Spaces:
Sleeping
Sleeping
Update src/streamlit_app.py
Browse files- src/streamlit_app.py +466 -130
src/streamlit_app.py
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
#
|
| 2 |
import streamlit as st
|
| 3 |
import requests
|
| 4 |
from bs4 import BeautifulSoup
|
|
@@ -7,25 +7,32 @@ import pandas as pd
|
|
| 7 |
from datetime import datetime
|
| 8 |
import urllib.parse
|
| 9 |
import time
|
|
|
|
|
|
|
| 10 |
|
| 11 |
# --- Configuration ---
|
| 12 |
CODEX_CATEGORIES = {
|
| 13 |
'codes': {
|
| 14 |
'name': 'Codes de Pratique (CXC)',
|
| 15 |
'url': 'https://www.fao.org/fao-who-codexalimentarius/codex-texts/codes-of-practice/fr/',
|
| 16 |
-
'prefix': 'CXC'
|
|
|
|
|
|
|
| 17 |
},
|
| 18 |
'standards': {
|
| 19 |
'name': 'Normes (CXS)',
|
| 20 |
'url': 'https://www.fao.org/fao-who-codexalimentarius/codex-texts/list-standards/fr/',
|
| 21 |
-
'prefix': 'CXS'
|
|
|
|
|
|
|
| 22 |
},
|
| 23 |
'guidelines': {
|
| 24 |
'name': 'Directives (CXG)',
|
| 25 |
'url': 'https://www.fao.org/fao-who-codexalimentarius/codex-texts/guidelines/fr/',
|
| 26 |
-
'prefix': 'CXG'
|
|
|
|
|
|
|
| 27 |
}
|
| 28 |
-
# 'misc' peut être ajouté si nécessaire
|
| 29 |
}
|
| 30 |
|
| 31 |
HEADERS = {
|
|
@@ -33,12 +40,94 @@ HEADERS = {
|
|
| 33 |
}
|
| 34 |
TIMEOUT = 30
|
| 35 |
BASE_URL = "https://www.fao.org"
|
| 36 |
-
# --- Fin Configuration ---
|
| 37 |
|
| 38 |
# Configuration de la page
|
| 39 |
-
st.set_page_config(
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
def extract_documents_from_url(url, category_key):
|
| 43 |
"""
|
| 44 |
Fonction pour extraire les documents d'une catégorie Codex.
|
|
@@ -46,7 +135,6 @@ def extract_documents_from_url(url, category_key):
|
|
| 46 |
"""
|
| 47 |
category_info = CODEX_CATEGORIES[category_key]
|
| 48 |
category_name = category_info['name']
|
| 49 |
-
st.info(f"Extraction de {category_name}...")
|
| 50 |
|
| 51 |
documents = []
|
| 52 |
seen_codes = set()
|
|
@@ -58,19 +146,15 @@ def extract_documents_from_url(url, category_key):
|
|
| 58 |
|
| 59 |
tables = soup.find_all('table')
|
| 60 |
if not tables:
|
| 61 |
-
st.warning(f"Aucun tableau trouvé pour {category_name}.")
|
| 62 |
return documents
|
| 63 |
|
| 64 |
for table in tables:
|
| 65 |
rows = table.find_all('tr')
|
| 66 |
for row in rows:
|
| 67 |
cells = row.find_all(['td', 'th'])
|
| 68 |
-
# Vérifier s'il y a au moins 5 cellules (données + cellule PDF)
|
| 69 |
if len(cells) >= 5:
|
| 70 |
-
# Extraire les données de base (cellules 1 à 4)
|
| 71 |
cell_texts = [cell.get_text(strip=True) for cell in cells[:4]]
|
| 72 |
code_candidate = cell_texts[0] if cell_texts else ""
|
| 73 |
-
# Pattern pour le préfixe de la catégorie
|
| 74 |
prefix = category_info['prefix']
|
| 75 |
code_match = re.match(rf'^({prefix})\s+([\w\-R]*\d+(?:-\d+)?[R]?)$', code_candidate)
|
| 76 |
|
|
@@ -90,29 +174,21 @@ def extract_documents_from_url(url, category_key):
|
|
| 90 |
except ValueError:
|
| 91 |
year = 0
|
| 92 |
|
| 93 |
-
#
|
| 94 |
-
# Le lien PDF est dans la 5ème cellule (index 4)
|
| 95 |
pdf_cell = cells[4]
|
| 96 |
pdf_url = None
|
| 97 |
-
|
| 98 |
-
# Trouver le premier lien <a> dans cette cellule qui contient 'pdf'
|
| 99 |
link_tag = pdf_cell.find('a', href=re.compile(r'.*\.pdf', re.IGNORECASE))
|
| 100 |
if link_tag:
|
| 101 |
href = link_tag.get('href')
|
| 102 |
if href:
|
| 103 |
-
# 1. Décoder les entités HTML (& -> &)
|
| 104 |
decoded_href = urllib.parse.unquote(href)
|
| 105 |
-
|
| 106 |
-
# 2. Construire l'URL absolue
|
| 107 |
pdf_url = urllib.parse.urljoin(BASE_URL, decoded_href)
|
| 108 |
|
| 109 |
-
# Si aucun lien PDF n'a été trouvé, lien de recherche
|
| 110 |
if not pdf_url:
|
| 111 |
pdf_url = f"https://www.fao.org/fao-who-codexalimentarius/search/en/?q={full_code.replace(' ', '%20')}"
|
| 112 |
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
is_updated = year == datetime.now().year # Mis à jour cette année
|
| 116 |
|
| 117 |
documents.append({
|
| 118 |
'code': full_code,
|
|
@@ -123,151 +199,411 @@ def extract_documents_from_url(url, category_key):
|
|
| 123 |
'category_name': category_name,
|
| 124 |
'pdf_url': pdf_url,
|
| 125 |
'is_new': is_new,
|
| 126 |
-
'is_updated': is_updated
|
|
|
|
|
|
|
| 127 |
})
|
| 128 |
-
|
| 129 |
return documents
|
| 130 |
|
| 131 |
except Exception as e:
|
| 132 |
st.error(f"Erreur lors de l'extraction de {category_name} : {e}")
|
| 133 |
return []
|
| 134 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 135 |
# Initialisation de l'état de session
|
| 136 |
if 'documents' not in st.session_state:
|
| 137 |
st.session_state.documents = []
|
| 138 |
st.session_state.last_update = None
|
| 139 |
|
| 140 |
-
#
|
| 141 |
-
st.
|
| 142 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 143 |
|
| 144 |
-
# Barre latérale
|
| 145 |
with st.sidebar:
|
| 146 |
-
st.
|
| 147 |
|
| 148 |
-
|
| 149 |
-
|
| 150 |
-
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
|
| 155 |
-
|
| 156 |
-
|
| 157 |
-
|
| 158 |
-
|
| 159 |
-
|
| 160 |
-
|
| 161 |
-
|
| 162 |
-
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
|
| 166 |
-
|
| 167 |
-
|
|
|
|
| 168 |
|
|
|
|
|
|
|
|
|
|
| 169 |
st.divider()
|
| 170 |
-
st.header("🔍 Filtres")
|
| 171 |
|
|
|
|
| 172 |
if st.session_state.documents:
|
| 173 |
-
|
| 174 |
|
| 175 |
-
|
| 176 |
-
|
| 177 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 178 |
|
| 179 |
-
|
| 180 |
-
|
| 181 |
-
|
|
|
|
|
|
|
|
|
|
| 182 |
|
| 183 |
-
|
| 184 |
-
|
| 185 |
-
|
| 186 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 187 |
|
| 188 |
-
|
| 189 |
-
|
| 190 |
|
| 191 |
-
|
| 192 |
-
|
| 193 |
|
| 194 |
-
|
| 195 |
-
|
|
|
|
| 196 |
|
| 197 |
-
|
| 198 |
-
|
|
|
|
| 199 |
|
| 200 |
-
|
| 201 |
-
|
| 202 |
|
| 203 |
-
|
| 204 |
-
|
| 205 |
|
| 206 |
-
|
| 207 |
-
|
| 208 |
-
|
| 209 |
-
|
| 210 |
-
|
| 211 |
-
|
| 212 |
-
# Stocker le DataFrame filtré dans st.session_state pour l'utiliser ailleurs
|
| 213 |
-
st.session_state.filtered_df = filtered_df
|
| 214 |
-
else:
|
| 215 |
-
st.info("Chargez les documents pour activer les filtres.")
|
| 216 |
|
| 217 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 218 |
if st.session_state.documents:
|
| 219 |
df_display = st.session_state.get('filtered_df', pd.DataFrame(st.session_state.documents))
|
| 220 |
-
|
| 221 |
-
# Trier par année (desc) puis code
|
| 222 |
df_display = df_display.sort_values(by=['year', 'code'], ascending=[False, True]).reset_index(drop=True)
|
| 223 |
|
| 224 |
-
|
| 225 |
-
st.
|
| 226 |
|
| 227 |
-
|
| 228 |
-
|
| 229 |
-
|
| 230 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 231 |
|
| 232 |
with col1:
|
| 233 |
-
|
| 234 |
-
|
| 235 |
-
|
| 236 |
-
|
| 237 |
-
|
| 238 |
-
|
| 239 |
-
|
| 240 |
-
|
| 241 |
-
|
| 242 |
-
st.markdown(f"**{doc['title']}**")
|
| 243 |
-
st.caption(f"🏢 Comité: {doc['committee']} | 📅 Année: {doc['year']}")
|
| 244 |
|
| 245 |
with col2:
|
| 246 |
-
|
| 247 |
-
st.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 248 |
|
| 249 |
-
|
| 250 |
-
|
| 251 |
-
|
| 252 |
-
st.divider()
|
| 253 |
-
st.subheader("💾 Exporter les données filtrées")
|
| 254 |
-
col1, col2 = st.columns(2)
|
| 255 |
-
with col1:
|
| 256 |
-
csv = df_display.to_csv(index=False, sep=';')
|
| 257 |
-
st.download_button(
|
| 258 |
-
label="📄 Télécharger en CSV",
|
| 259 |
-
data=csv,
|
| 260 |
-
file_name=f"codex_documents_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv",
|
| 261 |
-
mime="text/csv",
|
| 262 |
-
)
|
| 263 |
-
with col2:
|
| 264 |
-
json_str = df_display.to_json(orient='records', indent=2)
|
| 265 |
-
st.download_button(
|
| 266 |
-
label="📋 Télécharger en JSON",
|
| 267 |
-
data=json_str,
|
| 268 |
-
file_name=f"codex_documents_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json",
|
| 269 |
-
mime="application/json",
|
| 270 |
-
)
|
| 271 |
|
| 272 |
else:
|
| 273 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# codex_app_improved.py
|
| 2 |
import streamlit as st
|
| 3 |
import requests
|
| 4 |
from bs4 import BeautifulSoup
|
|
|
|
| 7 |
from datetime import datetime
|
| 8 |
import urllib.parse
|
| 9 |
import time
|
| 10 |
+
import plotly.express as px
|
| 11 |
+
import plotly.graph_objects as go
|
| 12 |
|
| 13 |
# --- Configuration ---
|
| 14 |
CODEX_CATEGORIES = {
|
| 15 |
'codes': {
|
| 16 |
'name': 'Codes de Pratique (CXC)',
|
| 17 |
'url': 'https://www.fao.org/fao-who-codexalimentarius/codex-texts/codes-of-practice/fr/',
|
| 18 |
+
'prefix': 'CXC',
|
| 19 |
+
'icon': '📋',
|
| 20 |
+
'color': '#FF6B6B'
|
| 21 |
},
|
| 22 |
'standards': {
|
| 23 |
'name': 'Normes (CXS)',
|
| 24 |
'url': 'https://www.fao.org/fao-who-codexalimentarius/codex-texts/list-standards/fr/',
|
| 25 |
+
'prefix': 'CXS',
|
| 26 |
+
'icon': '⚖️',
|
| 27 |
+
'color': '#4ECDC4'
|
| 28 |
},
|
| 29 |
'guidelines': {
|
| 30 |
'name': 'Directives (CXG)',
|
| 31 |
'url': 'https://www.fao.org/fao-who-codexalimentarius/codex-texts/guidelines/fr/',
|
| 32 |
+
'prefix': 'CXG',
|
| 33 |
+
'icon': '📖',
|
| 34 |
+
'color': '#45B7D1'
|
| 35 |
}
|
|
|
|
| 36 |
}
|
| 37 |
|
| 38 |
HEADERS = {
|
|
|
|
| 40 |
}
|
| 41 |
TIMEOUT = 30
|
| 42 |
BASE_URL = "https://www.fao.org"
|
|
|
|
| 43 |
|
| 44 |
# Configuration de la page
|
| 45 |
+
st.set_page_config(
|
| 46 |
+
page_title="Codex Alimentarius Monitor",
|
| 47 |
+
page_icon="🔬",
|
| 48 |
+
layout="wide",
|
| 49 |
+
initial_sidebar_state="expanded"
|
| 50 |
+
)
|
| 51 |
|
| 52 |
+
# CSS personnalisé pour améliorer le design
|
| 53 |
+
st.markdown("""
|
| 54 |
+
<style>
|
| 55 |
+
.main-header {
|
| 56 |
+
background: linear-gradient(90deg, #667eea 0%, #764ba2 100%);
|
| 57 |
+
padding: 2rem;
|
| 58 |
+
border-radius: 10px;
|
| 59 |
+
margin-bottom: 2rem;
|
| 60 |
+
color: white;
|
| 61 |
+
text-align: center;
|
| 62 |
+
}
|
| 63 |
+
.metric-container {
|
| 64 |
+
background: white;
|
| 65 |
+
padding: 1.5rem;
|
| 66 |
+
border-radius: 10px;
|
| 67 |
+
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
|
| 68 |
+
text-align: center;
|
| 69 |
+
margin-bottom: 1rem;
|
| 70 |
+
}
|
| 71 |
+
.category-card {
|
| 72 |
+
background: linear-gradient(135deg, #f5f7fa 0%, #c3cfe2 100%);
|
| 73 |
+
padding: 1.5rem;
|
| 74 |
+
border-radius: 10px;
|
| 75 |
+
border-left: 5px solid;
|
| 76 |
+
margin-bottom: 1rem;
|
| 77 |
+
transition: transform 0.2s;
|
| 78 |
+
}
|
| 79 |
+
.category-card:hover {
|
| 80 |
+
transform: translateY(-2px);
|
| 81 |
+
box-shadow: 0 4px 8px rgba(0,0,0,0.15);
|
| 82 |
+
}
|
| 83 |
+
.document-card {
|
| 84 |
+
background: white;
|
| 85 |
+
padding: 1.5rem;
|
| 86 |
+
border-radius: 10px;
|
| 87 |
+
border: 1px solid #e0e0e0;
|
| 88 |
+
margin-bottom: 1rem;
|
| 89 |
+
transition: all 0.2s;
|
| 90 |
+
}
|
| 91 |
+
.document-card:hover {
|
| 92 |
+
box-shadow: 0 4px 12px rgba(0,0,0,0.15);
|
| 93 |
+
border-color: #667eea;
|
| 94 |
+
}
|
| 95 |
+
.status-badge {
|
| 96 |
+
padding: 0.25rem 0.75rem;
|
| 97 |
+
border-radius: 20px;
|
| 98 |
+
font-size: 0.8rem;
|
| 99 |
+
font-weight: bold;
|
| 100 |
+
margin: 0.25rem;
|
| 101 |
+
display: inline-block;
|
| 102 |
+
}
|
| 103 |
+
.badge-new {
|
| 104 |
+
background-color: #d4edda;
|
| 105 |
+
color: #155724;
|
| 106 |
+
border: 1px solid #c3e6cb;
|
| 107 |
+
}
|
| 108 |
+
.badge-updated {
|
| 109 |
+
background-color: #cce5ff;
|
| 110 |
+
color: #004085;
|
| 111 |
+
border: 1px solid #b3d9ff;
|
| 112 |
+
}
|
| 113 |
+
.badge-category {
|
| 114 |
+
background-color: #f8f9fa;
|
| 115 |
+
color: #495057;
|
| 116 |
+
border: 1px solid #dee2e6;
|
| 117 |
+
}
|
| 118 |
+
.filter-section {
|
| 119 |
+
background: #f8f9fa;
|
| 120 |
+
padding: 1rem;
|
| 121 |
+
border-radius: 10px;
|
| 122 |
+
margin-bottom: 1rem;
|
| 123 |
+
}
|
| 124 |
+
.sidebar .stSelectbox > div > div > div {
|
| 125 |
+
background-color: white;
|
| 126 |
+
}
|
| 127 |
+
</style>
|
| 128 |
+
""", unsafe_allow_html=True)
|
| 129 |
+
|
| 130 |
+
@st.cache_data(ttl=1800)
|
| 131 |
def extract_documents_from_url(url, category_key):
|
| 132 |
"""
|
| 133 |
Fonction pour extraire les documents d'une catégorie Codex.
|
|
|
|
| 135 |
"""
|
| 136 |
category_info = CODEX_CATEGORIES[category_key]
|
| 137 |
category_name = category_info['name']
|
|
|
|
| 138 |
|
| 139 |
documents = []
|
| 140 |
seen_codes = set()
|
|
|
|
| 146 |
|
| 147 |
tables = soup.find_all('table')
|
| 148 |
if not tables:
|
|
|
|
| 149 |
return documents
|
| 150 |
|
| 151 |
for table in tables:
|
| 152 |
rows = table.find_all('tr')
|
| 153 |
for row in rows:
|
| 154 |
cells = row.find_all(['td', 'th'])
|
|
|
|
| 155 |
if len(cells) >= 5:
|
|
|
|
| 156 |
cell_texts = [cell.get_text(strip=True) for cell in cells[:4]]
|
| 157 |
code_candidate = cell_texts[0] if cell_texts else ""
|
|
|
|
| 158 |
prefix = category_info['prefix']
|
| 159 |
code_match = re.match(rf'^({prefix})\s+([\w\-R]*\d+(?:-\d+)?[R]?)$', code_candidate)
|
| 160 |
|
|
|
|
| 174 |
except ValueError:
|
| 175 |
year = 0
|
| 176 |
|
| 177 |
+
# Extraction du lien PDF
|
|
|
|
| 178 |
pdf_cell = cells[4]
|
| 179 |
pdf_url = None
|
|
|
|
|
|
|
| 180 |
link_tag = pdf_cell.find('a', href=re.compile(r'.*\.pdf', re.IGNORECASE))
|
| 181 |
if link_tag:
|
| 182 |
href = link_tag.get('href')
|
| 183 |
if href:
|
|
|
|
| 184 |
decoded_href = urllib.parse.unquote(href)
|
|
|
|
|
|
|
| 185 |
pdf_url = urllib.parse.urljoin(BASE_URL, decoded_href)
|
| 186 |
|
|
|
|
| 187 |
if not pdf_url:
|
| 188 |
pdf_url = f"https://www.fao.org/fao-who-codexalimentarius/search/en/?q={full_code.replace(' ', '%20')}"
|
| 189 |
|
| 190 |
+
is_new = year >= datetime.now().year - 1
|
| 191 |
+
is_updated = year == datetime.now().year
|
|
|
|
| 192 |
|
| 193 |
documents.append({
|
| 194 |
'code': full_code,
|
|
|
|
| 199 |
'category_name': category_name,
|
| 200 |
'pdf_url': pdf_url,
|
| 201 |
'is_new': is_new,
|
| 202 |
+
'is_updated': is_updated,
|
| 203 |
+
'icon': category_info['icon'],
|
| 204 |
+
'color': category_info['color']
|
| 205 |
})
|
| 206 |
+
|
| 207 |
return documents
|
| 208 |
|
| 209 |
except Exception as e:
|
| 210 |
st.error(f"Erreur lors de l'extraction de {category_name} : {e}")
|
| 211 |
return []
|
| 212 |
|
| 213 |
+
def create_dashboard_metrics(df):
|
| 214 |
+
"""Créer des métriques pour le dashboard"""
|
| 215 |
+
if df.empty:
|
| 216 |
+
return
|
| 217 |
+
|
| 218 |
+
col1, col2, col3, col4 = st.columns(4)
|
| 219 |
+
|
| 220 |
+
with col1:
|
| 221 |
+
st.markdown("""
|
| 222 |
+
<div class="metric-container">
|
| 223 |
+
<h2 style="color: #667eea; margin: 0;">📊</h2>
|
| 224 |
+
<h3 style="margin: 0.5rem 0;">{}</h3>
|
| 225 |
+
<p style="color: #666; margin: 0;">Total Documents</p>
|
| 226 |
+
</div>
|
| 227 |
+
""".format(len(df)), unsafe_allow_html=True)
|
| 228 |
+
|
| 229 |
+
with col2:
|
| 230 |
+
new_docs = len(df[df['is_new']])
|
| 231 |
+
st.markdown("""
|
| 232 |
+
<div class="metric-container">
|
| 233 |
+
<h2 style="color: #28a745; margin: 0;">✨</h2>
|
| 234 |
+
<h3 style="margin: 0.5rem 0;">{}</h3>
|
| 235 |
+
<p style="color: #666; margin: 0;">Nouveaux</p>
|
| 236 |
+
</div>
|
| 237 |
+
""".format(new_docs), unsafe_allow_html=True)
|
| 238 |
+
|
| 239 |
+
with col3:
|
| 240 |
+
updated_docs = len(df[df['is_updated']])
|
| 241 |
+
st.markdown("""
|
| 242 |
+
<div class="metric-container">
|
| 243 |
+
<h2 style="color: #17a2b8; margin: 0;">🔄</h2>
|
| 244 |
+
<h3 style="margin: 0.5rem 0;">{}</h3>
|
| 245 |
+
<p style="color: #666; margin: 0;">Mis à jour</p>
|
| 246 |
+
