
del item['face']
for tag in soup.findAll(name=['ul','li']):
tag.name = 'div'
return soup
def find_sections(self):
soup = self.index_to_soup('http://www.guardian.co.uk/theobserver')
# 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
idx = soup.find('div', id='book-index')
for s in idx.findAll('strong', attrs={'class':'book'}):
a = s.find('a', href=True)
yield (self.tag_to_string(a), a['href'])
def find_articles(self, url):
soup = self.index_to_soup(url)
div = soup.find('div', attrs={'class':'book-index'})
for ul in div.findAll('ul', attrs={'class':'trailblock'}):
for li in ul.findAll('li'):
a = li.find(href=True)
if not a:
continue
title = self.tag_to_string(a)
url = a['href']
if not title or not url:
continue
tt = li.find('div', attrs={'class':'trailtext'})
if tt is not None:
for da in tt.findAll('a'): da.extract()
desc = self.tag_to_string(tt).strip()
yield {
'title': title, 'url':url, 'description':desc,
'date' : strftime('%a, %d %b'),
}
def parse_index(self):
try:
feeds = []
for title, href in self.find_sections():
feeds.append((title, list(self.find_articles(href))))
return feeds
except:
raise NotImplementedError
def postprocess_html(self,soup,first):
return soup.findAll('html')[0]