Spaces:
Runtime error
Runtime error
| import requests | |
| from bs4 import BeautifulSoup | |
| import re | |
| def get_image_url(regionCode, taxonCode): | |
| url = f"https://search.macaulaylibrary.org/catalog?regionCode={regionCode}&taxonCode={taxonCode}&sort=rating_rank_desc&mediaType=photo" | |
| response = requests.get(url) | |
| if response.status_code == 200: | |
| soup = BeautifulSoup(response.content, 'html.parser') | |
| script_str = soup.find_all('script') | |
| match = re.search(r'assetId:(\d+),', str(script_str)) | |
| if match: | |
| asset_id = match.group(1) | |
| return asset_id | |
| else: | |
| return None | |
| else: | |
| return None | |
| # Set the URL of the webpage to be scraped | |
| url = "https://search.macaulaylibrary.org/catalog?regionCode=CO-ANT&taxonCode=bertin1&sort=rating_rank_desc&mediaType=photo" | |
| # Send a GET request to the URL | |
| response = requests.get(url) | |
| # Check if the request was successful (status code 200) | |
| if response.status_code == 200: | |
| # print('ok') | |
| # Parse the HTML content | |
| soup = BeautifulSoup(response.content, 'html.parser') | |
| script_str = soup.find_all('script') | |
| with open('prueba4.html', 'w', encoding='utf-8') as f: | |
| f.write(str(script_str)) | |
| # Extract the image URL from the HTML content) | |
| # enlace = soup.find('meta', {'property': 'og:image'})['content'] | |
| enlace = soup.find_all('div', {'id': 'ResultsGallery-row'}) | |
| # Imprimir el enlace | |
| print(enlace) | |
| # with open('prueba2.html', 'w', encoding='utf-8') as f: | |
| # f.write(str(soup)) | |
| #print(soup.prettify()) | |
| # prueba = soup.find_all('div', {'class': 'ResultsGallery'}) | |
| prueba = soup.find_all('script') | |
| # print(str(prueba)) | |
| match = re.search(r'assetId:(\d+),', str(prueba)) | |
| if match: | |
| asset_id = match.group(1) | |
| print(f"Asset ID: {asset_id}") | |
| else: | |
| print("Asset ID not found.") | |
| # --------------- | |
| # with open('prueba.html', 'w', encoding='utf-8') as f: | |
| # f.write(str(prueba)) | |
| # # Now you can use BeautifulSoup to extract information from the HTML | |
| # # For example, let's extract all image URLs | |
| # image_urls = [img['src'] for img in soup.find_all('data-asset-id')] | |
| # # Print the extracted image URLs | |
| # for i, url in enumerate(image_urls, start=1): | |
| # print(f"Image {i}: {url}") | |
| else: | |
| print(f"Failed to retrieve the webpage. Status code: {response.status_code}") |