journee_mondiale: restore website scraping

Official UN days are soooo boring…
This commit is contained in:
dece 2022-09-13 18:15:57 +02:00
parent 92f0ab3fef
commit 7f2fa0817e

View file

@ -1,14 +1,24 @@
import datetime
# BS is optional and only for scrapping journee-mondiale.com, thus why we do not
# mark the dependencies flag here.
try:
from bs4 import BeautifulSoup
except ImportError:
BeautifulSoup = None
from edmond.plugin import Plugin
from edmond.utils import http_get
class JourneeMondialePlugin(Plugin):
"""This plugin shows today's international observance.
It used to fetch data from the website journee-mondiale.com but it is
regularly broken so it is now loading a static list as a resource. This
list uses the format "MM-DD Name", one per line, e.g.:
regularly broken so it is now loading a static list as a resource, and the
website is fetched only if the user adds the "jmcom" config value to True.
The local list uses the format "MM-DD Name", one per line, e.g.:
```
01-01 NYE
@ -29,6 +39,22 @@ class JourneeMondialePlugin(Plugin):
if not self.should_handle_command(event.arguments[0], no_content=True):
return False
main_reply = self.get_registered_days()
if main_reply:
self.bot.say(event.target, main_reply)
jmcom_reply = ""
if self.config.get("jmcom", False) is True:
jmcom_reply = self.get_jmcom_days()
if jmcom_reply:
self.bot.say(event.target, jmcom_reply)
if not (main_reply or jmcom_reply):
self.bot.say(event.target, self.config["no_entry_reply"])
return True
def get_registered_days(self) -> str:
"""Get international days for the local list."""
now = datetime.datetime.now()
date_tag = f"{now.month:02}-{now.day:02}"
today_obs = map(
@ -37,8 +63,27 @@ class JourneeMondialePlugin(Plugin):
lambda line: line.startswith(date_tag), self.config["dates"]
),
)
reply = ", ".join(today_obs)
if not reply:
reply = self.config["no_entry_reply"]
self.bot.say(event.target, reply)
return True
days = ", ".join(today_obs)
return reply
def get_jmcom_days(self) -> str:
"""Get international days from journee-mondiale.com."""
response = http_get(self.config["url"])
if not response:
return ""
soup = BeautifulSoup(response, "html.parser")
entries = []
try:
items = soup.find("div", id="journeesDuJour").find_all("article")
for item in items:
entries.append({
"url": item.find("a").href,
"title": item.find("h2").string,
})
except (ValueError, KeyError):
return ""
# TODO add plus plugin support
return ", ".join(map(lambda i: i["title"], entries))