Implement structural updates and optimizations across multiple modules

README.md

@@ -1,5 +1,7 @@
 # 新聞解析 / News Analyze
 
+![](https://hackatime-badge.hackclub.com/U087ATD163V/news-analyize)
+
 ## Why?
 
 我們使用這個新聞來舉例：

scraping/main.py

@@ -1,7 +1,18 @@
-from urllib.request import urlopen
+import time
+import re # Regular expressions
+from urllib.request import urlopen # URL request lib.
+from bs4 import BeautifulSoup # BeautifulSoup lib.
 
-url = "https://tw.news.yahoo.com/"
+headers = {
+    'User-Agent': 'NewsSceraperBot/1.0 (news.yuanhau.com)'
+}
+
+#url = "https://tw.news.yahoo.com/"
+url = "https://news.google.com/home?hl=zh-TW&gl=TW&ceid=TW:zh-Hant"
 
 page = urlopen(url)
+html_bytes = page.read()
+html = html_bytes.decode("utf-8")
+soup = BeautifulSoup(html, "html.parser")
 
-page
+print(soup.find_all("article"))

scraping/requirements.txt

@@ -1 +1,2 @@
-urlopen
+urlopen
+beautifulsoup4