setop/agenda_culturel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Amélioration parse du Wix de la puce à l'oreille

Browse Source
This commit is contained in:
Jean-Marie Favreau
2025-04-12 08:33:35 +02:00
parent 516430f9f4
commit b186001132
1 changed files with 6 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/agenda_culturel/import_tasks/custom_extractors/lapucealoreille.py
View File

@@ -31,9 +31,12 @@ class CExtractor(TwoStepsExtractor):
title = soup.select("h2")[0].get_text()
start_day = Extractor.parse_french_date(
soup.select("h2")[1].get_text()
) # pas parfait, mais bordel que ce site est mal construit
# pas parfait, mais bordel que ce site est mal construit
for h2 in range(1, 4):
print(soup.select("h2")[h2].get_text())
start_day = Extractor.parse_french_date(soup.select("h2")[h2].get_text())
if start_day is not None:
break
spans = soup.select("div[data-testid=richTextElement] span")
start_time = None