import os
import requests
from bs4 import BeautifulSoup
def ensure_url_scheme(url):
if not url.startswith(('http://', 'https://')):
return 'https://' + url.lstrip('/')
return url
def get_publications_from_hal(author_id):
# URL pour l'API de HAL
url = f"https://api.archives-ouvertes.fr/search/?q=authIdHal_s:{author_id}&wt=json&fl=title_s,authFullName_s,producedDateY_i,uri_s,conferenceTitle_s,journalTitle_s,doiId_s,docType_s"
# Envoyer une requête GET à l'API de HAL
response = requests.get(url)
# Vérifier si la requête a réussi
if response.status_code == 200:
data = response.json()
publications = data['response']['docs']
return publications
else:
print(f"Erreur : Impossible de récupérer les données de l'API de HAL. Code de statut : {response.status_code}")
return None
def download_image(image_url, image_path):
image_url = ensure_url_scheme(image_url)
response = requests.get(image_url)
if response.status_code == 200:
with open(image_path, 'wb') as f:
f.write(response.content)
return True
else:
return False
def create_html(publications):
# Créer le dossier images s'il n'existe pas
if not os.path.exists('images'):
os.makedirs('images')
# Trier les publications du plus récent au plus vieux
publications.sort(key=lambda x: x.get('producedDateY_i', 0), reverse=True)
html_content = """
<!DOCTYPE html>
<html lang="fr">
<head>
<meta charset="UTF-8">
<title>Publications</title>
<style>
ul {
list-style-type: disc;
padding-left: 20px;
}
.year-section {
margin-top: 20px;
}
.publication {
margin-bottom: 10px;
}
img {
max-width: 100px;
height: auto;
margin-right: 10px;
}
p {
margin: 0;
}
</style>
</head>
<body>
<h1>Liste des Publications</h1>
"""
current_year = None
for pub in publications:
title_list = pub.get('title_s', [])
title = title_list[0] if title_list else ''
authors = ', '.join(pub.get('authFullName_s', []))
year = pub.get('producedDateY_i', '')
uri = pub.get('uri_s', '')
conference = pub.get('conferenceTitle_s', '')
journal = pub.get('journalTitle_s', '')
doi = pub.get('doiId_s', '')
doc_type = pub.get('docType_s', '')
# Télécharger l'image de la publication si disponible
image_path = ''
if uri:
soup = BeautifulSoup(requests.get(uri).content, 'html.parser')
img_tag = soup.find('img')
if img_tag and 'src' in img_tag.attrs:
image_url = img_tag['src']
# Remplacer les caractères spéciaux et les espaces dans le titre
safe_title = title.replace(' ', '_').replace('/', '_').replace('\\', '_').replace(':', '_').replace('*', '_').replace('?', '_').replace('"', '_').replace('<', '_').replace('>', '_').replace('|', '_')
image_path = f"web/content/research/images/{safe_title}.jpg"
download_image(image_url, image_path)
# Ajouter une section pour chaque année
if year != current_year:
if current_year is not None:
html_content += "</ul></div>"
current_year = year
html_content += f"<div class='year-section'><h2>{year}</h2><ul>"
# Construire la référence complète de la publication
reference_parts = [title]
if authors:
reference_parts.append(authors)
if doc_type == 'HDR':
reference_parts.append("HDR, Université")
if doc_type == 'Rapport de recherche':
reference_parts.append("Rapport de recherche")
if doc_type == 'Logiciel':
reference_parts.append("Code informatique")
if conference or journal:
reference_parts.append(f"{conference}, {journal}, {year}")
reference_text = '<br>'.join(part for part in reference_parts if part)
# Ajouter la publication à la section de l'année correspondante
html_content += f"""
<li class="publication">
<p><strong>{title}</strong></p>
<p>{authors}</p>
<p>{conference or journal}, {year}</p>
<p><a href="{uri}">Lien vers HAL</a> {f'<a href="https://doi.org/{doi}">, Lien DOI</a>' if doi else ''}</p>
</li>
"""
html_content += """
</ul></div>
</body>
</html>
"""
with open('web/content/research/publications.html', 'w', encoding='utf-8') as f:
f.write(html_content)
# Exemple d'utilisation
author_id = "alexandre-meyer"
publications = get_publications_from_hal(author_id)
if publications:
create_html(publications)