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"
url = f"https://api.archives-ouvertes.fr/search/?q=authIdHal_s:alexandre-meyer&wt=json&fl=title_s,authFullName_s,producedDateY_i,uri_s,conferenceTitle_s,journalTitle_s,doiId_s,docType_s,software_s,&start=0&rows=50"
# 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;
}
.custom-year-section {
margin-top: 20px;
}
.custom-publication {
margin-bottom: 0px;
margin: 0;
}
img {
max-width: 100px;
height: auto;
margin-right: 10px;
}
custom-p {
margin: 0;
}
</style>
</head>
<body>
<h1>Publications List</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', '')
thesis = pub.get('thesisDegreeGrantor_s', '')
doi = pub.get('doiId_s', '')
doc_type = pub.get('docType_s', '')
# Télécharger l'image de la publication si disponible
image_path = ''
if uri:
#print(requests.get(uri).content)
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='custom-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")
# if doc_type == 'REPORT':
# reference_parts.append("Research Report")
# if doc_type == 'THESE':
# reference_parts.append("Thesis")
# if doc_type == 'UNDEFINED':
# reference_parts.append("Code")
# print(doc_type)
# if conference or journal:
# reference_parts.append(f"{conference}, {journal}, {year}")
# reference_text = '<br>'.join(part for part in reference_parts if part)
# Construire la référence complète de la publication
reference_parts = [title]
if authors:
reference_parts.append(authors)
if doc_type == 'HDR':
pubtype = "HDR"
elif doc_type == 'REPORT':
pubtype = "Research Report"
elif doc_type == 'THESE':
pubtype = "Thesis"
elif doc_type == 'UNDEFINED':
pubtype = "Pre-publication"
print(doc_type + " title=" + title)
elif doc_type == 'COUV':
pubtype = "Book chapter"
elif doc_type == 'SOFTWARE':
pubtype = "Software"
elif conference or journal:
pubtype = conference if conference else journal
else:
pubtype = "Other"
print(doc_type + " title=" + title)
# Ajouter la publication à la section de l'année correspondante
html_content += f"""
<li class="custom-publication">
<custom-p><strong>{title}</strong></custom-p>
<custom-p>{authors}</custom-p>
<custom-p>{pubtype}, {year}</custom-p>
<custom-p><a href="{uri}">Lien vers HAL</a> {f'<a href="https://doi.org/{doi}">, Lien DOI</a>' if doi else ''}</custom-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)