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

Amélioration de l'import des événements avec google calendar

Browse Source
This commit is contained in:
Jean-Marie Favreau 2025-02-09 10:30:08 +01:00
parent d9f4f74937
commit 938ece5326
2 changed files with 31 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
src/agenda_culturel/import_tasks/extractor_ggcal_link.py
View File

@ -14,7 +14,27 @@ logger = logging.getLogger(__name__)
class GoogleCalendarLinkEventExtractor(Extractor):
def __init__(self):
super().__init__()
self.possible_urls = ["https://calendar.google.com/calendar/", "https://addtocalendar.com/"]
self.possible_urls = ["https://calendar.google.com/calendar/", "https://addtocalendar.com/", "https://www.google.com/calendar/event"]
def guess_image(self, soup, url):
image = soup.find("meta", property="og:image")
if image is None:
for img in soup.select('img'):
if img.find_parent(name='nav'):
continue
image = img["src"]
break
else:
image = image["content"]
if image.startswith("/"):
root_url = "https://" + urlparse(url).netloc + "/"
image = root_url + image
return image
def extract(
self, content, url, url_human=None, default_values=None, published=False
@ -40,6 +60,8 @@ class GoogleCalendarLinkEventExtractor(Extractor):
self.set_header(url)
image = self.guess_image(soup, url)
category = None
self.add_event(
@ -57,7 +79,7 @@ class GoogleCalendarLinkEventExtractor(Extractor):
end_day=end_day,
end_time=end_time,
published=published,
image=None,
image=image,
)
break

11
src/agenda_culturel/import_tasks/generic_extractors.py
View File

@ -1,6 +1,8 @@
from abc import abstractmethod
from urllib.parse import urlparse
from urllib.parse import parse_qs
from bs4 import BeautifulSoup
import logging
@ -38,10 +40,11 @@ class GGCalendar:
params = GGCalendar.filter_keys(params)
self.location = params["location"][0] if "location" in params else None
self.title = params["text"][0] if "text" in params else params["title"][0] if "title" in params else None
self.description = params["description"][0] if "description" in params else None
self.location = params["location"][0] if "location" in params else None
self.location = params["location"][0] if "location" in params else ""
self.title = params["text"][0] if "text" in params else params["title"][0] if "title" in params else ""
self.description = params["description"][0] if "description" in params else params["details"][0] if "details" in params else ""
if self.description != "":
self.description = BeautifulSoup(self.description, "html.parser").text
if "dates" in params:
dates = [x.replace(" ", "+") for x in params["dates"][0].split("/")]
if len(dates) > 0: