Spaces:
Build error
Build error
File size: 3,424 Bytes
ea349e1 abf5754 d52ce34 abf5754 ea349e1 abf5754 d52ce34 abf5754 d52ce34 abf5754 d52ce34 ea349e1 abf5754 ea349e1 d52ce34 abf5754 ea349e1 |
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 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
from flask import Flask, render_template, request, jsonify
from time import sleep
from bs4 import BeautifulSoup
from requests import get
import urllib
app = Flask(__name__)
def _req(term, results, lang, start, proxies, timeout, safe, ssl_verify):
resp = get(
url="https://www.google.com/search",
headers={
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36 Edg/111.0.1661.62"
},
params={
"q": term,
"num": results + 2, # Prevents multiple requests
"hl": lang,
"start": start,
"safe": safe,
},
proxies=proxies,
timeout=timeout,
verify=ssl_verify,
)
resp.raise_for_status()
return resp
class SearchResult:
def __init__(self, url, title, description):
self.url = url
self.title = title
self.description = description
def __repr__(self):
return f"SearchResult(url={self.url}, title={self.title}, description={self.description})"
def to_dict(self): # Add a method to convert to a dictionary
return {
"url": self.url,
"title": self.title,
"description": self.description,
}
def search(term, num_results=10, lang="en", proxy=None, advanced=False, sleep_interval=0, timeout=5, safe="active", ssl_verify=None):
"""Search the Google search engine"""
escaped_term = urllib.parse.quote_plus(term) # make 'site:xxx.xxx.xxx ' works.
# Proxy
proxies = None
if proxy:
if proxy.startswith("https"):
proxies = {"https": proxy}
else:
proxies = {"http": proxy}
# Fetch
start = 0
results = []
while start < num_results:
# Send request
resp = _req(escaped_term, num_results - start,
lang, start, proxies, timeout, safe, ssl_verify)
# Parse
soup = BeautifulSoup(resp.text, "html.parser")
result_block = soup.find_all("div", attrs={"class": "g"})
if len(result_block) == 0:
start += 1
for result in result_block:
# Find link, title, description
link = result.find("a", href=True)
title = result.find("h3")
description_box = result.find(
"div", {"style": "-webkit-line-clamp:2"})
if description_box:
description = description_box.text
if link and title and description:
start += 1
if advanced:
results.append(SearchResult(link["href"], title.text, description))
else:
results.append(link["href"])
sleep(sleep_interval)
return results
@app.route("/", methods=["GET", "POST"])
def index():
return render_template("index.html")
@app.route("/api/search", methods=["GET"])
def perform_search():
search_query = request.args.get("q")
max_results = int(request.args.get("max_results", 10)) # Default to 10 results
search_results = search(term=search_query, num_results=max_results, advanced=True)
# Convert search results to a list of dictionaries
results_json = [result.to_dict() for result in search_results]
return jsonify(results_json)
if __name__ == "__main__":
app.run(debug=True) |