</div>
|
| 247 |
+
""".format(updated_docs), unsafe_allow_html=True)
|
| 248 |
+
|
| 249 |
+
with col4:
|
| 250 |
+
categories = df['category_name'].nunique()
|
| 251 |
+
st.markdown("""
|
| 252 |
+
<div class="metric-container">
|
| 253 |
+
<h2 style="color: #ffc107; margin: 0;">📂</h2>
|
| 254 |
+
<h3 style="margin: 0.5rem 0;">{}</h3>
|
| 255 |
+
<p style="color: #666; margin: 0;">Catégories</p>
|
| 256 |
+
</div>
|
| 257 |
+
""".format(categories), unsafe_allow_html=True)
|
| 258 |
+
|
| 259 |
+
def create_category_overview(df):
|
| 260 |
+
"""Créer un aperçu des catégories"""
|
| 261 |
+
if df.empty:
|
| 262 |
+
return
|
| 263 |
+
|
| 264 |
+
st.subheader("📋 Aperçu par Catégorie")
|
| 265 |
+
|
| 266 |
+
category_stats = df.groupby(['category_name', 'category']).agg({
|
| 267 |
+
'code': 'count',
|
| 268 |
+
'is_new': 'sum',
|
| 269 |
+
'is_updated': 'sum'
|
| 270 |
+
}).reset_index()
|
| 271 |
+
|
| 272 |
+
for _, row in category_stats.iterrows():
|
| 273 |
+
category_key = row['category']
|
| 274 |
+
category_info = CODEX_CATEGORIES[category_key]
|
| 275 |
+
|
| 276 |
+
st.markdown(f"""
|
| 277 |
+
<div class="category-card" style="border-left-color: {category_info['color']};">
|
| 278 |
+
<div style="display: flex; justify-content: space-between; align-items: center;">
|
| 279 |
+
<div>
|
| 280 |
+
<h4 style="margin: 0; color: #333;">
|
| 281 |
+
{category_info['icon']} {row['category_name']}
|
| 282 |
+
</h4>
|
| 283 |
+
<p style="margin: 0.5rem 0; color: #666;">
|
| 284 |
+
{int(row['code'])} documents •
|
| 285 |
+
{int(row['is_new'])} nouveaux •
|
| 286 |
+
{int(row['is_updated'])} mis à jour
|
| 287 |
+
</p>
|
| 288 |
+
</div>
|
| 289 |
+
<div style="font-size: 2rem; opacity: 0.3;">
|
| 290 |
+
{category_info['icon']}
|
| 291 |
+
</div>
|
| 292 |
+
</div>
|
| 293 |
+
</div>
|
| 294 |
+
""", unsafe_allow_html=True)
|
| 295 |
+
|
| 296 |
+
def create_visualization(df):
|
| 297 |
+
"""Créer des visualisations"""
|
| 298 |
+
if df.empty:
|
| 299 |
+
return
|
| 300 |
+
|
| 301 |
+
st.subheader("📊 Visualisations")
|
| 302 |
+
|
| 303 |
+
col1, col2 = st.columns(2)
|
| 304 |
+
|
| 305 |
+
with col1:
|
| 306 |
+
# Graphique par catégorie
|
| 307 |
+
category_counts = df.groupby(['category_name']).size().reset_index(name='count')
|
| 308 |
+
fig_pie = px.pie(
|
| 309 |
+
category_counts,
|
| 310 |
+
values='count',
|
| 311 |
+
names='category_name',
|
| 312 |
+
title="Répartition par Catégorie",
|
| 313 |
+
color_discrete_sequence=['#FF6B6B', '#4ECDC4', '#45B7D1']
|
| 314 |
+
)
|
| 315 |
+
fig_pie.update_layout(height=400)
|
| 316 |
+
st.plotly_chart(fig_pie, use_container_width=True)
|
| 317 |
+
|
| 318 |
+
with col2:
|
| 319 |
+
# Graphique par année
|
| 320 |
+
year_counts = df[df['year'] > 2000].groupby('year').size().reset_index(name='count')
|
| 321 |
+
fig_bar = px.bar(
|
| 322 |
+
year_counts,
|
| 323 |
+
x='year',
|
| 324 |
+
y='count',
|
| 325 |
+
title="Documents par Année",
|
| 326 |
+
color='count',
|
| 327 |
+
color_continuous_scale='viridis'
|
| 328 |
+
)
|
| 329 |
+
fig_bar.update_layout(height=400)
|
| 330 |
+
st.plotly_chart(fig_bar, use_container_width=True)
|
| 331 |
+
|
| 332 |
+
def display_documents_grid(df):
|
| 333 |
+
"""Afficher les documents dans une grille"""
|
| 334 |
+
if df.empty:
|
| 335 |
+
st.info("Aucun document trouvé avec les filtres sélectionnés.")
