calibre/recipes/globe_and_mail.recipe
Kovid Goyal 29cd8d64ea
Change shebangs to python from python2
Also remove a few other miscellaneous references to python2
2020-08-22 18:47:51 +05:30

57 lines
1.9 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2018, Kovid Goyal <kovid at kovidgoyal.net>
from calibre.web.feeds.news import BasicNewsRecipe
def absolutize(href):
if href.startswith('/'):
href = 'https://www.theglobeandmail.com' + href
return href
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class GlobeMail(BasicNewsRecipe):
title = u'The Globe and Mail'
__author__ = 'Kovid Goyal'
encoding = 'utf-8'
publisher = 'Globe & Mail'
language = 'en_CA'
ignore_duplicate_articles = {'title', 'url'}
no_stylesheets = True
remove_attributes = ['style']
keep_only_tags = [
dict(name='h1'),
dict(name='main', attrs={'class': lambda x: x and 'article-primary-content-chain' in x.split()}),
]
remove_tags = [
classes('c-ad pb-f-commercial-dfp-ads pb-f-article-actions pb-f-article-meta'),
]
def parse_index(self):
ans = []
for section in 'canada opinion politics sports life arts world real-estate'.split():
if self.test and len(ans) >= self.test[0]:
break
soup = self.index_to_soup('https://www.theglobeandmail.com/{}/'.format(section))
self.log('Processing section:', section)
articles = list(self.parse_gm_section(soup))
if articles:
ans.append((section.capitalize(), articles))
return ans
def parse_gm_section(self, soup):
for a in soup.findAll('a', href=True, attrs={'data-lt-lid': lambda x: x and x.startswith('Headline.')}):
headline = a.find('div', 'c-card__hed-text')
title = self.tag_to_string(headline)
url = absolutize(a['href'])
self.log(' ', title, 'at', url)
yield {'title': title, 'url': url}