chat_indicate/main.py

import telebot
from config import Config
import pdfplumber
import time
import requests
from datetime import datetime
import schedule
from bs4 import BeautifulSoup
import requests
from selenium import webdriver
from selenium.webdriver.chrome.service import Service as ChromeService
from webdriver_manager.chrome import ChromeDriverManager



BOT_TOKEN = '6701395239:AAFE30dqvNihDdni9vYoAbWssO-X5yAmwho'
# BOT_TOKEN = "6746720034:AAEMaoV2FwIZ8pz_PF18-bo2a6gFC1eVtVs"
#BOT_TOKEN = '6589162555:AAHGhrTQ0wYNtIUySMohnfpxQl1d6blr24Q'

def broadcast_message(message:str,chat_id:str):
    r = requests.post(f"https://api.telegram.org/bot{BOT_TOKEN}/sendMessage",
        json={
            "chat_id": chat_id,
            "text": message,
        },
    )


def start():
    global startime
    startime = time.time()
    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' )
    print(soup)
    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
    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
    options = Options()
    # options.add_argument("--headless")  # 啟用無頭模式
    driver =webdriver.Chrome(options=options)
    driver.get(url)
    # time.sleep(3)
    date = driver.find_element(By.XPATH, '//*[@id="test"]/div[2]/article/div/div/div[1]/div[2]/div/div[1]/div/table/tbody/tr[1]/td[1]')
    value = driver.find_element(By.XPATH, '//*[@id="test"]/div[2]/article/div/div/div[1]/div[2]/div/div[1]/div/table/tbody/tr[1]/td[2]')
    return date.text , value.text
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.support.ui import WebDriverWait
    from selenium.webdriver.support import expected_conditions as EC
    import time
    options = Options()
    options.add_argument("--headless")  # 啟用無頭模式
    driver = webdriver.Firefox(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]
    value = driver.find_element(By.XPATH, '//*[@id="bodytext"]/div[1]/pre[1]').text.split('\n')[8:12]
    driver.quit()
    return date , value
# 是一個持續運行的迴圈，不斷從Telegram伺服器抓取新的消息
# 然後使用上面定義的消息處理器來處理這些消息。

#非農就業人數
def read_pdf_nonfarm(month, year):
    pdf = pdfplumber.open(f"empsit_{month}_{year}.pdf")
    page = pdf.pages[0]
    text = page.extract_text().split('\n')
    text = (text[7]+text[8]).split(',')
    text = text[0]+text[1]+text[2]
    return text
def download_pdf_nonfarm():
    url = "https://www.bls.gov/news.release/pdf/empsit.pdf"
    response = requests.get(url)

def read_nonfarm(url):
    from bs4 import BeautifulSoup
    import requests
    startimee = time.time()
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')

    # 使用CSS選擇器找到元素
    element = soup.select("div", class_='normalnews')
    print(element[0].text)
    endtimee = time.time()
    print("Time: ", endtimee-startimee)

    return element[0].text
    # print(text.split('\n')[7:9])
def read_CPI(url):

    startimee = time.time()
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')

    # 使用CSS選擇器找到元素
    element = soup.select("div", class_='normalnews')
    print(element[0].text)
    endtimee = time.time()
    print("Time: ", endtimee - startimee)

    return element[0].text
    # print(text.split('\n')[7:9])
def read_PCE():
    message = find_indicate_bs4("https://www.bea.gov/data/income-saving/personal-income")

    return message
def broadcast_all(target:str):
    startimee = time.time()
    message = read_PCE()
    while message.split(' ')[0] != target:
        message = read_PCE()
    broadcast_message(message, "-1002033782195")
    endtimee = time.time()
    broadcast_message(
        f"Now :{datetime.fromtimestamp(time.time())} , Spend time :{str(round(endtimee - startimee, 3))} s",
        "-1002033782195")
def broadcast_all_sele(target:str):
    startimee = time.time()
    date , message = find_indicate("https://www.bea.gov/data/personal-consumption-expenditures-price-index")
    while date.split(' ')[0] != target:
        date ,message = find_indicate("https://www.bea.gov/data/personal-consumption-expenditures-price-index")
    broadcast_message(date+message, "-1002033782195")
    endtimee = time.time()
    broadcast_message(
        f"Now :{datetime.fromtimestamp(time.time())} , Spend time :{str(round(endtimee - startimee, 3))} s",
        "-1002033782195")
def broadcast_all_cpi(target:str):
    startimee = time.time()
    date , message = find_cpi(cpi_url)
    while date != target:
        date, message = find_cpi(cpi_url)
    message= "\n".join(message)
    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
    nonfarm_url = "https://www.bls.gov/news.release/empsit.nr0.htm"
    cpi_url = "https://www.bls.gov/news.release/cpi.nr0.htm"
    print("Start Time:" , datetime.fromtimestamp(time.time()))
    schedule.every().day.at("17:49").do(broadcast_all_cpi, "JANUARY")
    while True:
        if datetime.now().strftime("%Y-%m-%d %H:%M") == "2024-03-12 17:49":
            schedule.run_pending()
        time.sleep(0.1)  # Check every 0.1 seconds
    #NonFarm
    # text = download_pdf_nonfarm()

    # read_nonfarm(url)
    # print(text)
    #CPI

    # data, value = find_cpi(cpi_url)
    # print(data, value)
    # read_CPI(cpi_url)