|
| 336 |
+
return
|
| 337 |
+
|
| 338 |
+
# Pagination
|
| 339 |
+
docs_per_page = 10
|
| 340 |
+
total_pages = (len(df) - 1) // docs_per_page + 1
|
| 341 |
+
|
| 342 |
+
if 'current_page' not in st.session_state:
|
| 343 |
+
st.session_state.current_page = 1
|
| 344 |
+
|
| 345 |
+
col1, col2, col3 = st.columns([1, 2, 1])
|
| 346 |
+
with col2:
|
| 347 |
+
page = st.selectbox(
|
| 348 |
+
"Page",
|
| 349 |
+
range(1, total_pages + 1),
|
| 350 |
+
index=st.session_state.current_page - 1,
|
| 351 |
+
key="page_selector"
|
| 352 |
+
)
|
| 353 |
+
st.session_state.current_page = page
|
| 354 |
+
|
| 355 |
+
# Documents pour la page actuelle
|
| 356 |
+
start_idx = (page - 1) * docs_per_page
|
| 357 |
+
end_idx = start_idx + docs_per_page
|
| 358 |
+
page_docs = df.iloc[start_idx:end_idx]
|
| 359 |
+
|
| 360 |
+
st.markdown(f"**Affichage de {start_idx + 1}-{min(end_idx, len(df))} sur {len(df)} documents**")
|
| 361 |
+
|
| 362 |
+
for _, doc in page_docs.iterrows():
|
| 363 |
+
# Badges de statut
|
| 364 |
+
badges_html = f"<span class='status-badge badge-category'>{doc['icon']} {doc['category_name']}</span>"
|
| 365 |
+
if doc['is_new']:
|
| 366 |
+
badges_html += "<span class='status-badge badge-new'>✨ NOUVEAU</span>"
|
| 367 |
+
if doc['is_updated']:
|
| 368 |
+
badges_html += "<span class='status-badge badge-updated'>🔄 MIS À JOUR</span>"
|
| 369 |
+
|
| 370 |
+
st.markdown(f"""
|
| 371 |
+
<div class="document-card">
|
| 372 |
+
<div style="display: flex; justify-content: space-between; align-items: start;">
|
| 373 |
+
<div style="flex: 1;">
|
| 374 |
+
<div style="margin-bottom: 0.5rem;">
|
| 375 |
+
{badges_html}
|
| 376 |
+
</div>
|
| 377 |
+
<h4 style="margin: 0.5rem 0; color: #333;">
|
| 378 |
+
{doc['code']} - {doc['title']}
|
| 379 |
+
</h4>
|
| 380 |
+
<p style="color: #666; margin: 0;">
|
| 381 |
+
🏢 Comité: {doc['committee']} • 📅 Année: {doc['year']}
|
| 382 |
+
</p>
|
| 383 |
+
</div>
|
| 384 |
+
</div>
|
| 385 |
+
</div>
|
| 386 |
+
""", unsafe_allow_html=True)
|
| 387 |
+
|
| 388 |
+
col1, col2 = st.columns([3, 1])
|
| 389 |
+
with col2:
|
| 390 |
+
st.link_button(
|
| 391 |
+
"📄 Télécharger PDF",
|
| 392 |
+
doc['pdf_url'],
|
| 393 |
+
type="primary",
|
| 394 |
+
use_container_width=True
|
| 395 |
+
)
|
| 396 |
+
|
| 397 |
# Initialisation de l'état de session
|
| 398 |
if 'documents' not in st.session_state:
|
| 399 |
st.session_state.documents = []
|
| 400 |
st.session_state.last_update = None
|
| 401 |
|
| 402 |
+
# Interface utilisateur principale
|
| 403 |
+
st.markdown("""
|
| 404 |
+
<div class="main-header">
|
| 405 |
+
<h1 style="margin: 0;">🔬 Codex Alimentarius Monitor</h1>
|
| 406 |
+
<p style="margin: 0.5rem 0 0 0; opacity: 0.9;">
|
| 407 |
+
Exploration et suivi des normes alimentaires internationales
|
| 408 |
+
</p>
|
| 409 |
+
</div>
|
| 410 |
+
""", unsafe_allow_html=True)
|
| 411 |
|
| 412 |
+
# Barre latérale améliorée
|
| 413 |
with st.sidebar:
|
| 414 |
+
st.markdown("### 🎛️ Centre de Contrôle")
|
| 415 |
|
| 416 |
+
# Section de chargement des données
|
| 417 |
+
with st.container():
|
| 418 |
+
st.markdown("#### 📊 Données")
|
| 419 |
+
if st.button("🔄 Actualiser les Documents", type="primary", use_container_width=True):
|
| 420 |
+
with st.spinner("🔍 Extraction en cours..."):
|
| 421 |
+
all_documents = []
|
| 422 |
+
progress_bar = st.progress(0)
|
| 423 |
+
status_container = st.container()
|
| 424 |
+
|
| 425 |
+
for i, (cat_key, cat_info) in enumerate(CODEX_CATEGORIES.items()):
|
| 426 |
+
with status_container:
|
| 427 |
+
st.info(f"{cat_info['icon']} Extraction de {cat_info['name']}...")
