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

On corrige l'import poulailler

Browse Source 
Fix #132
This commit is contained in:
Jean-Marie Favreau 2025-03-09 14:53:34 +01:00
parent 9dada3e6c2
commit 629a8509cb
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/agenda_culturel/import_tasks/generic_extractors/wordpress_mec.py
View File

@ -1,3 +1,4 @@
import re
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from ..extractor import Extractor from ..extractor import Extractor
@ -33,17 +34,16 @@ class CExtractor(TwoStepsExtractor):
return None, None return None, None
def build_event_url_list(self, content): def build_event_url_list(self, content):
soup = BeautifulSoup(content, "xml") soup = BeautifulSoup(content, "html.parser")
events = soup.select("div.mec-tile-event-content") events = soup.select("div.mec-tile-event-content")
for e in events: for e in events:
link = e.select("h4.mec-event-title a") link = e.select("h4.mec-event-title a")
if len(link) == 1: if len(link) == 1:
url = link[0]["href"] url = link[0]["href"]
title = link[0].get_text() title = link[0].get_text().replace("’", "'")
if self.add_event_url(url): if self.add_event_url(url):
print(url, title)
self.add_event_title(url, title) self.add_event_title(url, title)
categories = e.select(".mec-label-normal") categories = e.select(".mec-label-normal")
@ -64,7 +64,7 @@ class CExtractor(TwoStepsExtractor):
default_values=None, default_values=None,
published=False, published=False,
): ):
soup = BeautifulSoup(event_content, "xml") soup = BeautifulSoup(event_content, "html.parser")
start_day = soup.select(".mec-start-date-label") start_day = soup.select(".mec-start-date-label")
if start_day and len(start_day) > 0: if start_day and len(start_day) > 0:
@ -91,6 +91,7 @@ class CExtractor(TwoStepsExtractor):
description = soup.select(".mec-event-content .mec-single-event-description")[ description = soup.select(".mec-event-content .mec-single-event-description")[
0 0
].get_text(separator=" ") ].get_text(separator=" ")
description = re.sub(r"([ ]*\n)+", "\n", description).strip().replace("’", "'")
url_human = event_url url_human = event_url