| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
|
| 4 |
__license__ = 'GPL v3' |
| 5 |
__copyright__ = '2022' |
| 6 |
|
| 7 |
''' |
| 8 |
lemonde.fr/en |
| 9 |
''' |
| 10 |
|
| 11 |
import re |
| 12 |
|
| 13 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 14 |
|
| 15 |
|
| 16 |
def classes(classes): |
| 17 |
q = frozenset(classes.split(' ')) |
| 18 |
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) |
| 19 |
|
| 20 |
|
| 21 |
class LeMonde(BasicNewsRecipe): |
| 22 |
title = 'Le Monde in English' |
| 23 |
__author__ = 'Darko Miletic (based on veezh recipe)' |
| 24 |
description = 'Le Monde in English' |
| 25 |
publisher = 'Société Editrice du Monde' |
| 26 |
publication_type = 'newspaper' |
| 27 |
needs_subscription = 'optional' |
| 28 |
language = 'en' |
| 29 |
|
| 30 |
oldest_article = 2 |
| 31 |
max_articles_per_feed = 15 |
| 32 |
no_stylesheets = True |
| 33 |
remove_empty_feeds = True |
| 34 |
ignore_duplicate_articles = {'title', 'url'} |
| 35 |
|
| 36 |
conversion_options = {'publisher': publisher} |
| 37 |
|
| 38 |
masthead_url = 'http://upload.wikimedia.org/wikipedia/commons/thumb/5/54/Le_monde_logo.svg/800px-Le_monde_logo.svg.png' |
| 39 |
|
| 40 |
feeds = [ |
| 41 |
('Frontpage', 'https://www.lemonde.fr/en/rss/une.xml'), |
| 42 |
('International', 'https://www.lemonde.fr/en/international/rss_full.xml'), |
| 43 |
('Politics', 'https://www.lemonde.fr/en/politics/rss_full.xml'), |
| 44 |
('France', 'https://www.lemonde.fr/en/france/rss_full.xml'), |
| 45 |
('Economy', 'https://www.lemonde.fr/en/economy/rss_full.xml'), |
| 46 |
('Environment', 'https://www.lemonde.fr/en/environment/rss_full.xml'), |
| 47 |
('Science', 'https://www.lemonde.fr/en/science/rss_full.xml'), |
| 48 |
('Pixels', 'https://www.lemonde.fr/en/pixels/rss_full.xml'), |
| 49 |
('Culture', 'https://www.lemonde.fr/en/culture/rss_full.xml'), |
| 50 |
('Opinion', 'https://www.lemonde.fr/en/opinion/rss_full.xml'), |
| 51 |
('Our Times', 'https://www.lemonde.fr/en/our-times/rss_full.xml'), |
| 52 |
] |
| 53 |
|
| 54 |
keep_only_tags = [classes('article__header'), dict(name='section', attrs={'class': ['article__content', 'article__heading', 'article__wrapper']})] |
| 55 |
|
| 56 |
remove_tags = [ |
| 57 |
classes('article__status meta__date meta__reading-time meta__social multimedia-embed'), |
| 58 |
dict(name=['footer', 'link']), |
| 59 |
dict(name='img', attrs={'class': ['article__author-picture']}), |
| 60 |
dict(name='section', attrs={'class': ['article__reactions', 'author', 'catcher', 'portfolio', 'services-inread']}), |
| 61 |
] |
| 62 |
|
| 63 |
remove_attributes = ['data-sizes', 'height', 'sizes', 'width'] |
| 64 |
|
| 65 |
preprocess_regexps = [ |
| 66 |
# insert space between author name and description |
| 67 |
(re.compile(r'(<span class="[^"]*author__desc[^>]*>)([^<]*</span>)', re.IGNORECASE), lambda match: match.group(1) + ' ' + match.group(2)), |
| 68 |
# insert " | " between article type and description |
| 69 |
(re.compile(r'(<span class="[^"]*article__kicker[^>]*>[^<]*)(</span>)', re.IGNORECASE), lambda match: match.group(1) + ' | ' + match.group(2)), |
| 70 |
] |
| 71 |
|
| 72 |
extra_css = ''' |
| 73 |
h2 { font-size: 1em; } |
| 74 |
h3 { font-size: 1em; } |
| 75 |
.article__desc { font-weight: bold; } |
| 76 |
.article__fact { font-weight: bold; text-transform: uppercase; } |
| 77 |
.article__kicker { text-transform: uppercase; } |
| 78 |
.article__legend { font-size: 0.6em; margin-bottom: 1em; } |
| 79 |
.article__title { margin-top: 0em; } |
| 80 |
''' |
| 81 |
|
| 82 |
def get_browser(self): |
| 83 |
br = BasicNewsRecipe.get_browser(self) |
| 84 |
if self.username is not None and self.password is not None: |
| 85 |
br.open('https://secure.lemonde.fr/sfuser/connexion') |
| 86 |
br.select_form(nr=0) |
| 87 |
br['email'] = self.username |
| 88 |
br['password'] = self.password |
| 89 |
br.submit() |
| 90 |
return br |
| 91 |
|
| 92 |
def get_article_url(self, article): |
| 93 |
url = BasicNewsRecipe.get_article_url(self, article) |
| 94 |
# skip articles without relevant content (e.g., videos) |
| 95 |
for el in 'blog chat live podcasts portfolio video visuel'.split(): |
| 96 |
if '/' + el + '/' in url: |
| 97 |
self.log(url) |
| 98 |
self.abort_article() |
| 99 |
return url |
| 100 |
|
| 101 |
def preprocess_html(self, soup): |
| 102 |
# when an image is available in multiple sizes, select the smallest one |
| 103 |
for img in soup.find_all('img', {'data-srcset': True}): |
| 104 |
data_srcset = img['data-srcset'].split() |
| 105 |
if len(data_srcset) > 1: |
| 106 |
img['src'] = data_srcset[-2] |
| 107 |
del img['data-srcset'] |
| 108 |
return soup |
| 109 |
|
| 110 |
def postprocess_html(self, soup, first_fetch): |
| 111 |
# remove local hyperlinks |
| 112 |
for a in soup.find_all('a', {'href': True}): |
| 113 |
if '.lemonde.fr/' in a['href']: |
| 114 |
a.replace_with(self.tag_to_string(a)) |
| 115 |
# clean up header |
| 116 |
for ul in soup.find_all('ul', {'class': 'breadcrumb'}): |
| 117 |
div = soup.new_tag('div') |
| 118 |
category = '' |
| 119 |
for li in ul.find_all('li', {'class': True}): |
| 120 |
category += self.tag_to_string(li).strip().upper() + ' - ' |
| 121 |
div.string = category[:-3] |
| 122 |
ul.replace_with(div) |
| 123 |
return soup |