mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
103 lines
3.7 KiB
Python
103 lines
3.7 KiB
Python
# -*- mode: python; coding: utf-8; -*-
|
|
# vim: set syntax=python fileencoding=utf-8
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2021, Darko Miletic <darko.miletic at gmail.com>'
|
|
|
|
'''
|
|
www.eldiplo.org
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ptempfile import PersistentTemporaryFile
|
|
|
|
|
|
class ElDiplo2020(BasicNewsRecipe):
|
|
title = 'Le Monde Diplomatique - cono sur'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Publicación de Le Monde Diplomatique para el cono sur.'
|
|
publisher = 'Le Monde Diplomatique'
|
|
category = 'news, politics, Argentina, Uruguay, Paraguay, South America, World'
|
|
oldest_article = 31
|
|
no_stylesheets = True
|
|
encoding = 'utf8'
|
|
use_embedded_content = False
|
|
language = 'es_AR'
|
|
remove_empty_feeds = True
|
|
publication_type = 'magazine'
|
|
auto_cleanup = True
|
|
auto_cleanup_keep = '//div[contains(@class, "autor")] | //div[@class="edicion"]'
|
|
delay = 1
|
|
simultaneous_downloads = 1
|
|
timeout = 8
|
|
needs_subscription = 'optional'
|
|
ignore_duplicate_articles = {'url'}
|
|
articles_are_obfuscated = True
|
|
temp_files = []
|
|
fetch_retries = 10
|
|
handle_gzip = True
|
|
compress_news_images = True
|
|
scale_news_images_to_device = True
|
|
masthead_url = 'https://www.eldiplo.org/wp-content/themes/_polenta_/assets/diplo.png'
|
|
INDEX = 'https://www.eldiplo.org/'
|
|
|
|
extra_css = """
|
|
body{font-family: "GT Super", serif}
|
|
.autor{font-family: Inter, serif}
|
|
"""
|
|
|
|
conversion_options = {
|
|
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
|
|
}
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser(self)
|
|
br.open(self.INDEX)
|
|
if self.username is not None and self.password is not None:
|
|
br.select_form(id='loginform')
|
|
br['log'] = self.username
|
|
br['pwd'] = self.password
|
|
br.submit()
|
|
return br
|
|
|
|
def parse_index(self):
|
|
articles = []
|
|
soup = self.index_to_soup(self.INDEX)
|
|
mylink = soup.find('span', text='Sumario')
|
|
if mylink is None:
|
|
return None
|
|
indexurl = "https://www.eldiplo.org" + mylink.parent['href']
|
|
self.log(indexurl)
|
|
parts = indexurl.split('www.eldiplo.org/', 1)
|
|
series = parts[1].split('-', 1)[0]
|
|
self.conversion_options.update({'series' : self.title})
|
|
self.conversion_options.update({'series_index' : series})
|
|
soupindex = self.index_to_soup(indexurl)
|
|
totalfeeds = []
|
|
articles = []
|
|
for article in soupindex.findAll('a', href=True, attrs={'class':'title'}):
|
|
url = article['href']
|
|
title = self.tag_to_string(article)
|
|
articles.append({'title': title, 'url': url, 'description': '', 'date': ''})
|
|
self.log('title: ', title, ' url: ', url)
|
|
totalfeeds.append(('Articles',articles))
|
|
return totalfeeds
|
|
|
|
def get_obfuscated_article(self, url):
|
|
result = None
|
|
count = 0
|
|
while (count < self.fetch_retries):
|
|
try:
|
|
response = self.browser.open(url, timeout=self.timeout)
|
|
html = response.read()
|
|
count = self.fetch_retries
|
|
tfile = PersistentTemporaryFile('_fa.html')
|
|
tfile.write(html)
|
|
tfile.close()
|
|
self.temp_files.append(tfile)
|
|
result = tfile.name
|
|
except:
|
|
self.info("Retrying download...")
|
|
count += 1
|
|
return result
|