mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
83 lines
2.8 KiB
Plaintext
83 lines
2.8 KiB
Plaintext
__license__ = 'GPL v3'
|
|
|
|
'''
|
|
www.esquire.com
|
|
'''
|
|
from collections import defaultdict
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from css_selectors import Select
|
|
|
|
|
|
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 = [
|
|
dict(name='header', attrs={
|
|
'class': ['gallery-header', 'article-header']}),
|
|
dict(attrs={'class': ['gallery-main-view', 'article-body--content']}),
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(attrs={'class': 'article-body--share-container'}),
|
|
dict(attrs={'class': lambda x: x and 'tags--top' in x}),
|
|
dict(attrs={'class': lambda x: x and 'image-share' in x}),
|
|
dict(attrs={'class': lambda x: x and 'share-gallery' in x}),
|
|
dict(attrs={'class': lambda x: x and 'embedded-image--expand' in x}),
|
|
dict(attrs={'class': lambda x: x and 'embedded-image--close' in x}),
|
|
]
|
|
|
|
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 = 'http://www.esquire.com'
|
|
root = self.index_to_soup(url, as_tree=True)
|
|
select = Select(root)
|
|
feeds = defaultdict(list)
|
|
|
|
for a in select('.custom-promo--title a[href]'):
|
|
title = self.tag_to_string(a).strip()
|
|
url = a.get('href')
|
|
if url.startswith('/'):
|
|
url = 'http://www.esquire.com' + url
|
|
feeds['Cover Story'] = [{'title': title, 'url': url}]
|
|
break
|
|
|
|
for story in select('.landing-feed--story-container'):
|
|
for sec in select('.landing-feed--story-section-name', story):
|
|
section = self.tag_to_string(sec).strip()
|
|
break
|
|
else:
|
|
continue
|
|
articles = feeds[section]
|
|
for a in select('a.landing-feed--story-title[href]', story):
|
|
title = self.tag_to_string(a).strip()
|
|
url = a.get('href')
|
|
if url.startswith('/'):
|
|
url = 'http://www.esquire.com' + url
|
|
break
|
|
else:
|
|
continue
|
|
for div in select('.landing-feed--story-abstract', story):
|
|
desc = self.tag_to_string(div).strip()
|
|
break
|
|
else:
|
|
desc = ''
|
|
articles.append({'title': title, 'url': url, 'description': desc})
|
|
|
|
ans = []
|
|
for sec in sorted(feeds, key=lambda x: (x != 'Cover Story', x)):
|
|
articles = feeds[sec]
|
|
if articles:
|
|
ans.append((sec, articles))
|
|
return ans
|