mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
99 lines
3.8 KiB
Python
99 lines
3.8 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: E501
|
|
category = 'news, literature, UK'
|
|
publisher = 'LRB Ltd.'
|
|
language = 'en_GB'
|
|
no_stylesheets = True
|
|
delay = 1
|
|
encoding = 'utf-8'
|
|
INDEX = 'https://www.lrb.co.uk/the-paper/'
|
|
publication_type = 'magazine'
|
|
needs_subscription = 'optional'
|
|
requires_version = (3, 0, 0)
|
|
masthead_url = 'https://www.mylrb.co.uk/out/lrb-2014/img/logo-2x.png'
|
|
extra_css = '''
|
|
.article-word-count, #article-tag-holder { font-size:small; color:#202020; }
|
|
.embedded-image-caption { font-size:small; text-align:center; }
|
|
blockquote, em { color:#202020; }
|
|
'''
|
|
resolve_internal_links = True
|
|
|
|
keep_only_tags = [
|
|
dict(attrs={'id':['article-tag-holder', 'article-heading-holder']}),
|
|
classes('article-copy article-word-count'),
|
|
]
|
|
|
|
remove_attributes = ['style', '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 h2 in soup.findAll('h2'):
|
|
h2.name = 'h4'
|
|
for cap in soup.findAll(**classes('embedded-image-caption')):
|
|
for p in cap.findAll('p'):
|
|
p.name = 'div'
|
|
for img in soup.findAll('img', attrs={'data-srcset': True}):
|
|
img['src'] = 'https://www.lrb.co.uk/storage/400_filter/images/' + img['data-appsrc'].split('/images/')[-1]
|
|
return soup
|
|
|
|
recipe_specific_options = {
|
|
'issue_url': {
|
|
'short': 'The issue URL ',
|
|
'long': 'For example, https://www.lrb.co.uk/the-paper/v46/n01',
|
|
'default': 'https://www.lrb.co.uk/the-paper/'
|
|
}
|
|
}
|
|
|
|
def parse_index(self):
|
|
d = self.recipe_specific_options.get('issue_url')
|
|
if d and isinstance(d, str):
|
|
self.INDEX = d
|
|
soup = self.index_to_soup(self.INDEX)
|
|
container = soup.find('div', attrs={'class': 'article-issue-cover-image'})
|
|
if container:
|
|
self.cover_url = 'https://www.lrb.co.uk/storage/800_filter/images/' + container.img['data-appsrc'].split('/images/')[-1]
|
|
edition = self.tag_to_string(soup.find('h1', attrs={'class': 'toc-title'}))
|
|
self.timefmt = ' [{}]'.format(edition)
|
|
self.log('Downloading: ', edition)
|
|
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)]
|