Scraper version 00

books_scraper.py

@@ -0,0 +1,38 @@
+import requests
+from bs4 import BeautifulSoup
+import pandas as pd
+
+# Base URL from open library
+BASE_URL = "https://openlibrary.org/subjects/"
+
+# Extract an specific genre
+def scrape_books(genre, max_books=50):
+    url = f"{BASE_URL}{genre}.json?limit={max_books}"
+    response = requests.get(url)
+    if response.status_code != 200:
+        print(f"Error accesing website: {response.status_code}")
+        return []
+
+    # Parsear JSON
+    data = response.json()
+    books = []
+    for book in data.get("works", []):
+        books.append({
+            "title": book.get("title", "Unknown"),
+            "author": ", ".join(author["name"] for author in book.get("authors", [])),
+            "year": book.get("first_publish_year", "Unknown"),
+            "genre": genre,
+            "description": book.get("description", {}).get("value", "No description")
+            if isinstance(book.get("description"), dict)
+            else book.get("description", "No description")
+        })
+    return books
+
+# Example: Scraping sci-fi books
+genre = "science_fiction"
+books = scrape_books(genre, max_books=100)
+
+# Save in csv
+df = pd.DataFrame(books)
+df.to_csv(f"books_{genre}.csv", index=False, encoding="utf-8")
+print(f"Data saved in books_{genre}.csv")