On utilise les classes là où les ids sont multiples (html pas valide)

This commit is contained in:
Jean-Marie Favreau 2024-12-27 16:03:22 +01:00
parent cc0ae8b582
commit 49c7bd5300

View File

@ -109,10 +109,11 @@ class CExtractor(TwoStepsExtractor):
# on ajoute éventuellement les informations complémentaires
d_suite = ""
for d in ["typedesc", "dureedesc", "lieuspec","dureespec","typespec","uncontdroite","datespec"]:
comp_desc = soup.select("#" + d)
for d in ["#typespec", "#dureespec", "#lieuspec", ".lkuncontdroitespec"]:
comp_desc = soup.select(d)
if comp_desc and len(comp_desc) > 0:
d_suite += "\n\n" + comp_desc[0].get_text()
for desc in comp_desc:
d_suite += "\n\n" + desc.get_text()
if d_suite != "":
description += "\n\n> Informations complémentaires:" + d_suite
else: