calibre/recipes/jacobinmag.recipe
2021-01-20 09:20:42 +05:30

113 lines
3.6 KiB
Python

# -*- mode: python -*-
# -*- coding: utf-8 -*-
# vi: set ft=python :
__license__ = 'GPL v3'
__copyright__ = '2017, Darko Miletic <darko.miletic at gmail.com>'
'''
www.jacobinmag.com
'''
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)})
class Jacobinmag(BasicNewsRecipe):
title = 'Jacobin'
__author__ = 'Darko Miletic'
description = 'Jacobin is a leading voice of the American left, offering socialist perspectives on politics, economics, and culture.'
publisher = 'Jacobin'
category = 'news, politics, USA'
oldest_article = 65
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'en'
remove_empty_feeds = True
publication_type = 'magazine'
needs_subscription = 'optional'
auto_cleanup = False
issue_url = None
PREFIX = 'https://www.jacobinmag.com'
LOGIN = 'https://auth.jacobinmag.com/mini_profile?redirect=https%3A%2F%2Fwww.jacobinmag.com%2F'
extra_css = """
body{font-family: Antwerp, 'Times New Roman', Times, serif}
img{margin-top:1em; margin-bottom: 1em; display:block}
.entry-dek,.entry-author{font-family: Hurme-No3, Futura, sans-serif}
"""
conversion_options = {
'comment': description,
'tags': category,
'publisher': publisher,
'language': language
}
remove_tags = [
dict(id=['post-header-share', 'post-print']),
dict(name='form'),
]
keep_only_tags = [
classes('po__article')
]
def parse_index(self):
ans = []
articles = []
soup = self.index_to_soup('https://www.jacobinmag.com/store/issues')
lurl = 'https://jacobinmag.com' + soup.find('a', text='View Issue')['href']
feedtitle = 'Articles'
self.log('Loading issue from', lurl)
soup = self.index_to_soup(lurl)
# Find cover url
di = soup.find('figure', attrs={'class': lambda x: x and '__cover' in x})
img = di.find('img')
self.cover_url = img['src']
# End find cover url
# Get series title
title = soup.find('h1', attrs={'class': lambda x: x and '__heading' in x})
feedtitle = self.tag_to_string(title)
# Scrape article links
for section in soup.findAll('div', attrs={'class': lambda x: x and '__content' in x}):
for art in section.findAll('article'):
h1 = art.find('h1')
a = h1.find('a')
title = self.tag_to_string(a)
url = 'https://jacobinmag.com' + a['href']
desc = ''
p = art.find('p')
if p:
desc = self.tag_to_string(p)
articles.append({'title': title, 'url': url, 'description': desc})
self.log(title, 'at', url)
if desc:
self.log('\t', desc)
if articles:
ans.append((feedtitle, articles))
return ans
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open(self.PREFIX)
if self.username is not None and self.password is not None:
br.open(self.LOGIN)
br.select_form(nr=0)
br['login.email'] = self.username
br['login.password'] = self.password
br.submit()
page = br.response().read()
soup = self.index_to_soup(page)
div = soup.find('div', attrs={'id': 'redirect-target'})
if div:
br.open(div['data-redirect'])
return br