mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
124 lines
4.7 KiB
Python
124 lines
4.7 KiB
Python
#!/usr/bin/env python
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
|
|
__docformat__ = 'restructuredtext en'
|
|
|
|
'''
|
|
www.guardian.co.uk
|
|
'''
|
|
from calibre import strftime
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from datetime import date
|
|
|
|
class Guardian(BasicNewsRecipe):
|
|
|
|
title = u'The Guardian / The Observer'
|
|
if date.today().weekday() == 6:
|
|
base_url = "http://www.guardian.co.uk/theobserver"
|
|
else:
|
|
base_url = "http://www.guardian.co.uk/theguardian"
|
|
|
|
__author__ = 'Seabound and Sujata Raman'
|
|
language = 'en_GB'
|
|
|
|
oldest_article = 7
|
|
max_articles_per_feed = 100
|
|
remove_javascript = True
|
|
|
|
# List of section titles to ignore
|
|
# For example: ['Sport']
|
|
ignore_sections = []
|
|
|
|
timefmt = ' [%a, %d %b %Y]'
|
|
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':["guardian-tickets promo-component",]}),
|
|
dict(name='ul', attrs={'class':["pagination"]}),
|
|
dict(name='ul', attrs={'id':["content-actions"]}),
|
|
#dict(name='img'),
|
|
]
|
|
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;}
|
|
'''
|
|
|
|
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")
|
|
soup = self.index_to_soup(self.base_url)
|
|
# 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():
|
|
if not title in self.ignore_sections:
|
|
feeds.append((title, list(self.find_articles(href))))
|
|
return feeds
|
|
except:
|
|
raise NotImplementedError
|
|
|
|
|