PrivateCoffee/wikimore
5
1
Fork 1
Code Issues 11 Pull requests Projects Releases Packages Wiki Activity Actions

fix: handle Unicode in titles and improve error handling

Browse source 
Encoded titles using `quote` to handle Unicode characters correctly in API requests. Added error handling for cases where article content is not found, returning a 404 page with an appropriate message. This ensures a more resilient and user-friendly application.

Fixed #15.
This commit is contained in:
Kumi 2024-08-19 07:27:49 +02:00
parent 5bf7554619
commit 2eeb4d30cf
Signed by: kumi
GPG key ID: ECBCC9082395383F
1 changed files with 14 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
src/wikimore/app.py
View file

@ -1,6 +1,6 @@
from flask import Flask, render_template, request, redirect, url_for from flask import Flask, render_template, request, redirect, url_for
import urllib.request import urllib.request
from urllib.parse import urlencode, urlparse from urllib.parse import urlencode, urlparse, quote
from html import escape from html import escape
import json import json
import os import os
@ -119,11 +119,21 @@ def wiki_article(project, lang, title):
logger.debug(f"Fetching {title} from {base_url}") logger.debug(f"Fetching {title} from {base_url}")
url = f"{base_url}/w/api.php?action=query&format=json&titles={escape(title.replace(' ', '_'), False)}&prop=revisions&rvprop=content&rvparse=1" url = f"{base_url}/w/api.php?action=query&format=json&titles={quote(escape(title.replace(' ', '_'), False))}&prop=revisions&rvprop=content&rvparse=1"
with urllib.request.urlopen(url) as response: with urllib.request.urlopen(url) as response:
data = json.loads(response.read().decode()) data = json.loads(response.read().decode())
pages = data["query"]["pages"] pages = data["query"]["pages"]
article_html = next(iter(pages.values()))["revisions"][0]["*"]
try:
article_html = next(iter(pages.values()))["revisions"][0]["*"]
except KeyError:
return render_template(
"article.html",
title=title.replace("_", " "),
content="Article not found",
wikimedia_projects=app.wikimedia_projects,
languages=app.languages,
), 404
soup = BeautifulSoup(article_html, "html.parser") soup = BeautifulSoup(article_html, "html.parser")
@ -205,7 +215,7 @@ def search_results(project, lang, query):
logger.debug(f"Searching {base_url} for {query}") logger.debug(f"Searching {base_url} for {query}")
srquery = escape(query.replace(" ", "_"), True) srquery = quote(escape(query.replace(" ", "_"), True))
url = ( url = (
f"{base_url}/w/api.php?action=query&format=json&list=search&srsearch={srquery}" f"{base_url}/w/api.php?action=query&format=json&list=search&srsearch={srquery}"