Spaces:
Runtime error
Runtime error
Upload 3 files
Browse files- WebScout_DDC.py +36 -0
- app_flask.py +46 -0
- requirements.txt +4 -0
WebScout_DDC.py
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from webscout import WEBS
|
| 2 |
+
import requests
|
| 3 |
+
|
| 4 |
+
def websearch_ddc(query, max_results=5, time_limit=5):
|
| 5 |
+
response = requests.get(f"https://oevortex-webscout-api.hf.space/api/search?q={query}&max_results={max_results}&timelimit={time_limit}&safesearch=off®ion=wt-wt")
|
| 6 |
+
return response.json()['results']
|
| 7 |
+
|
| 8 |
+
def attributes_ext(json_data):
|
| 9 |
+
|
| 10 |
+
# Initialize empty lists for each key
|
| 11 |
+
title = []
|
| 12 |
+
href = []
|
| 13 |
+
body = []
|
| 14 |
+
|
| 15 |
+
# Iterate over each item in the list and extract values for each key
|
| 16 |
+
for item in json_data:
|
| 17 |
+
title.append(item['title'])
|
| 18 |
+
href.append(item['href'])
|
| 19 |
+
body.append(item['body'])
|
| 20 |
+
|
| 21 |
+
return title, href, body
|
| 22 |
+
|
| 23 |
+
def main(query, max_results=10):
|
| 24 |
+
|
| 25 |
+
raw_output = websearch_ddc(query, max_results=max_results)
|
| 26 |
+
|
| 27 |
+
titles_list, urls_list, text_list = attributes_ext(raw_output)
|
| 28 |
+
|
| 29 |
+
return titles_list, urls_list, text_list
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
if __name__ == "__main__":
|
| 33 |
+
# Prompt the user for a search query
|
| 34 |
+
query = "ipl 2024"
|
| 35 |
+
titles_list, urls_list, text_list = main(query)
|
| 36 |
+
print(titles_list)
|
app_flask.py
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from flask import Flask, request, jsonify
|
| 2 |
+
import WebScout_DDC
|
| 3 |
+
|
| 4 |
+
app = Flask(__name__)
|
| 5 |
+
|
| 6 |
+
@app.route('/search', methods=['GET'])
|
| 7 |
+
def search():
|
| 8 |
+
|
| 9 |
+
# Extract query parameter
|
| 10 |
+
query = request.args.get('query')
|
| 11 |
+
|
| 12 |
+
# Extract additional parameters
|
| 13 |
+
max_results = int(request.args.get('max_results', 10))
|
| 14 |
+
|
| 15 |
+
if query:
|
| 16 |
+
# Call the main function with the specified parameters
|
| 17 |
+
titles_list, urls_list, text_list = WebScout_DDC.main(
|
| 18 |
+
query,
|
| 19 |
+
max_results=max_results,
|
| 20 |
+
)
|
| 21 |
+
|
| 22 |
+
# Create a dictionary containing the extracted attributes
|
| 23 |
+
response = {
|
| 24 |
+
'titles': titles_list,
|
| 25 |
+
'urls': urls_list,
|
| 26 |
+
'text': text_list
|
| 27 |
+
}
|
| 28 |
+
|
| 29 |
+
# Return the response as prettified JSON
|
| 30 |
+
return jsonify(response), 200, {'Content-Type': 'application/json; charset=utf-8'}
|
| 31 |
+
else:
|
| 32 |
+
error_message = {
|
| 33 |
+
'developer_contact': {
|
| 34 |
+
'telegram': 'https://t.me/DevsDoCode',
|
| 35 |
+
'instagram': 'https://www.instagram.com/sree.shades_/',
|
| 36 |
+
'discord': 'https://discord.gg/ehwfVtsAts',
|
| 37 |
+
'linkedin': 'https://www.linkedin.com/in/developer-sreejan/',
|
| 38 |
+
'twitter': 'https://twitter.com/Anand_Sreejan'
|
| 39 |
+
},
|
| 40 |
+
'error': 'Oops! Something went wrong. Please contact the developer for assistance.'
|
| 41 |
+
}
|
| 42 |
+
return jsonify(error_message), 400
|
| 43 |
+
|
| 44 |
+
if __name__ == '__main__':
|
| 45 |
+
app.run(debug=True)
|
| 46 |
+
# Example Usage : http://127.0.0.1:5000/search?query=python%20tutorial&result_num=20&safe=False&types=web&types=video&extract_webpage=False
|
requirements.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
webscout==1.2.3
|
| 2 |
+
flask==3.0.0
|
| 3 |
+
gunicorn
|
| 4 |
+
orjson
|