calibre/recipes/journalofaccountancy.recipe
2021-03-14 10:50:31 +05:30

134 lines
4.8 KiB
Python

#!/usr/bin/python2
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2020, Jose Ortiz <jlortiz84 at gmail.com>
from __future__ import absolute_import, division, print_function, unicode_literals
import json
from time import sleep
from mechanize import Request
from contextlib import closing
from calibre.web.feeds.news import BasicNewsRecipe
def absolutize(url):
if url.startswith('/'):
url = ('https://www.journalofaccountancy.com' + url).partition('#')[0]
return url
def classes(classes):
q = frozenset(classes.split(' '))
return dict(
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
)
class JournalOfAccountancy(BasicNewsRecipe):
__author__ = 'Jose Ortiz'
language = 'en'
title = u'Journal of Accountancy'
description = (
'A monthly journal of tax, financial reporting, auditing and other'
' topics of accountancy from American Institute of Certified Public'
' Accountants (AICPA).'
)
publication_type = 'magazine'
masthead_url = 'http://developmentprofits.com/images/JournalOfAccountancy.jpg'
no_stylesheets = True
remove_javascript = True
conversion_options = {
'comments': description,
'tags': 'News, Accountancy',
'publisher': 'American Institute of Certified Public Accountants (AICPA)'
}
keep_only_tags = [classes('contentSectionArticlePage')]
def parse_index(self):
# ISSUES ######################
issues_url = 'https://www.journalofaccountancy.com/issues.html'
with closing(self.browser.open(issues_url)):
pass
###############################
common_headers = {
'X-Requested-With': 'XMLHttpRequest',
'Accept': 'application/json, text/javascript, */*; q=0.01',
'DNT': '1',
'Pragma': 'no-cache',
'Cache-Control': 'no-cache'
}
URL_TEMPLATE = 'https://www.journalofaccountancy.com/content/jofa-home/issues/jcr:content/main-content-section/issuelibrary.%s.service'
# INIT #################################################
init_url = URL_TEMPLATE % 'init'
init_headers = {'Referer': issues_url}
init_headers.update(common_headers)
self.log('\nINIT URL at ', init_url)
with closing(self.browser.open(Request(init_url, None, init_headers))) as r:
issue_path = json.loads(r.read())[0]['page']['path']
########################################################
# FILTER ###############################
filter_url = URL_TEMPLATE % ('filter.' + issue_path.split('/')[-2])
filter_headers = {'issues': issue_path}
filter_headers.update(init_headers)
self.log('\nFILTER URL at ', filter_url)
with closing(
self.browser.open(Request(filter_url, None, filter_headers))
) as r:
issue_data = json.loads(r.read())[0]
########################################
self.cover_url = absolutize(issue_data['issueCover']['src'])
self.log('cover_url at ', self.cover_url)
self.timefmt = ' ' + issue_data['issueName']
# INDEX ####################################
index_url = absolutize(issue_path + '.html')
self.log('INDEX URL at ', index_url)
self.log('3 second pause')
sleep(3) # mimicking human user behavior
with closing(self.browser.open(index_url)):
pass
############################################
service_headers = {'Referer': index_url}
service_headers.update(common_headers)
def get_data(service):
service_url = (
'https://www.journalofaccountancy.com' + issue_path +
'/jcr:content/main-content-section/' + service + '.en.service'
)
self.log('\nSERIVICE URL at ', service_url)
req = Request(service_url, None, service_headers)
with closing(self.browser.open(req)) as r:
return json.loads(r.read())
def make_topic(category, articles):
topic = (category, [])
self.log(topic[0])
for article in articles:
title = article['articleTitle']
url = absolutize(article['page']['path'] + '.html')
desc = article.get('articleAbstract')
self.log('\t', title, ' at ', url)
topic[1].append({'title': title, 'url': url, 'description': desc})
return topic
ans = [
make_topic('SPOTLIGHT', get_data('issuelanding/articles1')),
make_topic('FEATURES', get_data('issuelanding/articles2'))
]
for category, articles in get_data('articletypelist').items():
ans.append(make_topic(category, articles))
return ans