jgitta/senior-kiosk
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

deploy: randomize and shuffle top RSS feeds

Browse Source
This commit is contained in:
Jozsef Gtta
2026-05-27 14:21:30 +00:00
parent abe61d1156
commit f02ac40b91
1 changed files with 75 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files
browser.py
+75 -51
View File
@@ -4,7 +4,7 @@ SeniorNet Kiosk — PyQt5 single-row floating toolbar over Google Chrome.
Navigation: ◀ ▶ ⌂ icon buttons + ☰ hamburger menu for bookmarks. Navigation: ◀ ▶ ⌂ icon buttons + ☰ hamburger menu for bookmarks.
Chrome is controlled via Chrome DevTools Protocol (CDP) over WebSocket. Chrome is controlled via Chrome DevTools Protocol (CDP) over WebSocket.
""" """
import sys, json, os, subprocess, time, threading, urllib.request, websocket, pathlib, shutil, sqlite3 import sys, json, os, subprocess, time, threading, urllib.request, websocket, pathlib, shutil, sqlite3, random
from PyQt5.QtCore import Qt, QTimer, QPoint, QRect, QEvent from PyQt5.QtCore import Qt, QTimer, QPoint, QRect, QEvent
from PyQt5.QtGui import QFont, QColor, QPalette, QCursor from PyQt5.QtGui import QFont, QColor, QPalette, QCursor
from PyQt5.QtWidgets import ( from PyQt5.QtWidgets import (
@@ -864,15 +864,23 @@ if __name__ == "__main__":
time.sleep(900) time.sleep(900)
def update_news_cache(): def update_news_cache():
"""Fetch top RSS news feeds (BBC, NPR), scrape full article text & images in background, and cache locally.""" """Fetch top RSS news feeds, scrape full article text & images in background, and cache locally with randomized sources."""
import xml.etree.ElementTree as ET import xml.etree.ElementTree as ET
import re import re
cache_file = _HOME / "kiosk-home" / "news-data.json" cache_file = _HOME / "kiosk-home" / "news-data.json"
feeds = { # Expanded catalog of highly reliable news sources
"World News": ("http://feeds.bbci.co.uk/news/world/rss.xml", "BBC News"), world_catalog = [
"National News": ("https://feeds.npr.org/1001/rss.xml", "NPR News") ("http://feeds.bbci.co.uk/news/world/rss.xml", "BBC News"),
} ("https://rss.nytimes.com/services/xml/rss/nyt/World.xml", "New York Times"),
("https://www.aljazeera.com/xml/rss/all.xml", "Al Jazeera")
]
national_catalog = [
("https://feeds.npr.org/1001/rss.xml", "NPR News"),
("https://rss.nytimes.com/services/xml/rss/nyt/US.xml", "New York Times"),
("http://rss.cnn.com/rss/cnn_topstories.rss", "CNN News")
]
def scrape_article(url): def scrape_article(url):
try: try:
@@ -902,7 +910,8 @@ if __name__ == "__main__":
ignore_terms = [ ignore_terms = [
"British Broadcasting Corporation", "Watch Live", "HomeNewsSport", "British Broadcasting Corporation", "Watch Live", "HomeNewsSport",
"Special Series", "Up First", "All Up First Stories", "hide caption", "Special Series", "Up First", "All Up First Stories", "hide caption",
"LISTEN & FOLLOW", "Morning Edition", "Morning news brief", "Podcast" "LISTEN & FOLLOW", "Morning Edition", "Morning news brief", "Podcast",
"New York Times", "NYT", "The Times", "Al Jazeera", "BBC", "CNN"
] ]
if any(term in p_clean for term in ignore_terms): if any(term in p_clean for term in ignore_terms):
continue continue
@@ -916,56 +925,71 @@ if __name__ == "__main__":
return "", "" return "", ""
while True: while True:
# Randomly select 2 World feeds and 2 National feeds to harvest
selected_world = random.sample(world_catalog, 2)
selected_national = random.sample(national_catalog, 2)
feeds = {
"World News": selected_world,
"National News": selected_national
}
payload = {} payload = {}
for category, (url, source_name) in feeds.items(): for category, source_list in feeds.items():
try: category_stories = []
req = urllib.request.Request(url, headers={"User-Agent": "Mozilla/5.0"}) for url, source_name in source_list:
xml_raw = urllib.request.urlopen(req, timeout=12).read() try:
root = ET.fromstring(xml_raw) req = urllib.request.Request(url, headers={"User-Agent": "Mozilla/5.0"})
xml_raw = urllib.request.urlopen(req, timeout=12).read()
stories = [] root = ET.fromstring(xml_raw)
channel = root.find("channel")
if channel is not None: channel = root.find("channel")
# Scrape top 5 rich stories per category to keep it fast if channel is not None:
for idx, item in enumerate(channel.findall("item")): # Fetch top 3 stories per selected feed to compile a rich, diverse set
if idx >= 5: items_harvested = 0
break for item in channel.findall("item"):
title = item.find("title") if items_harvested >= 3:
link = item.find("link") break
pub_date = item.find("pubDate") title = item.find("title")
link = item.find("link")
t_str = title.text.strip() if title is not None and title.text else "" pub_date = item.find("pubDate")
l_str = link.text.strip() if link is not None and link.text else ""
t_str = title.text.strip() if title is not None and title.text else ""
p_str = "" l_str = link.text.strip() if link is not None and link.text else ""
if pub_date is not None and pub_date.text:
try: p_str = ""
p_str = " ".join(pub_date.text.split()[:4]) if pub_date is not None and pub_date.text:
except Exception: try:
p_str = pub_date.text p_str = " ".join(pub_date.text.split()[:4])
except Exception:
# Perform background scraping for full text and image p_str = pub_date.text
full_story, img_url = "", ""
if l_str: # Scrape rich data
full_story, img_url = scrape_article(l_str) full_story, img_url = "", ""
if l_str:
stories.append({ full_story, img_url = scrape_article(l_str)
"title": t_str,
"summary": full_story if full_story else "Click to read the story details.", category_stories.append({
"image": img_url, "title": t_str,
"source": source_name, "summary": full_story if full_story else "Click to read the story details.",
"date": p_str "image": img_url,
}) "source": source_name,
payload[category] = stories "date": p_str
print(f"Successfully cached and scraped {len(stories)} stories for category: {category}") })
except Exception as e: items_harvested += 1
print(f"Failed to fetch RSS category {category}: {e}") print(f"Harvested {items_harvested} stories from {source_name} for {category}")
except Exception as e:
print(f"Failed to harvest RSS feed {source_name} ({url}): {e}")
# Fully randomize/shuffle the compiled stories list so sources are mixed nicely!
random.shuffle(category_stories)
payload[category] = category_stories
if payload: if payload:
try: try:
cache_file.parent.mkdir(parents=True, exist_ok=True) cache_file.parent.mkdir(parents=True, exist_ok=True)
cache_file.write_text(json.dumps(payload, indent=2)) cache_file.write_text(json.dumps(payload, indent=2))
print("Updated local news-data.json cache with full stories successfully") print("Updated local news-data.json cache with randomized shuffled stories successfully")
except Exception as e: except Exception as e:
print(f"Failed to write news cache file: {e}") print(f"Failed to write news cache file: {e}")