ChatGPT 网页抓取：分步指南

				
					import requests
from bs4 import BeautifulSoup
import csv

# Define the URL of the target website
url = "https://books.toscrape.com/"

# Send a GET request to the website
response = requests.get(url)

# Check if the request was successful
if response.status_code == 200:
    # Parse the HTML content using BeautifulSoup
    soup = BeautifulSoup(response.content, 'html.parser')

    # Find all book containers on the page
    books = soup.select('#default > div > div > div > div > section > div:nth-child(2) > ol > li')

    # Prepare a list to hold the titles and prices
    books_data = []

    for book in books:
        # Extract the title using the specified CSS selector
        title = book.select_one('article > h3 > a')['title']

        # Extract the price using the specified CSS selector
        price = book.select_one('article > div.product_price > p.price_color').text

        # Append the extracted data to the list
        books_data.append([title, price])

    # Define the CSV file to save the data
    csv_file = "books.csv"

    # Save the data to a CSV file
    with open(csv_file, mode='w', newline='', encoding='utf-8') as file:
        writer = csv.writer(file)
        writer.writerow(["Title", "Price"])  # Write the header
        writer.writerows(books_data)  # Write the data rows

    print(f"Data successfully saved to {csv_file}")
else:
    print(f"Failed to retrieve the page. Status code: {response.status_code}")