cpi update

Dockerfile

@@ -2,7 +2,21 @@ FROM python:3.10
 
 # Install Python and pip
 RUN apt-get update && apt-get install -y python3 python3-pip && apt install nano
-RUN apt-get update && apt-get install -y wget bzip2 libxtst6 libgtk-3-0 libx11-xcb-dev libdbus-glib-1-2 libxt6 libpci-dev && rm -rf /var/lib/apt/lists/*
+
+RUN apt-get update && apt-get install -y \
+    wget unzip \
+    && rm -rf /var/lib/apt/lists/* \
+    && wget https://chromedriver.storage.googleapis.com/114.0.5735.90/chromedriver_linux64.zip \
+    && unzip chromedriver_linux64.zip \
+    && mv chromedriver /usr/local/bin/ \
+    && chmod +x /usr/local/bin/chromedriver
+
+# 安裝Google Chrome
+RUN wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add - \
+    && echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" | tee /etc/apt/sources.list.d/google-chrome.list \
+    && apt-get update && apt-get install -y \
+    google-chrome-stable \
+    && rm -rf /var/lib/apt/lists/*
 # Set the working directory in the container
 WORKDIR /app
 

main.py

@@ -86,14 +86,17 @@ def find_Fomc_bs4(date:str):
 def find_cpi(url):
     from selenium import webdriver
     from selenium.webdriver.common.by import By
-    from selenium.webdriver.firefox.options import Options
+    from selenium.webdriver.chrome.options import Options
+
     from selenium.webdriver.support.ui import WebDriverWait
     from selenium.webdriver.support import expected_conditions as EC
     import time
     print("Start")
     options = Options()
-    options.add_argument("--headless")  # 啟用無頭模式
+    # options.add_argument('--headless')
-    driver = webdriver.Firefox(options = options)
+    options.add_argument('--no-sandbox')
+    options.add_argument('--disable-dev-shm-usage')
+    driver = webdriver.Chrome( options=options)
     driver.get(url)
     # time.sleep(3)
     date = driver.find_element(By.XPATH, '//*[@id="bodytext"]/div[1]/pre[1]').text.split('\n')[6].split("-")[1].split(" ")[1]
@@ -105,9 +108,6 @@ def find_fomc(url,date:str):
     from selenium import webdriver
     from selenium.webdriver.common.by import By
     from selenium.webdriver.firefox.options import Options
-    from selenium.webdriver.support.ui import WebDriverWait
-    from selenium.webdriver.support import expected_conditions as EC
-    import time
     print("Start")
     options = Options()
     options.add_argument("--headless")  # 啟用無頭模式
@@ -121,6 +121,60 @@ def find_fomc(url,date:str):
 
