# **從facebook粉絲團抓取文章**

## 1.匯入函數

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By

from bs4 import BeautifulSoup

import time

## 2.設定變數，用函數把將值填入

# Login with Selenium
FACEBOOK_ID = "[e-mail]"
FACEBOOK_PW = "自行填入"
TARGET_URL = "https://www.facebook.com/groups/pythontw"

options = webdriver.ChromeOptions()
options.add_argument("incognito")

driver = webdriver.Chrome(options = options)
driver.get("https://www.facebook.com")

username = driver.find_element(By.ID, 'email')
username.send_keys(FACEBOOK_ID)
password = driver.find_element(By.ID, 'pass')
password.send_keys(FACEBOOK_PW)
login= driver.find_element(By.NAME,'login')
login.submit()

## 3.登入失敗，連入粉絲團

time.sleep(3) ##等三秒後，連入粉絲團

driver.get(TARGET_URL)

## 4.滑滾輪四次，載入更多文章

time.sleep(3)
for x in range(1, 4):
    driver.execute_script("window.scrollTo(0,document.body.scrollHeight)")
    time.sleep(5)

## 5.用Beautifulsoup抓取文章

# beautifulSoup 接手

# Get source
soup = BeautifulSoup(driver.page_source, 'html.parser')
titles = soup.findAll("div", {"class":  "x11i5rnm xat24cr x1mh8g0r x1vvkbs xdj266r x126k92a"})##facebook的class值一段時間會隨機變換

## 6.印出有幾則文章，從陣列取出文章

print("一共:" + str(len(titles)) + " 則文章...")

for title in titles:##用findAll取值的資料會是陣列，用迭代取值
    posts = title.findAll('div', {'dir': 'auto'})
    for post in posts:
        if post:
            print(post.getText())

    print("----------------------------------------")##用此作分隔線

# Exit
driver.quit()
##關閉webdriver

## 7.Output