calibre/recipes/guardian.recipe
2019-04-13 09:17:31 +05:30

102 lines
3.9 KiB
Python

#!/usr/bin/env python2
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
'''
www.guardian.co.uk
'''
from calibre import random_user_agent
from calibre.web.feeds.news import BasicNewsRecipe
from datetime import date
class Guardian(BasicNewsRecipe):
title = u'The Guardian and The Observer'
if date.today().weekday() == 6:
base_url = "https://www.theguardian.com/theobserver"
cover_pic = 'Observer digital edition'
masthead_url = 'http://static.guim.co.uk/sys-images/Guardian/Pix/site_furniture/2010/10/19/1287478087992/The-Observer-001.gif'
else:
base_url = "https://www.theguardian.com/uk"
cover_pic = 'Guardian digital edition'
masthead_url = 'http://static.guim.co.uk/static/f76b43f9dcfd761f0ecf7099a127b603b2922118/common/images/logos/the-guardian/titlepiece.gif'
__author__ = 'Kovid Goyal'
language = 'en_GB'
oldest_article = 7
max_articles_per_feed = 100
remove_javascript = True
encoding = 'utf-8'
remove_empty_feeds = True
no_stylesheets = True
remove_attributes = ['style']
ignore_duplicate_articles = {'title', 'url'}
timefmt = ' [%a, %d %b %Y]'
keep_only_tags = [
dict(attrs={'class': lambda x: x and 'content__main-column' in x.split()}),
]
remove_tags = [
dict(attrs={'class': lambda x: x and '--twitter' in x}),
dict(attrs={'class': lambda x: x and 'submeta' in x.split()}),
dict(attrs={'data-component': ['share', 'social']}),
dict(attrs={'data-link-name': 'block share'}),
dict(attrs={'class': lambda x: x and 'inline-expand-image' in x}),
dict(attrs={'class': lambda x: x and 'modern-visible' in x.split()}),
dict(name=['link', 'meta', 'style']),
]
remove_tags_after = [
dict(attrs={'class': lambda x: x and 'content__article-body' in x.split()}),
]
def get_browser(self, *a, **kw):
# This site returns images in JPEG-XR format if the user agent is IE
if not hasattr(self, 'non_ie_ua'):
try:
self.non_ie_ua = random_user_agent(allow_ie=False)
except TypeError:
self.non_ie_ua = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.111 Safari/537.36'
kw['user_agent'] = self.non_ie_ua
br = BasicNewsRecipe.get_browser(self, *a, **kw)
return br
def preprocess_raw_html(self, raw, url):
import html5lib
from lxml import html
return html.tostring(html5lib.parse(raw, namespaceHTMLElements=False, treebuilder='lxml'), encoding='unicode')
def preprocess_html(self, soup):
for img in soup.findAll('img', srcset=True):
img['src'] = img['srcset'].partition(' ')[0]
img['srcset'] = ''
return soup
def parse_section(self, url, title_prefix=''):
feeds = []
soup = self.index_to_soup(url)
for section in soup.findAll('section'):
title = title_prefix + self.tag_to_string(section.find(
attrs={'class': 'fc-container__header__title'})).strip().capitalize()
self.log('\nFound section:', title)
feeds.append((title, []))
for li in section.findAll('li'):
for a in li.findAll('a', attrs={'data-link-name': 'article'}, href=True):
title = self.tag_to_string(a).strip()
url = a['href']
self.log(' ', title, url)
feeds[-1][1].append({'title': title, 'url': url})
break
return feeds
def parse_index(self):
feeds = self.parse_section(self.base_url)
feeds += self.parse_section(
'https://www.theguardian.com/uk/sport', 'Sport - ')
if date.today().weekday() in (5, 6):
feeds += self.parse_section('https://www.theguardian.com/theguardian/weekend', 'Weekend - ')
return feeds