Update El Diplo

Fixes #1891216 [New recipe for Le Monde Diplomatique - cono sur](https://bugs.launchpad.net/calibre/+bug/1891216)
This commit is contained in:
Kovid Goyal 2020-08-12 07:45:22 +05:30
parent 2912b411f9
commit 3523a126dc
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 88 additions and 108 deletions

View File

@ -1,123 +1,103 @@
# Copyright 2013 Tomás Di Domenico
#
# This is a news fetching recipe for the Calibre ebook software, for
# fetching the Cono Sur edition of Le Monde Diplomatique (www.eldiplo.org).
#
# This recipe is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This software is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this recipe. If not, see <http://www.gnu.org/licenses/>.
# -*- mode: python; coding: utf-8; -*-
# vim: set syntax=python fileencoding=utf-8
import re
from contextlib import closing
from calibre.web.feeds.recipes import BasicNewsRecipe
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2020, Darko Miletic <darko.miletic at gmail.com>'
'''
www.eldiplo.org
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ptempfile import PersistentTemporaryFile
from calibre.utils.magick import Image
class ElDiplo_Recipe(BasicNewsRecipe):
title = u'El Diplo'
__author__ = 'Tomas Di Domenico'
description = 'Publicacion mensual de Le Monde Diplomatique, edicion Argentina'
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'
needs_subscription = True
remove_empty_feeds = True
publication_type = 'magazine'
auto_cleanup = True
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/eldiplo/img/logo.png'
INDEX = 'https://www.eldiplo.org/'
def get_cover(self, url):
tmp_cover = PersistentTemporaryFile(suffix=".jpg", prefix="eldiplo_")
self.cover_url = tmp_cover.name
extra_css = """
body{font-family: Roboto, sans-serif}
.entry-title{font-family: Spectral, serif}
"""
with closing(self.browser.open(url)) as r:
imgdata = r.read()
img = Image()
img.load(imgdata)
img.crop(img.size[0], img.size[1] / 2, 0, 0)
img.save(tmp_cover.name)
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.open('http://www.eldiplo.org/index.php/login/-/do_login/index.html')
br.select_form(nr=3)
br['uName'] = self.username
br['uPassword'] = self.password
br.select_form(id='loginform')
br['log'] = self.username
br['pwd'] = self.password
br.submit()
self.browser = br
return br
def parse_index(self):
default_sect = 'General'
articles = {default_sect: []}
ans = [default_sect]
sectionsmarker = 'DOSSIER_TITLE: '
sectionsre = re.compile('^' + sectionsmarker)
articles = []
soup = self.index_to_soup(self.INDEX)
mylink = soup.find('a', {'class':'edicion_cover'})
if mylink is None:
return None
self.cover_url = mylink.img['src']
indexurl = mylink['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
soup = self.index_to_soup('http://www.eldiplo.org/index.php')
coverdivs = soup.findAll(True, attrs={'id': ['lmd-foto']})
a = coverdivs[0].find('a', href=True)
coverurl = a['href'].split("?imagen=")[1]
self.get_cover(coverurl)
thedivs = soup.findAll(True, attrs={'class': ['lmd-leermas']})
for div in thedivs:
a = div.find('a', href=True)
if 'Sumario completo' in self.tag_to_string(a, use_alt=True):
summaryurl = re.sub(r'\?.*', '', a['href'])
summaryurl = 'http://www.eldiplo.org' + summaryurl
for pagenum in range(1, 10):
soup = self.index_to_soup(
'{0}/?cms1_paging_p_b32={1}'.format(summaryurl, pagenum))
thedivs = soup.findAll(True, attrs={'class': ['interna']})
if len(thedivs) == 0:
break
for div in thedivs:
section = div.find(True, text=sectionsre).replace(
sectionsmarker, '')
if section == '':
section = default_sect
if section not in articles.keys():
articles[section] = []
ans.append(section)
nota = div.find(
True, attrs={'class': ['lmd-pl-titulo-nota-dossier']})
a = nota.find('a', href=True)
if not a:
continue
url = re.sub(r'\?.*', '', a['href'])
url = 'http://www.eldiplo.org' + url
title = self.tag_to_string(a, use_alt=True).strip()
summary = div.find(
True, attrs={'class': 'lmd-sumario-descript'}).find('p')
if summary:
description = self.tag_to_string(summary, use_alt=False)
aut = div.find(True, attrs={'class': 'lmd-autor-sumario'})
if aut:
auth = self.tag_to_string(aut, use_alt=False).strip()
if section not in articles: # noqa
articles[section] = []
articles[section].append(dict(
title=title, author=auth, url=url, date=None, description=description, content=''))
ans = [(s, articles[s]) for s in ans if s in articles]
return ans
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

BIN
recipes/icons/el_diplo.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 438 B