ShareChat Scraper: Real-Time Extraction of Posts, Hashtags, and User Data

import requests
from bs4 import BeautifulSoup

# Headers to mimic a real browser
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
    "Accept-Language": "en-US,en;q=0.9",
}

def scrape_sharechat_post(url):
    response = requests.get(url, headers=HEADERS)
    if response.status_code != 200:
        print("Failed to fetch page:", response.status_code)
        return None
    
    soup = BeautifulSoup(response.text, "lxml")
    
    # Helper function to safely extract text
    def extract_text(tag, attrs):
        element = soup.find(tag, attrs)
        return element.get_text(strip=True) if element else "N/A"

    # Extract ShareChat post details
    post_data = {
        "Username": extract_text("span", {"class": "user-name"}),
        "Post_Content": extract_text("div", {"class": "post-text"}),
        "Hashtags": [tag.get_text(strip=True) for tag in soup.find_all("a", {"class": "post-hashtag"})] if soup.find_all("a", {"class": "post-hashtag"}) else [],
        "Likes": extract_text("span", {"class": "like-count"}) or "0",
        "Comments": extract_text("span", {"class": "comment-count"}) or "0",
        "Shares": extract_text("span", {"class": "share-count"}) or "0"
    }
    
    return post_data

# Example ShareChat post URL (Replace with actual URL)
sharechat_post_url = "https://www.sharechat.com/post/example"
data_output = scrape_sharechat_post(sharechat_post_url)

# Print extracted data
print(data_output)