calibre/recipes/new_york_review_of_books.recipe
2025-01-04 17:51:20 +05:30

99 lines
2.8 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
'''
nybooks.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
def absurl(url):
if url.startswith('//'):
url = 'https:' + url
elif url.startswith('/'):
url = 'https://www.nybooks.com' + url
return url
class NewYorkReviewOfBooks(BasicNewsRecipe):
title = u'New York Review of Books'
description = u'Book reviews'
language = 'en_US'
__author__ = 'Kovid Goyal'
no_stylesheets = True
no_javascript = True
needs_subscription = True
keep_only_tags = [
dict(name='h1'),
classes('author article-col article-main-content review-items'),
]
remove_tags = [
classes('inline-ad'),
]
remove_tags_after = classes('article-main-content')
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open('https://www.nybooks.com/account/signin/')
br.select_form(id='loginform')
br['log'] = self.username
br['pwd'] = self.password
br.submit()
return br
def parse_index(self):
soup = self.index_to_soup('https://www.nybooks.com/current-issue')
# from calibre.utils.ipython import ipython
# ipython({'soup': soup})
# Find cover
cover = soup.find('img', attrs={'class':'border-light-gray', 'src': True})
if cover is not None:
self.cover_url = absurl(cover['src'])
self.log('Found cover at:', self.cover_url)
# Find date
div = soup.find('p', **classes('h2'))
if div is not None:
text = self.tag_to_string(div)
self.timefmt = text
self.log('Issue date:', text)
# Find TOC
articles = []
for h4 in soup.findAll('h4'):
title = self.tag_to_string(h4).strip()
url = absurl(h4.find('a')['href'])
author = self.tag_to_string(h4.parent.parent.find('a'))
title = title + ' (%s)' % author
desc = ''
div = h4
while div.next_sibling:
div = div.next_sibling
desc += self.tag_to_string(div).strip()
self.log('Found article:', title)
self.log('\t', url)
self.log('\t', desc)
articles.append({'title': title, 'url': url, 'date': '',
'description': desc})
return [('Current Issue', articles)]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-lazy-src':True}):
img['src'] = img['data-lazy-src']
return soup