mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Update London Review of Books
This commit is contained in:
Kovid Goyal
parent
dcbed07c95
commit
17caace497
@ -1,43 +1,61 @@
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
lrb.co.uk
|
||||
'''
|
||||
|
||||
#!/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
|
||||
|
||||
|
||||
class LondonReviewOfBooks(BasicNewsRecipe):
|
||||
title = 'London Review of Books (free)'
|
||||
__author__ = 'Darko Miletic'
|
||||
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.'
|
||||
oldest_article = 15
|
||||
max_articles_per_feed = 100
|
||||
publisher = 'LRB Ltd.'
|
||||
language = 'en_GB'
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
delay = 1
|
||||
encoding = 'utf-8'
|
||||
INDEX = 'https://www.lrb.co.uk'
|
||||
publication_type = 'magazine'
|
||||
masthead_url = 'http://www.lrb.co.uk/assets/images/lrb_logo_big.gif'
|
||||
extra_css = ' body{font-family: Georgia,Palatino,"Palatino Linotype",serif} '
|
||||
|
||||
conversion_options = {
|
||||
'comments': description, 'tags': category, 'language': language, 'publisher': publisher
|
||||
}
|
||||
requires_version = (3, 0, 0)
|
||||
|
||||
keep_only_tags = [
|
||||
dict(attrs={'class': ['article-body indent', 'letters', 'article-list']})]
|
||||
classes('article-header--title paperArticle-reviewsHeader article-content letters-content'),
|
||||
]
|
||||
remove_tags = [
|
||||
classes('social-button article-mask'),
|
||||
]
|
||||
remove_attributes = ['width', 'height']
|
||||
|
||||
feeds = [(u'London Review of Books', u'http://www.lrb.co.uk/lrbrss.xml')]
|
||||
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})
|
||||
|
||||
def get_cover_url(self):
|
||||
cover_url = None
|
||||
soup = self.index_to_soup('http://www.lrb.co.uk/')
|
||||
cover_item = soup.find('p', attrs={'class': 'cover'})
|
||||
if cover_item:
|
||||
cover_url = cover_item.a.img['src']
|
||||
return cover_url
|
||||
return [('Articles', articles)]
|
||||
|
||||
@ -1,88 +0,0 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
lrb.co.uk
|
||||
'''
|
||||
import re
|
||||
from calibre import strftime
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class LondonReviewOfBooksPayed(BasicNewsRecipe):
|
||||
title = 'London Review of Books'
|
||||
__author__ = 'Rich Shang, Darko Miletic'
|
||||
description = 'Subscription content. 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.'
|
||||
max_articles_per_feed = 100
|
||||
language = 'en_GB'
|
||||
no_stylesheets = True
|
||||
delay = 1
|
||||
use_embedded_content = False
|
||||
encoding = 'utf-8'
|
||||
INDEX = 'https://www.lrb.co.uk'
|
||||
LOGIN = INDEX + '/login'
|
||||
masthead_url = INDEX + '/assets/images/lrb_logo_big.gif'
|
||||
needs_subscription = True
|
||||
publication_type = 'magazine'
|
||||
requires_version = (3, 0, 0)
|
||||
extra_css = ' body{font-family: Georgia,Palatino,"Palatino Linotype",serif} '
|
||||
|
||||
def get_browser(self):
|
||||
br = BasicNewsRecipe.get_browser(self)
|
||||
if self.username is not None and self.password is not None:
|
||||
br.open(self.LOGIN)
|
||||
br.select_form(action='/login')
|
||||
br['username'] = self.username
|
||||
br['password'] = self.password
|
||||
raw = br.submit().read()
|
||||
if b'You are logged in as' not in raw:
|
||||
raise ValueError('Failed to log in, check username and password')
|
||||
return br
|
||||
|
||||
def parse_index(self):
|
||||
articles = []
|
||||
soup = self.index_to_soup(self.INDEX)
|
||||
cover_item = soup.find('p', attrs={'class': 'cover'})
|
||||
dates = type(u'')(soup.find('span', attrs={'class': 'coverdate'}))
|
||||
try:
|
||||
newdates = re.sub(r'\<.*\>', '', re.split(r'<br\s*/>', dates)[1])
|
||||
self.timefmt = ' [%s]' % newdates
|
||||
except Exception:
|
||||
pass
|
||||
lrbtitle = self.title
|
||||
if cover_item:
|
||||
self.cover_url = re.sub('/m/', '/l/', cover_item.a.img['src'])
|
||||
content = self.INDEX + cover_item.a['href']
|
||||
soup2 = self.index_to_soup(content)
|
||||
sitem = soup2.find(attrs={'class': 'article-list'})
|
||||
lrbtitle = soup2.head.title.string
|
||||
for item in sitem.findAll('a', attrs={'class': 'title'}):
|
||||
description = u''
|
||||
title_prefix = u''
|
||||
feed_link = item
|
||||
if feed_link.get('href'):
|
||||
url = self.INDEX + feed_link['href']
|
||||
title_link = re.split('<br />', str(feed_link))
|
||||
if len(title_link) > 1:
|
||||
title = title_prefix + \
|
||||
re.sub(
|
||||
r'\<.*\>', '', title_link[0]) + ' - ' + re.sub(r'\<.*\>', '', title_link[1])
|
||||
else:
|
||||
title = title_prefix + self.tag_to_string(feed_link)
|
||||
desc = item.findNext('li')
|
||||
if desc is not None and desc.find('cite') is not None and desc.find('ul') is None:
|
||||
description = self.tag_to_string(desc)
|
||||
date = strftime(self.timefmt)
|
||||
articles.append({
|
||||
'title': title, 'date': date, 'url': url, 'description': description
|
||||
})
|
||||
return [(lrbtitle, articles)]
|
||||
|
||||
conversion_options = {
|
||||
'comments': description, 'tags': category, 'language': language, 'publisher': publisher
|
||||
}
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'class': ['article-body indent', 'letters']})]
|
||||
remove_attributes = ['width', 'height']
|
||||
Loading…
x
Reference in New Issue
Block a user