|
| 428 |
+
docs = extract_documents_from_url(cat_info['url'], cat_key)
|
| 429 |
+
all_documents.extend(docs)
|
| 430 |
+
progress_bar.progress((i + 1) / len(CODEX_CATEGORIES))
|
| 431 |
+
time.sleep(0.5)
|
| 432 |
+
|
| 433 |
+
st.session_state.documents = all_documents
|
| 434 |
+
st.session_state.last_update = datetime.now()
|
| 435 |
+
status_container.empty()
|
| 436 |
+
st.success("✅ Données actualisées!")
|
| 437 |
|
| 438 |
+
if st.session_state.last_update:
|
| 439 |
+
st.caption(f"🕒 Dernière mise à jour: {st.session_state.last_update.strftime('%d/%m/%Y à %H:%M')}")
|
| 440 |
+
|
| 441 |
st.divider()
|
|
|
|
| 442 |
|
| 443 |
+
# Filtres avancés
|
| 444 |
if st.session_state.documents:
|
| 445 |
+
st.markdown("#### 🔍 Filtres Avancés")
|
| 446 |
|
| 447 |
+
with st.container():
|
| 448 |
+
df_all = pd.DataFrame(st.session_state.documents)
|
| 449 |
+
|
| 450 |
+
# Filtre par catégorie avec icônes
|
| 451 |
+
categories = ['🌐 Toutes les catégories'] + [f"{CODEX_CATEGORIES[cat]['icon']} {name}"
|
| 452 |
+
for cat, name in df_all.groupby('category')['category_name'].first().items()]
|
| 453 |
+
selected_category = st.selectbox("Catégorie:", categories)
|
| 454 |
+
|
| 455 |
+
# Filtre par comité
|
| 456 |
+
committees = ['🏢 Tous les comités'] + sorted([f"🏢 {c}" for c in df_all['committee'].unique()])
|
| 457 |
+
selected_committee = st.selectbox("Comité:", committees)
|
| 458 |
|
| 459 |
+
# Filtres de statut
|
| 460 |
+
col1, col2 = st.columns(2)
|
| 461 |
+
with col1:
|
| 462 |
+
filter_new = st.checkbox("✨ Nouveaux")
|
| 463 |
+
with col2:
|
| 464 |
+
filter_updated = st.checkbox("🔄 Mis à jour")
|
| 465 |
|
| 466 |
+
# Filtre par année
|
| 467 |
+
years = sorted(df_all[df_all['year'] > 0]['year'].unique(), reverse=True)
|
| 468 |
+
if years:
|
| 469 |
+
year_range = st.select_slider(
|
| 470 |
+
"📅 Période:",
|
| 471 |
+
options=years,
|
| 472 |
+
value=(years[-1], years[0])
|
| 473 |
+
)
|
| 474 |
|
| 475 |
+
# Recherche textuelle
|
| 476 |
+
search_term = st.text_input("🔍 Recherche:", placeholder="Code ou titre...")
|
| 477 |
|
| 478 |
+
# Application des filtres
|
| 479 |
+
filtered_df = df_all.copy()
|
| 480 |
|
| 481 |
+
if not selected_category.startswith('🌐'):
|
| 482 |
+
cat_name = selected_category.split(' ', 1)[1]
|
| 483 |
+
filtered_df = filtered_df[filtered_df['category_name'] == cat_name]
|
| 484 |
|
| 485 |
+
if not selected_committee.startswith('🏢 Tous'):
|
| 486 |
+
committee_name = selected_committee.split(' ', 1)[1]
|
| 487 |
+
filtered_df = filtered_df[filtered_df['committee'] == committee_name]
|
| 488 |
|
| 489 |
+
if filter_new:
|
| 490 |
+
filtered_df = filtered_df[filtered_df['is_new']]
|
| 491 |
|
| 492 |
+
if filter_updated:
|
| 493 |
+
filtered_df = filtered_df[filtered_df['is_updated']]
|
| 494 |
|
| 495 |
+
if 'year_range' in locals() and years:
|
| 496 |
+
filtered_df = filtered_df[
|
| 497 |
+
(filtered_df['year'] >= year_range[0]) &
|
| 498 |
+
(filtered_df['year'] <= year_range[1])
|
| 499 |
+
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 500 |
|
| 501 |
+
if search_term:
|
| 502 |
+
filtered_df = filtered_df[
|
| 503 |
+
filtered_df['title'].str.contains(search_term, case=False, na=False) |
|
| 504 |
+
filtered_df['code'].str.contains(search_term, case=False, na=False)
|
| 505 |
+
]
|
| 506 |
+
|
| 507 |
+
st.session_state.filtered_df = filtered_df
|
| 508 |
+
|
| 509 |
+
st.markdown(f"**📊 {len(filtered_df)} documents trouvés**")
|
| 510 |
+
|
| 511 |
+
# Contenu principal
|
| 512 |
if st.session_state.documents:
|
| 513 |
df_display = st.session_state.get('filtered_df', pd.DataFrame(st.session_state.documents))
|
|
|
|
|
|
|
| 514 |
df_display = df_display.sort_values(by=['year', 'code'], ascending=[False, True]).reset_index(drop=True)
|
| 515 |
|
| 516 |
+
# Onglets pour différentes vues
|
| 517 |
+
tab1, tab2, tab3, tab4 = st.tabs(["📊 Dashboard", "📋 Aperçu", "📈 Analyses", "📄 Documents"])
|
| 518 |
|
| 519 |
+
with tab1:
|
| 520 |
+
create_dashboard_metrics(df_display)
|
| 521 |
+
create_category_overview(df_display)
|
| 522 |
+
|
| 523 |
+
with tab2:
|
| 524 |
+
st.subheader("📋 Résumé Exécutif")
|
| 525 |
+
if not df_display.empty:
|
| 526 |
+
col1, col2 = st.columns(2)
|
| 527 |
+
with col1:
|
| 528 |
+
st.markdown("##### 📊 Statistiques Générales")
|
| 529 |
+
st.write(f"• **Total documents**: {len(df_display)}")
|
| 530 |
+
st.write(f"• **Nouveaux documents**: {len(df_display[df_display['is_new']])}")
|
| 531 |
+
st.write(f"• **Mis à jour cette année**: {len(df_display[df_display['is_updated']])}")
|
| 532 |
+
st.write(f"• **Période couverte**: {df_display['year'].min()} - {df_display['year'].max()}")
|
| 533 |
+
|
| 534 |
+
with col2:
|
| 535 |
+
st.markdown("##### 🏢 Top 5 Comités")
|
| 536 |
+
top_committees = df_display['committee'].value_counts().head().reset_index()
|
| 537 |
+
for _, row in top_committees.iterrows():
|
| 538 |
+
st.write(f"• **{row['committee']}**: {row['count']} documents")
|
| 539 |
+
|
| 540 |
+
with tab3:
|
| 541 |
+
create_visualization(df_display)
|
| 542 |
+
|
| 543 |
+
with tab4:
|
| 544 |
+
st.subheader(f"📄 Documents ({len(df_display)} résultats)")
|
| 545 |
+
display_documents_grid(df_display)
|
| 546 |
+
|
| 547 |
+
# Options d'export
|
| 548 |
+
if not df_display.empty:
|
| 549 |
+
st.divider()
|
| 550 |
+
st.subheader("💾 Exporter les Données")
|
| 551 |
+
col1, col2, col3 = st.columns(3)
|
| 552 |
|
| 553 |
with col1:
|
| 554 |
+
csv = df_display.to_csv(index=False, sep=';')
|
| 555 |
+
st.download_button(
|
| 556 |
+
label="📊 Télécharger CSV",
|
| 557 |
+
data=csv,
|
| 558 |
+
file_name=f"codex_documents_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv",
|
| 559 |
+
mime="text/csv",
|
| 560 |
+
use_container_width=True
|
| 561 |
+
)
|
|
|
|
|
|
|
|
|
|
| 562 |
|
| 563 |
with col2:
|
| 564 |
+
json_str = df_display.to_json(orient='records', indent=2)
|
| 565 |
+
st.download_button(
|
| 566 |
+
label="📋 Télécharger JSON",
|
| 567 |
+
data=json_str,
|
| 568 |
+
file_name=f"codex_documents_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json",
|
| 569 |
+
mime="application/json",
|
| 570 |
+
use_container_width=True
|
| 571 |
+
)
|
| 572 |
|
| 573 |
+
with col3:
|
| 574 |
+
# Export Excel (nécessiterait openpyxl)
|
| 575 |
+
st.button("📈 Exporter Excel", disabled=True, help="Fonctionnalité à venir")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 576 |
|
| 577 |
else:
|
| 578 |
+
# Page d'accueil avec instructions
|
| 579 |
+
col1, col2, col3 = st.columns([1, 2, 1])
|
| 580 |
+
with col2:
|
| 581 |
+
st.markdown("""
|
| 582 |
+
<div style="text-align: center; padding: 3rem; background: #f8f9fa; border-radius: 10px; margin: 2rem 0;">
|
| 583 |
+
<h2 style="color: #667eea;">🚀 Commencer l'Exploration</h2>
|
| 584 |
+
<p style="color: #666; margin: 1rem 0;">
|
| 585 |
+
Cliquez sur le bouton "Actualiser les Documents" dans la barre latérale
|
| 586 |
+
pour charger les dernières données du Codex Alimentarius.
|
| 587 |
+
</p>
|
| 588 |
+
<div style="margin: 2rem 0;">
|
| 589 |
+
<p style="font-size: 3rem; margin: 0;">📊</p>
|
| 590 |
+
</div>
|
| 591 |
+
</div>
|
| 592 |
+
""", unsafe_allow_html=True)
|
| 593 |
+
|
| 594 |
+
# Informations sur l'application
|
| 595 |
+
with st.expander("ℹ️ À propos de cette application"):
|
| 596 |
+
st.markdown("""
|
| 597 |
+
**Codex Alimentarius Monitor** vous permet de:
|
| 598 |
+
|
| 599 |
+
- 📊 **Explorer** les normes alimentaires internationales
|
| 600 |
+
- 🔍 **Rechercher** et filtrer les documents par catégorie, comité, année
|
| 601 |
+
- 📈 **Visualiser** les tendances et statistiques
|
| 602 |
+
- 📄 **Télécharger** les documents PDF officiels
|
| 603 |
+
- 💾 **Exporter** les données pour analyse externe
|
| 604 |
+
|
| 605 |
+
**Catégories disponibles:**
|
| 606 |
+
- 📋 **Codes de Pratique (CXC)** - Procédures et bonnes pratiques
|
| 607 |
+
- ⚖️ **Normes (CXS)** - Standards alimentaires officiels
|
| 608 |
+
- 📖 **Directives (CXG)** - Lignes directrices et recommandations
|
| 609 |
+
""")
|