Le Canard Enchaine by Kabonix

This commit is contained in:
Kovid Goyal 2024-12-20 07:58:12 +05:30
parent aaac047c0e
commit e622ee00e2
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C

View File

@ -0,0 +1,108 @@
#!/usr/bin/env python
from calibre.web.feeds.news import BasicNewsRecipe
class LeCanardEnchaine(BasicNewsRecipe):
title = 'Le Canard Enchaîné'
author = 'Kabonix'
description = 'Articles du Canard Enchaîné'
language = 'fr'
no_stylesheets = True
remove_javascript = True
keep_only_tags = [
dict(name='div', attrs={'class': ['editorial', 'article__core']}),
dict(name='div', attrs={'class': ['non-paywall', 'paywall']})
]
remove_tags = [
dict(name=['script', 'style', 'nav', 'header', 'footer']),
dict(name='div', attrs={'class': ['social-share', 'comments', 'share-mobile', 'article__author', 'article__tags']})
]
# URL de la couverture
cover_url = 'https://docimg-cdn.immanens.com/phnxc1/getcover/logistic-code/PVN1/l-pub-id/2410/l-doc-id/536798/doc-version/5/profile/cover-large.jpg'
SECTIONS = {
'Politique': '/politique/',
'Économie': '/economie/',
'International': '/international/',
'Défense': '/defense/',
'Société': '/societe/',
'Police-Justice': '/police-justice/',
'Santé': '/sante/',
'Éducation': '/education/',
'Environnement': '/environnement/',
'Technologie-Sciences': '/technologie-sciences/',
'Culture-Idées': '/culture-idees/',
'Médias': '/medias/',
'Sport': '/sport/',
'Social': '/social/',
'Brèves': '/breves/'
}
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.set_handle_robots(False)
br.open('https://www.lecanardenchaine.fr/coin/identification?u=/')
br.select_form(nr=13)
br['_username'] = 'email'
br['_password'] = 'password'
br.submit()
return br
def parse_index(self):
br = self.get_browser()
feeds = []
for section_title, section_url in self.SECTIONS.items():
print(f"Exploration de la rubrique : {section_title}")
articles = []
try:
url = 'https://www.lecanardenchaine.fr' + section_url
raw = br.open(url).read()
soup = self.index_to_soup(raw)
for link in soup.findAll('a', href=True):
href = link.get('href', '')
if section_url[1:-1] in href and href.count('/') == 2:
title = link.get_text().strip()
if title:
if not href.startswith('http'):
href = 'https://www.lecanardenchaine.fr' + href
articles.append({
'title': title,
'url': href,
'description': ''
})
seen_urls = set()
unique_articles = []
for article in articles:
if article['url'] not in seen_urls:
seen_urls.add(article['url'])
unique_articles.append(article)
if unique_articles:
feeds.append((section_title, unique_articles))
print(f" {len(unique_articles)} articles trouvés")
except Exception as e:
print(f"Erreur sur {section_title}: {str(e)}")
return feeds
def preprocess_html(self, soup):
# S'assure que le contenu paywall est visible
for div in soup.findAll('div', attrs={'class': ['unlocked', 'paywall']}):
div['class'] = ''
return soup
def postprocess_html(self, soup, first_fetch):
for tag in soup.findAll(True):
for attr in list(tag.attrs):
if attr not in ['href', 'src']:
del tag[attr]
return soup