jmtrivial/agenda_culturel
4
4
Fork 0
Code Issues 72 Pull Requests 1 Projects 1 Releases Wiki Activity

L'url des images est absolue

Browse Source
This commit is contained in:
Jean-Marie Favreau 2025-01-19 14:20:08 +01:00
parent f48f202e18
commit 9d84f4f630
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/agenda_culturel/import_tasks/custom_extractors/iguana_agenda.py
View File

@ -1,6 +1,7 @@
from ..generic_extractors import * from ..generic_extractors import *
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from datetime import datetime from datetime import datetime
from urllib.parse import urlparse
# A class dedicated to get events from Raymond Bar # A class dedicated to get events from Raymond Bar
# URL: https://www.raymondbar.net/ # URL: https://www.raymondbar.net/
@ -63,6 +64,8 @@ class CExtractor(TwoStepsExtractorNoPause):
published=False, published=False,
): ):
root_address_human = "https://" + urlparse(self.url_human).netloc + "/"
soup = BeautifulSoup(event_content, "xml") soup = BeautifulSoup(event_content, "xml")
@ -71,7 +74,7 @@ class CExtractor(TwoStepsExtractorNoPause):
soup = BeautifulSoup(content, "html.parser") soup = BeautifulSoup(content, "html.parser")
image = soup.select_one(".image img")["src"] image = root_address_human + soup.select_one(".image img")["src"]
description = soup.select_one(".rightcolumn .content").text description = soup.select_one(".rightcolumn .content").text
location = soup.select_one(".infos .location").text location = soup.select_one(".infos .location").text
public = soup.select_one(".infos .public").text public = soup.select_one(".infos .public").text