diff --git a/scraping/main.py b/scraping/main.py
index 8cec59f..adb1805 100644
--- a/scraping/main.py
+++ b/scraping/main.py
@@ -1,10 +1,12 @@
+# Going to love the stupid tab tab tab tab system, instead of using brances.
import time
import re # Regular expressions
from urllib.request import urlopen # URL request lib.
from bs4 import BeautifulSoup # BeautifulSoup lib.
+import json
headers = {
- 'User-Agent': 'NewsSceraperBot/1.0 (news.yuanhau.com)'
+ 'User-Agent': 'NewsSceraperBot/1.0 (https://github.com/hpware/news-analyze)'
}
#url = "https://tw.news.yahoo.com/"
@@ -14,5 +16,32 @@ page = urlopen(url)
html_bytes = page.read()
html = html_bytes.decode("utf-8")
soup = BeautifulSoup(html, "html.parser")
+hotarticles = soup.find_all("article")
+news_data = []
+for article in hotarticles:
+ try:
+ title_elem = article.find('a', class_='gPFEn')
+ title = title_elem.text.strip() if title_elem else ''
+
+ source_elem = article.find('div', class_='vr1PYe')
+ source = source_elem.text.strip() if source_elem else ''
+
+ link_elem = article.find('a', class_='WwrzSb')
+ orglink = link_elem['href'] if link_elem else ''
+ link = re.sub(r'./read/', 'https://news.google.com/read/', orglink)
+
+ article_data = {
+ 'title': title,
+ 'source': source,
+ 'link': link,
+ }
+
+ news_data.append(article_data)
+
+ except Exception as e:
+ print(f"Error processing article: {e}")
+ continue
+
+with open('news.json', 'w', encoding='utf-8') as f:
+ json.dump(news_data, f, ensure_ascii=False, indent=2)
-print(soup.find_all("article"))
diff --git a/scraping/news.json b/scraping/news.json
index bf4e9b1..23bcd40 100644
--- a/scraping/news.json
+++ b/scraping/news.json
@@ -1 +1,52 @@
-[
2個恐怖組織成印巴衝突導火線 虔誠軍、穆罕默德軍是何來頭？, 印度與巴基斯坦達成全面停火 巴國當局重新開放領空, 演哪齣？印巴互射一輪飛彈互攻 彼此突喊話「收手讓情勢降溫」, 驚傳印軍「飆風戰機飛行員」被俘虜 媒體人訝異1事, 
中美關稅談判在即…川普突發文：對中關稅80%合理 台股周一開盤恐遭波及漲勢疲軟, 結束了？美中瑞士經貿會談 路透：雙方代表團離場, 美中貿易戰僵局終於破冰 雙方代表在日內瓦展開關稅會談, 川普提對中關稅降至80% 中國學者：不可接受| 兩岸, 