From 456b2ad33ec4d022be9593fd76c80ba4bab182e0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=90=B3=E5=85=83=E7=9A=93?= <hw@yuanhau.com>
Date: Wed, 14 May 2025 00:17:26 +0800
Subject: [PATCH] Fuck Microsoft, Yahoo news is better to scrape :D

---
 scraping/hot_articles.py |  2 --
 scraping/msn.py          | 57 ++++++++++++++++++++++++++++++++++++++++
 scraping/yahoo.py        | 57 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 114 insertions(+), 2 deletions(-)
 create mode 100644 scraping/msn.py
 create mode 100644 scraping/yahoo.py

diff --git a/scraping/hot_articles.py b/scraping/hot_articles.py
index 58ff574..3113b11 100644
--- a/scraping/hot_articles.py
+++ b/scraping/hot_articles.py
@@ -25,8 +25,6 @@ headers = {
     'User-Agent': 'NewsSceraperBot/1.0 (https://github.com/hpware/news-analyze)'
 }
 
-#url = "https://tw.news.yahoo.com/"
-#url = "https://news.google.com/home?hl=zh-TW&gl=TW&ceid=TW:zh-Hant"
 url = "https://news.google.com/topics/CAAqJQgKIh9DQkFTRVFvSUwyMHZNRFptTXpJU0JYcG9MVlJYS0FBUAE?hl=zh-TW&gl=TW&ceid=TW%3Azh-Hant"
 
 topiccwiz_css = "PO9Zff Ccj79 kUVvS"
diff --git a/scraping/msn.py b/scraping/msn.py
new file mode 100644
index 0000000..c8c0b0a
--- /dev/null
+++ b/scraping/msn.py
@@ -0,0 +1,57 @@
+# BROKEN
+import re
+from urllib.request import urlopen, Request
+import chardet
+from bs4 import BeautifulSoup
+import json
+import psycopg2
+import pandas as pd
+import dotenv
+import os
+import gzip
+import io
+
+# Load environment variables from .env file
+dotenv.load_dotenv()
+
+headers = {
+    #'User-Agent': 'NewsSceraperBot/1.0 (https://github.com/hpware/news-analyze)',
+    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
+    'Accept': '*',
+    'Accept-Language': 'zh-TW,zh;q=0.9,en-US;q=0.8,en;q=0.7',
+    'Accept-Encoding': 'gzip, deflate, br',
+    'Connection': 'keep-alive',
+    'Sec-Fetch-Dest': 'document',
+    'Sec-Fetch-Mode': 'navigate',
+    'Sec-Fetch-Site': 'same-origin',
+    'Cache-Control': 'max-age=0',
+}
+
+
+url = "https://www.msn.com/zh-tw/news/living/%E7%99%BD%E5%A4%A9-%E6%99%9A%E4%B8%8A%E9%81%8B%E5%8B%95%E5%93%AA%E5%80%8B%E5%A5%BD-%E9%86%AB%E6%8F%AD-1%E9%97%9C%E9%8D%B5-%E6%AF%94%E6%8C%91%E6%99%82%E9%96%93%E6%9B%B4%E9%87%8D%E8%A6%81/ar-AA1D4zTQ"
+
+try:
+    req = Request(url, headers=headers)
+    response = urlopen(req)
+    if response.info().get('Content-Encoding') == 'gzip':
+        gzip_file = gzip.GzipFile(fileobj=io.BytesIO(response.read()))
+        html = gzip_file.read().decode('utf-8')
+    else:
+        html = response.read().decode('utf-8')
+    
+    
+    soupsoup = BeautifulSoup(html, "html.parser")
+    soup = soupsoup.find('views-header-wc')
+    # Extract content
+    title = soup.find('h1', class_='viewsHeaderText') 
+    title_text = title.text.strip() if title else "No title found"
+
+    article = soup.find('body', class_="article-body")
+    paragraph = article.text.strip() if article else ""
+    
+    # Print results
+    print(f"Title: {title_text}")
+    print(f"Content: {paragraph}")
+    
+except Exception as e:
+    print(f"Error: {str(e)}")
diff --git a/scraping/yahoo.py b/scraping/yahoo.py
new file mode 100644
index 0000000..1b4f5d3
--- /dev/null
+++ b/scraping/yahoo.py
@@ -0,0 +1,57 @@
+# BROKEN
+import re
+from urllib.request import urlopen, Request
+import chardet
+from bs4 import BeautifulSoup
+import json
+import psycopg2
+import pandas as pd
+import dotenv
+import os
+import gzip
+import io
+
+# Load environment variables from .env file
+dotenv.load_dotenv()
+
+headers = {
+    #'User-Agent': 'NewsSceraperBot/1.0 (https://github.com/hpware/news-analyze)',
+    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
+    'Accept': '*',
+    'Accept-Language': 'zh-TW,zh;q=0.9,en-US;q=0.8,en;q=0.7',
+    'Accept-Encoding': 'gzip, deflate, br',
+    'Connection': 'keep-alive',
+    'Sec-Fetch-Dest': 'document',
+    'Sec-Fetch-Mode': 'navigate',
+    'Sec-Fetch-Site': 'same-origin',
+    'Cache-Control': 'max-age=0',
+}
+
+
+url = "https://tw.news.yahoo.com/%E5%93%BD%E5%92%BD%E7%A8%B1%E8%80%81%E5%90%8C%E5%AD%B8%E6%9D%8E%E6%96%87%E5%AE%97-%E8%A2%AB%E5%86%A4%E7%8D%84-%E6%9F%AF%E6%96%87%E5%93%B2-%E4%BD%A0%E5%80%91%E5%8F%AA%E6%98%AF%E8%A6%81%E6%8A%BC%E6%88%91-%E5%85%B6%E4%BB%96%E5%85%88%E6%94%BE%E8%B5%B0-122535612.html"
+
+try:
+    req = Request(url, headers=headers)
+    response = urlopen(req)
+    if response.info().get('Content-Encoding') == 'gzip':
+        gzip_file = gzip.GzipFile(fileobj=io.BytesIO(response.read()))
+        html = gzip_file.read().decode('utf-8')
+    else:
+        html = response.read().decode('utf-8')
+    
+    
+    soup = BeautifulSoup(html, "html.parser")
+    
+    # Extract content
+    title = soup.find('h1', attrs={"data-test-locator": "headline"}) 
+    title_text = title.text.strip() if title else "No title found"
+
+    article = soup.find('div', class_="caas-body")
+    paragraph = article.text.strip() if article else ""
+    
+    # Print results
+    print(f"Title: {title_text}")
+    print(f"Content: {paragraph}")
+    
+except Exception as e:
+    print(f"Error: {str(e)}")