calibre/recipes/berlin_policy_journal.recipe
Kovid Goyal 29cd8d64ea
Change shebangs to python from python2
Also remove a few other miscellaneous references to python2
2020-08-22 18:47:51 +05:30

111 lines
4.5 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2016, Aimylios <aimylios at gmx.de>
from __future__ import unicode_literals, division, absolute_import, print_function
'''
berlinpolicyjournal.com
'''
import re
import time
from calibre.web.feeds.news import BasicNewsRecipe
class BerlinPolicyJournal(BasicNewsRecipe):
title = 'Berlin Policy Journal'
__author__ = 'Aimylios'
description = 'Articles from berlinpolicyjournal.com'
publisher = 'Deutsche Gesellschaft für Auswärtige Politik e.V.'
publication_type = 'magazine'
language = 'en_DE'
oldest_article = 50
max_articles_per_feed = 30
simultaneous_downloads = 5
no_stylesheets = True
remove_javascript = True
conversion_options = {'smarten_punctuation': True,
'publisher': publisher}
INDEX = 'http://berlinpolicyjournal.com/'
masthead_url = INDEX + 'IP/wp-content/uploads/2015/04/logo_bpj_header.gif'
keep_only_tags = [
dict(name='article')
]
remove_tags = [
dict(name='div', attrs={
'class': ['hidden', 'meta-count', 'meta-share']}),
dict(name='span', attrs={'class': 'ava-auth'}),
dict(name='img', attrs={'alt': re.compile('_store_120px_width$')}),
dict(name='img', attrs={'alt': re.compile('^bpj_app_')}),
dict(name='img', attrs={'alt': re.compile('^BPJ-Montage_')}),
dict(name=['link', 'footer', 'br'])
]
remove_attributes = ['sizes', 'width', 'height', 'align']
extra_css = 'h1 {font-size: 1.6em; text-align: left} \
.entry-subtitle {font-style: italic; margin-bottom: 1em} \
.wp-caption {margin-top: 1em} \
.wp-caption-text {font-size: 0.6em; margin-top: 0em}'
def parse_index(self):
soup = self.index_to_soup(self.INDEX)
img_div = soup.find('div', {'id': 'text-2'})
self.cover_url = img_div.find('img', src=True)['src']
menu = soup.find('ul', {'id': re.compile('menu-ip')})
submenus = menu.findAll(
'li', {'class': re.compile('item-has-children')})
mag = submenus[0].find('li')
mag_name = self.tag_to_string(mag.a)
mag_url = mag.a['href']
categories = [{'name': mag_name, 'url': mag_url, 'type': 'magazine'}]
for blog in submenus[1].findAll('li'):
blog_name = self.tag_to_string(blog.a)
blog_url = blog.a['href']
categories.append(
{'name': blog_name, 'url': blog_url, 'type': 'blog'})
feeds = []
for cat in categories:
cat['articles'] = []
for i in ['1', '2']:
soup = self.index_to_soup(cat['url'] + '/page/' + i)
for div in soup.findAll('div', {'class': 'post-box-big'}):
timestamp = time.strptime(div.find('time')['datetime'][
:15], '%Y-%m-%dT%H:%M')
age = (time.time() - time.mktime(timestamp)) / (24 * 3600)
if age > self.oldest_article and cat['type'] == 'blog':
continue
article_title = self.tag_to_string(
div.find('h3', {'class': 'entry-title'}).a)
article_url = div.find(
'h3', {'class': 'entry-title'}).a['href']
article_date = type(u'')(time.strftime(
' [%a, %d %b %H:%M]', timestamp))
article_desc = self.tag_to_string(
div.find('div', {'class': 'i-summary'}).p)
cat['articles'].append({'title': article_title,
'url': article_url,
'date': article_date,
'description': article_desc})
if soup.find('div', {'class': 'pagination'}) is None:
break
if cat['articles']:
feeds.append((cat['name'], cat['articles']))
return feeds
def postprocess_html(self, soup, first_fetch):
# clean up formatting of author(s) and date
div = soup.find('div', {'class': 'meta-info'})
authors = ''
for entry in div.findAll('span', {'class': 'entry-author'}):
authors = authors + entry.a.span.renderContents().decode('utf-8').strip() + ', '
date = div.find('time').renderContents().decode('utf-8').strip()
div.replaceWith('<div>' + date + ' | ' + authors[:-2] + '<br/></div>')
return soup