Facebook Live Embed Scraper

facebook-live-video-scraper.txt

This script allows you to scrape a Facebook page for live videos, and generate a iframe embed code for your website. It uses Selenium Firefox web driver. You may get banned if you run this too often - this is yet to be seen.

The file `livestream-data.json` will be updated with extra fields if/when a live video is found.

livestream-data.json

{
  "last_updated": 1584600828.746, 
  "pages": [
    {
      "facebook_url": "https://www.facebook.com/newslivetvofficial/", 
      "name": "Test FB Page", 
      "website": "https://example.com/"
    }
  ]
}

scraper.py

import os
import sys
import time
import random
import json
import urllib

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait

# Load data file from disk
data = open('livestream-data.json').read()
data = json.loads(data)

updated = False

fb_embed_template = """<iframe src="https://www.facebook.com/plugins/video.php?href={URL_VIDEO}&show_text=1&width=560" width="560" height="382" style="border:none;overflow:hidden" scrolling="no" frameborder="0" allowTransparency="true" allow="encrypted-media" allowFullScreen="true"></iframe>"""

for page in data['pages']:

    with webdriver.Firefox() as driver:
        wait = WebDriverWait(driver, 10)
        driver.get(page['facebook_url'])

        elements_userContent = driver.find_elements_by_class_name("userContentWrapper")

        # Loop over all userContent, trying to find an <a> tag
        for block in elements_userContent:

            elements = block.find_elements_by_tag_name("a")

            # Loop over all <a> tags, trying to find video
            for e in elements:
                try:

                    if 'video' in e.get_attribute("href"):
                        # Found a video, but need to check it's live
                        parent = e.find_element_by_xpath('..').find_element_by_xpath('..').find_element_by_xpath('..').find_element_by_xpath('..').find_element_by_xpath('..')
                        html = parent.get_attribute("innerHTML")

                        if 'is live now' in html:
                            # Found a live video
                            print "LIVE VIDEO", page['name'], e.get_attribute("href")
                            url = e.get_attribute("href")

                            if "?" in url:
                                url_split = url.split("?")
                                url = url_split[0]

                            page['facebook_live_url'] = url
                            page['facebook_live_last_updated_utc'] = time.time()
                            page['facebook_live_embed'] = fb_embed_template.replace("{URL_VIDEO}", urllib.quote_plus(page['facebook_live_url']))
                            updated = True

                except Exception as e:
                    print "EXCEPTION", e

        # Scroll down the page a bit
        driver.execute_script("window.scrollTo(0, "+str(random.randint(1000, 5000))+")") 

        # Keep the browser window open a short while before closing it
        time.sleep(random.randint(9, 25))

# Update file on disk
if updated is True:
    data['last_updated'] = time.time()
    with open('livestream-data.json', 'w') as f:
        f.write(json.dumps(data, sort_keys=True, indent=2))