app.py

import gradio as gr
import requests
from bs4 import BeautifulSoup
from urllib.parse import quote_plus
import random
import time
import re

USER_AGENTS = [
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0 Safari/605.1.15",
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0"
]

def human_like_delay(min_delay=1, max_delay=3):
    time.sleep(random.uniform(min_delay, max_delay))

def random_query_string(length=10):
    letters = 'abcdefghijklmnopqrstuvwxyz'
    return ''.join(random.choice(letters) for i in range(length))

def natural_search_and_extract(keyword):
    session = requests.Session()
    user_agent = random.choice(USER_AGENTS)
    session.headers.update({
        "User-Agent": user_agent,
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
        "Accept-Language": "ja,en-US;q=0.7,en;q=0.3",
        "Accept-Encoding": "gzip, deflate, br",
        "DNT": "1",
        "Connection": "keep-alive",
        "Upgrade-Insecure-Requests": "1"
    })
    
    search_url = f"https://www.google.com/search?q={quote_plus(keyword)}&hl=ja&{random_query_string()}"
    
    try:
        human_like_delay()
        response = session.get(search_url)
        
        if response.status_code != 200:
            return f"Error: Unable to fetch search results. Status code: {response.status_code}"

        soup = BeautifulSoup(response.text, 'html.parser')
        queries = []

        # 「他の人はこちらも検索」セクションを探す
        related_section = soup.find('span', string=re.compile('他の人はこちらも検索'))
        if related_section:
            parent_div = related_section.find_parent('div')
            if parent_div:
                for b_tag in parent_div.find_all('b'):
                    query_text = b_tag.get_text(strip=True)
                    if query_text and query_text not in queries:
                        queries.append(query_text)
                    human_like_delay(0.5, 1)

        # 結果を整形
        if queries:
            return "\n".join(queries)
        else:
            return f"No related queries found. HTML structure might have changed.\nKeyword searched: {keyword}\nURL: {search_url}\nResponse length: {len(response.text)}"

    except Exception as e:
        return f"An error occurred: {str(e)}"

# Gradioインターフェースの設定
iface = gr.Interface(
    fn=natural_search_and_extract,
    inputs=gr.Textbox(lines=1, label="検索キーワード"),
    outputs=gr.Textbox(label="関連検索キーワード"),
    title="Google検索関連キーワード抽出ツール",
    description="キーワードを入力して、Googleの「他の人はこちらも検索」セクションから関連キーワードを抽出します。"
)

iface.launch()