Douyin Scraper: Real-Time Short Video Content and Engagement Collection

import requests
from bs4 import BeautifulSoup

HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
    "Accept-Language": "en-US,en;q=0.9",
}

def scrape_douyin_profile(url):
    response = requests.get(url, headers=HEADERS, timeout=10)

    if response.status_code != 200:
        return None

    soup = BeautifulSoup(response.text, "html.parser")

    return {
        "Creator": soup.select_one(".author-name").get_text(strip=True) if soup.select_one(".author-name") else "N/A",
        "Followers": soup.select_one(".follower-count").get_text(strip=True) if soup.select_one(".follower-count") else "N/A",
        "Video_Likes": soup.select_one(".like-total").get_text(strip=True) if soup.select_one(".like-total") else "N/A",
        "Hashtag": soup.select_one(".video-hashtag").get_text(strip=True) if soup.select_one(".video-hashtag") else "N/A",
        "Views": soup.select_one(".video-views").get_text(strip=True) if soup.select_one(".video-views") else "N/A"
    }

# Example Douyin profile URL
douyin_profile_url = "https://www.douyin.com/user/example"

profile_data = scrape_douyin_profile(douyin_profile_url)
print(profile_data)