| 1 |
# -*- mode: python; coding: utf-8; -*- |
| 2 |
# vim: set syntax=python fileencoding=utf-8 |
| 3 |
|
| 4 |
__license__ = 'GPL v3' |
| 5 |
__copyright__ = '2023, Tomás Di Domenico <tdido at tdido.eu>' |
| 6 |
|
| 7 |
''' |
| 8 |
www.eldiplo.org |
| 9 |
''' |
| 10 |
|
| 11 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 12 |
|
| 13 |
|
| 14 |
class ElDiplo2023(BasicNewsRecipe): |
| 15 |
title = 'Le Monde Diplomatique - cono sur' |
| 16 |
__author__ = 'Tomás Di Domenico' |
| 17 |
description = 'Publicación de Le Monde Diplomatique para el cono sur.' |
| 18 |
publisher = 'Capital Intelectual' |
| 19 |
category = 'News, Politics, Argentina, Uruguay, Paraguay, South America, World' |
| 20 |
oldest_article = 31 |
| 21 |
no_stylesheets = True |
| 22 |
encoding = 'utf8' |
| 23 |
use_embedded_content = False |
| 24 |
language = 'es_AR' |
| 25 |
remove_empty_feeds = True |
| 26 |
publication_type = 'magazine' |
| 27 |
delay = 1 |
| 28 |
simultaneous_downloads = 1 |
| 29 |
timeout = 8 |
| 30 |
needs_subscription = True |
| 31 |
ignore_duplicate_articles = {'url'} |
| 32 |
temp_files = [] |
| 33 |
fetch_retries = 10 |
| 34 |
handle_gzip = True |
| 35 |
compress_news_images = True |
| 36 |
scale_news_images_to_device = True |
| 37 |
masthead_url = 'https://www.eldiplo.org/wp-content/themes/_polenta_/assets/diplo.png' |
| 38 |
INDEX = 'https://www.eldiplo.org/' |
| 39 |
|
| 40 |
conversion_options = {'series': 'El Dipló', 'publisher': publisher, 'base_font_size': 8, 'tags': category} |
| 41 |
|
| 42 |
keep_only_tags = [dict(name=['article'])] |
| 43 |
|
| 44 |
remove_tags = [dict(name=['button'])] |
| 45 |
|
| 46 |
extra_css = ''' |
| 47 |
.entry-title { |
| 48 |
text-align: center; |
| 49 |
} |
| 50 |
.text-right { |
| 51 |
text-align: right; |
| 52 |
} |
| 53 |
.bajada { |
| 54 |
display: block; |
| 55 |
font-family: sans-serif; |
| 56 |
text-align: center; |
| 57 |
font-size: 110%; |
| 58 |
padding: 2%; |
| 59 |
} |
| 60 |
.Destacado{ |
| 61 |
display: block; |
| 62 |
font-size: 120%; |
| 63 |
font-weight: bold; |
| 64 |
font-style: italic; |
| 65 |
padding-left: 10%; |
| 66 |
padding-right: 10%; |
| 67 |
} |
| 68 |
''' |
| 69 |
|
| 70 |
def get_browser(self): |
| 71 |
br = BasicNewsRecipe.get_browser(self) |
| 72 |
br.open(self.INDEX) |
| 73 |
if self.username is not None and self.password is not None: |
| 74 |
br.select_form(id='loginform') |
| 75 |
br['log'] = self.username |
| 76 |
br['pwd'] = self.password |
| 77 |
br.submit() |
| 78 |
return br |
| 79 |
|
| 80 |
def get_cover_url(self): |
| 81 |
soup_index = self.index_to_soup(self.INDEX) |
| 82 |
tag_sumario = soup_index.find('span', text='Sumario') |
| 83 |
url_sumario = 'https://www.eldiplo.org' + tag_sumario.parent['href'] |
| 84 |
|
| 85 |
soup = self.index_to_soup(url_sumario) |
| 86 |
|
| 87 |
container = soup.find('div', class_='px-5') |
| 88 |
url = container.find('img')['src'] |
| 89 |
|
| 90 |
return getattr(self, 'cover_url', url) |
| 91 |
|
| 92 |
def _process_article(self, article): |
| 93 |
url = article.find('a', href=True, attrs={'class': 'title'})['href'] |
| 94 |
title = self.tag_to_string(article).replace('Editorial', 'Editorial: ') |
| 95 |
try: |
| 96 |
title, authors = title.split(', por') |
| 97 |
authors = f'por {authors}' |
| 98 |
except ValueError: |
| 99 |
authors = '' |
| 100 |
self.log('title: ', title, ' url: ', url) |
| 101 |
return {'title': title, 'url': url, 'description': authors, 'date': ''} |
| 102 |
|
| 103 |
def preprocess_html(self, soup): |
| 104 |
font_size = '90%' |
| 105 |
|
| 106 |
# make the footnotes smaller |
| 107 |
for p in soup.find('div', id='nota_pie').findChildren('p', recursive=False): |
| 108 |
p['style'] = f'font-size: {font_size};' |
| 109 |
|
| 110 |
# remove extra text |
| 111 |
extra_text = soup.find(string='POST TYPE: post') |
| 112 |
if extra_text: |
| 113 |
extra_text.parent.decompose() |
| 114 |
|
| 115 |
return soup |
| 116 |
|
| 117 |
def parse_index(self): |
| 118 |
soup_index = self.index_to_soup(self.INDEX) |
| 119 |
|
| 120 |
tag_sumario = soup_index.find('span', text='Sumario') |
| 121 |
|
| 122 |
if tag_sumario is None: |
| 123 |
return None |
| 124 |
|
| 125 |
url_sumario = 'https://www.eldiplo.org' + tag_sumario.parent['href'] |
| 126 |
self.log(url_sumario) |
| 127 |
|
| 128 |
soup_sumario = self.index_to_soup(url_sumario) |
| 129 |
|
| 130 |
feeds = [] |
| 131 |
articles = [] |
| 132 |
dossiers = [] |
| 133 |
|
| 134 |
sumario = soup_sumario.find('div', class_='sumario') |
| 135 |
|
| 136 |
for section in sumario.find_all('div', recursive=False): |
| 137 |
classes = section.attrs['class'] |
| 138 |
|
| 139 |
if 'dossier' in classes: |
| 140 |
dtitle = self.tag_to_string(section.find('h3')) |
| 141 |
darticles = [] |
| 142 |
for article in section.find_all('div', recursive=False): |
| 143 |
darticles.append(self._process_article(article)) |
| 144 |
dossiers.append((dtitle, darticles)) |
| 145 |
else: |
| 146 |
articles.append(self._process_article(section)) |
| 147 |
feeds.append(('Artículos', articles)) |
| 148 |
feeds += dossiers |
| 149 |
|
| 150 |
return feeds |