data-ad-preview='message' Facebook Selector: Python Scraping Guide

<div role="article" data-ft="{...}">
  <div data-ad-preview="message">
    This is the actual post text content...
  </div>
  <div data-ad-preview="media">
    <!-- image or video content -->
  </div>
  <div data-ad-preview="engagement">
    <!-- likes, comments, shares -->
  </div>
</div>

from bs4 import BeautifulSoup

# After loading page_source from Selenium
soup = BeautifulSoup(driver.page_source, "html.parser")

# Target the data-ad-preview='message' attribute
post_divs = soup.find_all("div", {"data-ad-preview": "message"})

# Extract and clean text
post_text = " ".join([
    div.get_text(strip=True)
    for div in post_divs
])

print(post_text)

def extract_post_text_robust(soup):
"""Try multiple selectors to maximize extraction success"""
selectors = [
    ("div", {"data-ad-preview": "message"}),  # Primary
    ("div", {"class": "x1n2onr6 x1ja2u2z"}),  # Fallback class
    ("div", {"role": "article"}),              # Broad fallback
]

for tag, attrs in selectors:
matches = soup.find_all(tag, attrs)
if matches:
text = " ".join([m.get_text(strip=True) for m in matches])
if text.strip():
return text
return None

# ── IMPORTS ──────────────────────────────────────────────────
import time, os, pandas as pd
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

class FacebookPostScraper:
def __init__(self, email, password):
self.email = email
self.password = password
self.driver = None

def initialize_driver(self):
options = webdriver.EdgeOptions()
options.add_argument("--disable-blink-features=AutomationControlled")
options.add_experimental_option("excludeSwitches", ["enable-automation"])
self.driver = webdriver.Edge(options=options)
self.driver.maximize_window()

def login(self):
self.driver.get("https://www.facebook.com/login")
time.sleep(3)
self.driver.find_element(By.NAME, "email").send_keys(self.email)
self.driver.find_element(By.NAME, "pass").send_keys(self.password)
self.driver.find_element(By.NAME, "login").click()
time.sleep(15)  # Wait for feed + potential 2FA

def extract_post_text(self, post_url):
self.driver.get(post_url)
# Wait for post content to load
WebDriverWait(self.driver, 20).until(
EC.presence_of_element_located((By.XPATH, "//div[@data-ad-preview='message']"))
)
# Parse with BeautifulSoup
soup = BeautifulSoup(self.driver.page_source, "html.parser")
post_divs = soup.find_all("div", {"data-ad-preview": "message"})
text = " ".join([div.get_text(strip=True) for div in post_divs])
return text.strip() if text.strip() else None

def close(self):
if self.driver:
self.driver.quit()

# ── USAGE ────────────────────────────────────────────────────
if __name__ == "__main__":
EMAIL = os.getenv("FB_EMAIL")
PASSWORD = os.getenv("FB_PASSWORD")
scraper = FacebookPostScraper(EMAIL, PASSWORD)
try:
scraper.initialize_driver()
scraper.login()
text = scraper.extract_post_text("https://www.facebook.com/your-target-post")
print("Extracted text:", text)
finally:
scraper.close()