calibre/recipes/esquire.recipe
2019-08-27 19:25:31 +05:30

74 lines
2.2 KiB
Plaintext

__license__ = 'GPL v3'
'''
www.esquire.com
'''
from collections import defaultdict
from calibre.web.feeds.news import BasicNewsRecipe
from css_selectors import Select
def absolutize(url):
if url.startswith('/'):
url = 'https://www.esquire.com' + url
return url
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class Esquire(BasicNewsRecipe):
title = 'Esquire'
__author__ = 'Kovid Goyal'
description = 'Esquire: Man at His Best'
publisher = 'Hearst Communications, Inc.'
no_stylesheets = True
encoding = 'utf-8'
language = 'en'
keep_only_tags = [
classes('article-header gallery-header listicle-header listicle-body standard-header standard-body article-body gallery-main-view')
]
remove_tags = [
classes('article-body--share-container tags--top image-share share-gallery embedded-image--expand embedded-image--close')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']
return soup
def parse_index(self):
url = 'https://www.esquire.com'
root = self.index_to_soup(url, as_tree=True)
select = Select(root)
feeds = defaultdict(list)
for a in select('.cover-story-marquee a[href]'):
title = self.tag_to_string(a).strip() or 'Cover Story'
url = absolutize(a.get('href'))
self.log('Cover story:', title, url)
feeds['Cover Story'] = [{'title': title, 'url': url}]
break
for a in select('a[data-vars-cta]'):
title = self.tag_to_string(a).strip()
if not title:
continue
url = absolutize(a.get('href'))
section = a.get('data-vars-cta')
feeds[section].append({'title': title, 'url': url})
self.log(title, url)
ans = []
for sec in sorted(feeds, key=lambda x: (x != 'Cover Story', x)):
articles = feeds[sec]
if articles:
ans.append((sec, articles))
return ans