calibre/recipes/nytimesbook.recipe
2022-09-15 12:24:41 +05:30

93 lines
3.2 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2015, Kovid Goyal <kovid at kovidgoyal.net>
from calibre.web.feeds.news import BasicNewsRecipe
use_wayback_machine = False
def absolutize(url):
if url.startswith('/'):
url = 'https://www.nytimes.com' + url
return url
class NewYorkTimesBookReview(BasicNewsRecipe):
title = u'New York Times Book Review'
language = 'en'
description = 'The New York Times Sunday Book Review'
__author__ = 'Kovid Goyal'
no_stylesheets = True
no_javascript = True
ignore_duplicate_articles = {'title', 'url'}
encoding = 'utf-8'
articles_are_obfuscated = use_wayback_machine
if use_wayback_machine:
def get_obfuscated_article(self, url):
from calibre.ptempfile import PersistentTemporaryFile
with PersistentTemporaryFile() as tf:
tf.write(self.get_nyt_page(url))
return tf.name
@property
def nyt_parser(self):
ans = getattr(self, '_nyt_parser', None)
if ans is None:
from calibre.live import load_module
self._nyt_parser = ans = load_module('calibre.web.site_parsers.nytimes')
return ans
def get_nyt_page(self, url):
if use_wayback_machine:
from calibre import browser
return self.nyt_parser.download_url(url, browser())
return self.browser.open_novisit(url).read()
def preprocess_raw_html(self, raw_html, url):
html = self.nyt_parser.extract_html(self.index_to_soup(raw_html))
return html
def parse_index(self):
# return [('Articles', [{'url': 'https://www.nytimes.com/2022/09/08/books/review/karen-armstrong-by-the-book-interview.html', 'title':'test'}])]
soup = self.index_to_soup(
self.get_nyt_page('https://www.nytimes.com/pages/books/review/index.html'))
# Find TOC
toc = soup.find('section', id='collection-book-review').find('section').find('ol')
main_articles, articles = [], []
feeds = [('Features', main_articles), ('Latest', articles)]
for li in toc.findAll('li'):
h2 = li.find('h2')
a = h2.find('a', href=True)
if a is not None:
title = self.tag_to_string(a)
url = absolutize(a['href'])
desc = ''
p = h2.findNextSibling('p')
if p:
desc = self.tag_to_string(p)
main_articles.append(
{'title': title, 'url': url, 'description': desc})
self.log('Found:', title, 'at', url)
if desc:
self.log('\t', desc)
for li in soup.find(id='stream-panel').find('ol').findAll('li'):
h2 = li.find('h2')
a = h2.findParent('a')
url = absolutize(a['href'])
p = h2.findNextSibling('p')
title = self.tag_to_string(h2)
desc = ''
if p:
desc = self.tag_to_string(p)
articles.append({'title': title, 'url': url, 'description': desc})
self.log('Found:', title, 'at', url)
if desc:
self.log('\t', desc)
return feeds