Spaces:
Sleeping
Sleeping
File size: 2,774 Bytes
0db0b4e b722bd0 0db0b4e b722bd0 0db0b4e b722bd0 0db0b4e b722bd0 0db0b4e b722bd0 0db0b4e b722bd0 0db0b4e b722bd0 0db0b4e b722bd0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 |
from flask import Flask, request, jsonify
from urllib.parse import quote, urlparse, parse_qs, unquote
import requests
from bs4 import BeautifulSoup
app = Flask(__name__)
def duckduckgo_search(query):
url = 'https://duckduckgo.com/html/'
params = {'q': query}
headers = {'User-Agent': 'Mozilla/5.0'}
response = requests.get(url, params=params, headers=headers)
if response.status_code != 200:
return []
soup = BeautifulSoup(response.text, 'html.parser')
results = []
for result in soup.find_all('div', class_='result'):
title_tag = result.find('a', class_='result__a')
if not title_tag:
continue
title = title_tag.get_text()
link = title_tag['href']
# Decode the actual URL from the DuckDuckGo redirect link
parsed_link = urlparse(link)
query_params = parse_qs(parsed_link.query)
actual_url = unquote(query_params.get('uddg', [''])[0])
description_tag = result.find('a', class_='result__snippet')
description = description_tag.get_text() if description_tag else 'No description available'
# Attempt to fetch the favicon
icon = 'No icon available'
if actual_url:
parsed_actual_url = urlparse(actual_url)
favicon_url = f"{parsed_actual_url.scheme}://{parsed_actual_url.netloc}/favicon.ico"
favicon_response = requests.get(favicon_url, headers=headers)
if favicon_response.status_code == 200:
icon = favicon_url
results.append({
'title': title,
'link': actual_url,
'description': description,
'icon': icon
})
return results
# DuckDuckGo search API
@app.route('/search', methods=['GET'])
def search_duckduckgo():
query = request.args.get('query')
if not query:
return jsonify([]), 400
results = duckduckgo_search(query)
return jsonify(results)
# Google Image Search API
@app.route('/image_search', methods=['GET'])
def get_image_urls():
query = request.args.get('query')
num_images = int(request.args.get('num_images', 10))
if not query:
return jsonify([]), 400
query = quote(query)
url = f"https://www.google.com/search?hl=en&tbm=isch&q={query}"
headers = {"User-Agent": "Mozilla/5.0"}
response = requests.get(url, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
image_urls = []
for img_tag in soup.find_all("img", limit=num_images):
img_url = img_tag.get("src")
if img_url and img_url.startswith("http"):
image_urls.append(img_url)
return jsonify(image_urls)
if __name__ == '__main__':
app.run(host="0.0.0.0", port=7860) |