     driver.quit()
     return date , value[0].strip('\n')
+def find_pce(date:str):
+    from selenium import webdriver
+    from selenium.webdriver.common.by import By
+    from selenium.webdriver.chrome.options import Options
+    print("Start")
+    options = Options()
+    options.add_argument("--headless")  # 啟用無頭模式
+    driver = webdriver.Chrome()
+    driver.get(pce_url+date)
+    # time.sleep(3)
+    date = driver.find_element(By.XPATH, '//*[@id="home"]/h1').text.split(' ')[4]
+    value_1 = driver.find_element(By.XPATH, '//*[@id="home"]/div[2]/div/div/p[2]').text
+    value_2 = driver.find_element(By.XPATH, '//*[@id="home"]/div[2]/div/div/div[1]/table/tbody/tr[13]').text.strip(' ').split(' ')[-1]
+    driver.quit()
+    return date , value_1 , value_2
+def find_pce_bs4(date:str):
+    from bs4 import BeautifulSoup
+    import requests
+    response = requests.get(pce_url+date)
+    soup = BeautifulSoup(response.text, 'html.parser')
+    print(soup)
+    # 使用CSS選擇器找到元素
+    time_elements = soup.select('.row release-embargo')
+    value_elements = soup.find_all('div',class_="col-md-12 release-body" )
+    value2_elements = soup.find_all('td',class_="text-left" )
+    print(value_elements)
+    if time_elements:
+        time_text = time_elements[0].text
+        print(time_text)
+        time = time_text.split(' ')[4]
+        print(time)
+    else:
+        time = None
+
+    if value_elements:
+        split_elements = [item.text.split('.') for item in value_elements]
+        print(value_elements)
+        value1 = []
+        for sublist in split_elements:
+            value1.extend(sublist)
+        print(value1)
+
+    else:
+        value1 = None
+    if value2_elements:
+        split_elements = [item.text.split('.') for item in value2_elements]
+        value2 = []
+        for sublist in split_elements:
+            value2.extend(sublist)
+        print(value2)
+
+    else:
+        value2 = None
+    return time, value1 , value2
 #非農就業人數
 def read_pdf_nonfarm(month, year):
     pdf = pdfplumber.open(f"empsit_{month}_{year}.pdf")
@@ -218,26 +272,49 @@ def broadcast_all_bs4_fomc(target:str):
     broadcast_message(
         f"Now :{datetime.fromtimestamp(time.time())} , Spend time :{str(round(endtimee - startimee, 3))} s",
         "-1002033782195")
+def broadcast_all_pce(target:str,date_target:str):
+    startimee = time.time()
+    date, message1, message2 = find_pce(date_target)
+    while date != target:
+        date, message1, message2 = find_pce(date_target)
+    broadcast_message(date+" PCE Data", "-1002033782195")
+    broadcast_message(message1+'\n\n Percent change from month one year ago : '+message2, "-1002033782195")
+    endtimee = time.time()
+    broadcast_message(
+        f"Now :{datetime.fromtimestamp(time.time())} , Spend time :{str(round(endtimee - startimee, 3))} s",
+        "-1002033782195")
+
+def broadcast_all_bs4_pce(target:str):
+    startimee = time.time()
+    date , message = find_pce_bs4('20240131a')
+    while date != target:
+        date, message = find_pce_bs4('20240131a')
+    broadcast_message(date+" PCE Data", "-1002033782195")
+    broadcast_message(message, "-1002033782195")
+    endtimee = time.time()
+    broadcast_message(
+        f"Now :{datetime.fromtimestamp(time.time())} , Spend time :{str(round(endtimee - startimee, 3))} s",
+        "-1002033782195")
 if __name__ == "__main__":
-    global nonfarm_url , cpi_url , fomc_url
+    global nonfarm_url , cpi_url , fomc_url , pce_url
     nonfarm_url = "https://www.bls.gov/news.release/empsit.nr0.htm"
     cpi_url = "https://www.bls.gov/news.release/cpi.nr0.htm"
     fomc_url = "https://www.federalreserve.gov/newsevents/pressreleases/monetary"
-    print("Start Time:" , datetime.fromtimestamp(time.time()))
+    pce_url = "https://www.bea.gov/news/2024/personal-income-and-outlays-"#january-2024
-    schedule.every().day.at("18:00").do(broadcast_all_bs4_fomc, "February")
+    # broadcast_all_pce("February", "february-2024")
-    while True:
+    # print("Start Time:" , datetime.fromtimestamp(time.time()))
-        if datetime.now().strftime("%Y-%m-%d %H:%M") == "2024-03-20 18:00":
+    # schedule.every().day.at("18:39").do(broadcast_all_cpi, "FEBRUARY")
-            schedule.run_pending()
+    # while True:
-        time.sleep(0.1)  # Check every 0.1 seconds
+    #     if datetime.now().strftime("%Y-%m-%d %H:%M") == "2024-04-10 18:39":
+    #         schedule.run_pending()
+    #     time.sleep(0.1)  # Check every 0.1 seconds
     #NonFarm
     # text = download_pdf_nonfarm()
 
     # read_nonfarm(url)
     # print(text)
     #CPI
-
+    date , value = find_cpi(cpi_url)
-    # data, value = find_cpi(cpi_url)
+    print(date)
-    # print(data, value)
+    print(value)
     # broadcast_all_cpi("FEBRUARY")
-    # read_CPI(cpi_url)
-    # broadcast_all_fomc("January")