calibre/recipes/lrb.recipe
2020-08-22 18:48:32 +05:30

82 lines
2.9 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2019, Kovid Goyal <kovid at kovidgoyal.net>
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 absolutize(href):
if href.startswith('/'):
href = 'https://www.lrb.co.uk' + href
return href
class LondonReviewOfBooksPayed(BasicNewsRecipe):
title = 'London Review of Books'
__author__ = 'Kovid Goyal'
description = 'Literary review publishing essay-length book reviews and topical articles on politics, literature, history, philosophy, science and the arts by leading writers and thinkers' # noqa
category = 'news, literature, UK'
publisher = 'LRB Ltd.'
language = 'en_GB'
no_stylesheets = True
delay = 1
encoding = 'utf-8'
INDEX = 'https://www.lrb.co.uk'
publication_type = 'magazine'
needs_subscription = True
requires_version = (3, 0, 0)
keep_only_tags = [
classes('article-header--title paperArticle-reviewsHeader article-content letters-content'),
]
remove_tags = [
classes('social-button article-mask lrb-readmorelink article-send-letter article-share'),
]
remove_attributes = ['width', 'height']
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if self.username and self.password:
br.open('https://www.lrb.co.uk/login')
br.select_form(id='login_form')
br['_username'] = self.username
br['_password'] = self.password
raw = br.submit().read()
if b'>My Account<' not in raw:
raise ValueError('Failed to login check username and password')
return br
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-srcset': True}):
for x in img['data-srcset'].split():
if '/' in x:
img['src'] = x
return soup
def parse_index(self):
articles = []
soup = self.index_to_soup(self.INDEX)
container = soup.find(attrs={'class': 'issue-grid'})
img = container.find('img')
self.cover_url = img['data-srcset'].split()[-2]
h3 = container.find('h3')
self.timefmt = ' [{}]'.format(self.tag_to_string(h3))
a = img.findParent('a')
soup = self.index_to_soup(absolutize(a['href']))
grid = soup.find(attrs={'class': 'toc-grid-items'})
articles = []
for a in grid.findAll(**classes('toc-item')):
url = absolutize(a['href'])
h3 = a.find('h3')
h4 = a.find('h4')
title = '{}: {}'.format(self.tag_to_string(h3), self.tag_to_string(h4))
self.log(title, url)
articles.append({'title': title, 'url': url})
return [('Articles', articles)]