OK, here is my amateur reworking of Kovid's latest LRB script.
Changes are:
- Successfully retrieves specified archive copies. It requires the manual entry of the Volume and Edition number [in 2-digit format] of the desired issue into the script. Getting back-issues was the main object in making the changes.
- Volume and edition are included in the title for filing purposes.
- High resolution cover retrieved for archived editions, not the low-res thumbnail from the archive edition front page.
- Annoying address for letters removed from the end of every article article.
- Missing author information link re-added to end of articles.
I've had the temerity to add my name to the authors, purely because if anything goes pear-shaped it will undoubtedly be something I've changed and you'll know who to blame.
Desirable changes might include reformatting the article titles in sans but that's a mystery to me.
No warranty as to suitability is offered!
Argel
Code:
#!/usr/bin/env python2
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2019, Kovid Goyal <kovid at kovidgoyal.net>
from calibre.web.feeds.news import BasicNewsRecipe
# Insert correct volume and edition number here
volume_number = '41'
edition_number = '22'
archive_url='https://www.lrb.co.uk/the-paper/v' + volume_number + '/n' + edition_number
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, Volume ' + volume_number + ', Number ' + edition_number
__author__ = 'Kovid Goyal, David Lawrence'
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 article-letters-inner contributor-pane'),
]
remove_tags = [
classes('social-button article-mask lrb-readmorelink article-send-letter article-share'),
]
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 parse_index(self):
articles = []
soup = self.index_to_soup(archive_url)
container = soup.find(attrs={'class': 'lrb-content-container'})
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(archive_url)
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)]