From 2b5f63240802c8904ca65d1d1e6843efb22170cb Mon Sep 17 00:00:00 2001
From: joey0629 <jjjoey020629@gmail.com>
Date: Wed, 21 Feb 2024 00:01:50 +0800
Subject: [PATCH] bs4 update

---
 main.py | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/main.py b/main.py
index 84c404b..4b21dc4 100644
--- a/main.py
+++ b/main.py
@@ -86,7 +86,16 @@ def start():
     url = "https://www.bea.gov/news/2024/personal-income-and-outlays-december-2023"
     text = find_indicate(url)
     return text
+def find_indicate_bs4(url):
+    from bs4 import BeautifulSoup
+    import requests
+    response = requests.get(url)
+    soup = BeautifulSoup(response.text, 'html.parser')
 
+    # 使用CSS選擇器找到元素
+    element = soup.select("tr",class_ ='item-fact-row' )
+
+    return element[1].text.split('+')[0]+" "+element[1].text.split('+')[1]
 def find_indicate(url):
     from selenium import webdriver
     from selenium.webdriver.common.by import By
@@ -94,7 +103,7 @@ def find_indicate(url):
     import time
     options = Options()
     # options.add_argument("--headless")  # 啟用無頭模式
-    driver = webdriver.Chrome(options=options)
+    driver =webdriver.Chrome(options=options)
     driver.get(url)
     # time.sleep(3)
     chat = driver.find_element(By.XPATH, '//*[@id="home"]/div[2]/div/div/div[1]/table/tbody/tr[13]/td[6]')
@@ -135,7 +144,7 @@ if __name__ == "__main__":
     endtimee = time.time()
     print("Time_NonFarm: ", endtimee-startimee)
     startimee = time.time()
-    print(find_indicate("https://www.bea.gov/news/2024/personal-income-and-outlays-december-2023"))
+    print(find_indicate_bs4("https://www.bea.gov/data/personal-consumption-expenditures-price-index"))
     endtimee = time.time()
     print("Time_NonFarm: ", endtimee-startimee)
     # cfg = Config()