|
| 1 | +import requests |
| 2 | +from bs4 import BeautifulSoup |
| 3 | +import csv |
| 4 | + |
| 5 | +def scrape_website(url): |
| 6 | + # Send a GET request to the URL |
| 7 | + response = requests.get(url) |
| 8 | + |
| 9 | + # Check if request was successful (status code 200) |
| 10 | + if response.status_code == 200: |
| 11 | + # Parse the HTML content of the page |
| 12 | + soup = BeautifulSoup(response.text, 'html.parser') |
| 13 | + |
| 14 | + # Find the elements containing the data you want to extract |
| 15 | + # Replace 'example' with actual HTML tags and classes/IDs |
| 16 | + data_elements = soup.find_all('div', class_='example') |
| 17 | + |
| 18 | + # Extract data from the elements and store in a list of dictionaries |
| 19 | + scraped_data = [] |
| 20 | + for element in data_elements: |
| 21 | + # Example: Extract text from a specific tag within the element |
| 22 | + data = { |
| 23 | + 'title': element.find('h2').text.strip(), |
| 24 | + 'description': element.find('p').text.strip() |
| 25 | + } |
| 26 | + scraped_data.append(data) |
| 27 | + |
| 28 | + return scraped_data |
| 29 | + else: |
| 30 | + print("Error: Failed to fetch website") |
| 31 | + return [] |
| 32 | + |
| 33 | +def save_to_csv(data, filename): |
| 34 | + # Define CSV header based on keys of the first dictionary in the list |
| 35 | + fields = list(data[0].keys()) |
| 36 | + |
| 37 | + # Write data to CSV file |
| 38 | + with open(filename, 'w', newline='') as csvfile: |
| 39 | + writer = csv.DictWriter(csvfile, fieldnames=fields) |
| 40 | + |
| 41 | + # Write header |
| 42 | + writer.writeheader() |
| 43 | + |
| 44 | + # Write rows |
| 45 | + for row in data: |
| 46 | + writer.writerow(row) |
| 47 | + |
| 48 | +def main(): |
| 49 | + url = "https://example.com" |
| 50 | + filename = "data.csv" |
| 51 | + |
| 52 | + # Scrape website |
| 53 | + scraped_data = scrape_website(url) |
| 54 | + |
| 55 | + # Save data to CSV |
| 56 | + save_to_csv(scraped_data, filename) |
| 57 | + |
| 58 | + print(f"Data has been scraped and saved to {filename}") |
| 59 | + |
| 60 | +if __name__ == "__main__": |
| 61 | + main() |
0 commit comments