HiAnime Scraper: Structured Anime Catalog and Digital Entertainment Data Extraction

import requests
from bs4 import BeautifulSoup

REQUEST_HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
    "Accept-Language": "en-US,en;q=0.8",
}

def extract_hianime_details(page_url):
    try:
        response = requests.get(
            page_url,
            headers=REQUEST_HEADERS,
            timeout=15
        )
        response.raise_for_status()
    except requests.RequestException:
        return None

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

    title_node = soup.select_one("h1")
    description_node = soup.select_one(".description, .film-description")
    rating_node = soup.select_one(".rating, .film-rating")
    genre_nodes = soup.select(".genres a, .film-genres a")
    episode_node = soup.select_one(".episode-number, .ep-item")

    return {
        "Title": title_node.get_text(strip=True) if title_node else "N/A",
        "Description": description_node.get_text(" ", strip=True)
        if description_node else "N/A",
        "Rating": rating_node.get_text(" ", strip=True)
        if rating_node else "N/A",
        "Genres": [
            genre.get_text(strip=True)
            for genre in genre_nodes
        ] or ["N/A"],
        "Episode_Info": episode_node.get_text(" ", strip=True)
        if episode_node else "N/A"
    }

# Example HiAnime page URL
hianime_url = "https://example.com/anime/sample-title"

anime_data = extract_hianime_details(hianime_url)

if anime_data:
    print(anime_data)
else:
    print("Unable to retrieve anime data.")