calibre/recipes/harpers_full.recipe

107 lines
4.2 KiB
Python

# -*- mode: python -*-
# -*- coding: utf-8 -*-
# vi: set fenc=utf-8 ft=python :
# kate: encoding utf-8; syntax python;
__license__ = 'GPL v3'
__copyright__ = '2008-2017, Darko Miletic <darko.miletic at gmail.com>'
'''
harpers.org - paid subscription/ printed issue articles
This recipe only get's article's published in text format
images and pdf's are ignored
If you have institutional subscription based on access IP you do not need to enter
anything in username/password fields
'''
import time
import re
import urllib
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Harpers_full(BasicNewsRecipe):
title = "Harper's Magazine - articles from printed edition"
__author__ = 'Darko Miletic'
description = "Harper's Magazine, the oldest general-interest monthly in America, explores the issues that drive our national conversation, through long-form narrative journalism and essays, and such celebrated features as the iconic Harper's Index." # noqa
publisher = "Harpers's"
category = 'news, politics, USA'
oldest_article = 30
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
delay = 1
language = 'en'
encoding = 'utf8'
needs_subscription = 'optional'
masthead_url = 'https://harpers.org/wp-content/themes/harpers/images/pheader.gif'
publication_type = 'magazine'
LOGIN = 'https://harpers.org/wp-admin/admin-ajax.php'
extra_css = """
body{font-family: adobe-caslon-pro,serif}
.category{font-size: small}
.articlePost p:first-letter{display: inline; font-size: xx-large; font-weight: bold}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
keep_only_tags = [
dict(name='div', attrs={'class': ['postdetailFull', 'articlePost']})]
remove_tags = [
dict(name='div', attrs={'class': 'fRight rightDivPad'}), dict(
name=['link', 'meta', 'object', 'embed', 'iframe'])
]
remove_attributes = ['xmlns']
def get_browser(self):
# harpers ssl certificate is broken as of Jul 2017
br = BasicNewsRecipe.get_browser(self, verify_ssl_certificates=False)
br.open('https://harpers.org/')
if self.username is not None and self.password is not None:
tt = time.localtime() * 1000
data = urllib.urlencode({'action': 'cds_auth_user', 'm': self.username, 'p': self.password, 'rt': 'https://harpers.org/', 'tt': tt
})
br.open(self.LOGIN, data)
return br
def parse_index(self):
# find current issue
soup = self.index_to_soup('https://harpers.org/')
currentIssue = soup.find('div', attrs={'class': 'mainNavi'}).find(
'li', attrs={'class': 'curentIssue'})
currentIssue_url = self.tag_to_string(currentIssue.a['href'])
self.log(currentIssue_url)
# go to the current issue
soup1 = self.index_to_soup(currentIssue_url)
currentIssue_title = self.tag_to_string(soup1.head.title.string)
date = re.split('\s\|\s', currentIssue_title)[0]
self.timefmt = u' [%s]' % date
# get cover
self.cover_url = soup1.find(
'div', attrs={'class': 'picture_hp'}).find('img', src=True)['src']
self.log(self.cover_url)
articles = []
count = 0
for item in soup1.findAll('div', attrs={'class': 'articleData'}):
text_links = item.findAll('h2')
if text_links:
for text_link in text_links:
if count == 0:
count = 1
else:
url = text_link.a['href']
title = self.tag_to_string(text_link.a)
date = strftime(' %B %Y')
articles.append({
'title': title, 'date': date, 'url': url, 'description': ''
})
return [(currentIssue_title, articles)]
def print_version(self, url):
return url + '?single=1'