File size: 5,177 Bytes
b0327be
 
 
 
 
 
 
ad8845e
b0327be
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ad8845e
 
 
b0327be
 
ad8845e
b0327be
ad8845e
b0327be
 
ad8845e
 
b0327be
ad8845e
 
 
 
 
 
 
 
 
 
 
 
b0327be
ad8845e
 
 
 
b0327be
ad8845e
 
b0327be
ad8845e
 
b0327be
ad8845e
 
 
b0327be
ad8845e
 
b0327be
ad8845e
 
 
 
b0327be
ad8845e
 
 
 
 
 
 
 
 
 
 
 
 
 
b0327be
ad8845e
 
 
 
 
 
 
 
 
 
 
 
 
 
b0327be
 
 
ad8845e
 
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
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
import requests
from bs4 import BeautifulSoup
import os
import urllib.request
import json
import time
import random
import gradio as gr
import shutil
import threading

# Hàm lấy gợi ý tìm kiếm từ Google
def get_google_suggestions(query):
    url = f"http://suggestqueries.google.com/complete/search?client=firefox&q={query}"
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"}
    try:
        response = requests.get(url, headers=headers, timeout=5)
        return json.loads(response.text)[1]
    except:
        return []

# Hàm tải ảnh
def download_images(search_term, num_images_per_term, save_folder, status_callback):
    if not os.path.exists(save_folder):
        os.makedirs(save_folder)
    
    search_url = f"https://www.google.com/search?q={search_term}+free&tbm=isch"
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"}
    
    try:
        response = requests.get(search_url, headers=headers, timeout=10)
        response.raise_for_status()
    except:
        status_callback(f"Lỗi truy cập {search_term}")
        return 0

    soup = BeautifulSoup(response.text, 'html.parser')
    img_tags = soup.find_all('img')
    
    count = 0
    for i, img in enumerate(img_tags):
        if count >= num_images_per_term:
            break
        try:
            img_url = img.get('src')
            if img_url and img_url.startswith('http'):
                file_name = f"{save_folder}/{search_term.replace(' ', '_')}_{count}.jpg"
                urllib.request.urlretrieve(img_url, file_name)
                status_callback(f"Đã tải: {file_name}")
                count += 1
                time.sleep(random.uniform(1, 3))
        except Exception as e:
            status_callback(f"Lỗi ảnh {i} ({search_term}): {str(e)}")
            continue
    
    return count

# Hàm nén thư mục
def zip_folder(folder_path):
    output_zip = os.path.join(os.path.dirname(folder_path), "downloaded_images")
    try:
        shutil.make_archive(output_zip, 'zip', folder_path)
        return f"Đã nén thành công: {output_zip}.zip"
    except Exception as e:
        return f"Lỗi khi nén: {str(e)}"

# Hàm chính tải ảnh
def start_download(initial_query, target_images, max_per_term, save_folder):
    status_log = []
    
    def status_callback(message):
        status_log.append(message)
    
    total_downloaded = 0
    current_query = initial_query
    used_queries = set()
    
    while total_downloaded < target_images:
        suggestions = get_google_suggestions(current_query)
        if not suggestions:
            status_callback("Hết gợi ý, dừng lại.")
            break
        
        available_suggestions = [s for s in suggestions if s not in used_queries]
        if not available_suggestions:
            status_callback("Hết gợi ý mới, dừng lại.")
            break
        
        current_query = random.choice(available_suggestions)
        used_queries.add(current_query)
        
        remaining = target_images - total_downloaded
        images_to_download = min(max_per_term, remaining)
        
        status_callback(f"Tìm kiếm: {current_query}")
        downloaded = download_images(current_query, images_to_download, save_folder, status_callback)
        total_downloaded += downloaded
        
        status_callback(f"Tổng: {total_downloaded}/{target_images}")
        time.sleep(random.uniform(2, 5))
    
    status_callback(f"Hoàn tất! Đã tải {total_downloaded} ảnh.")
    status_callback("Đang nén thư mục...")
    zip_result = zip_folder(save_folder)
    status_callback(zip_result)
    
    return "\n".join(status_log)

# Giao diện Gradio
def create_interface():
    with gr.Blocks(title="Image Downloader") as demo:
        gr.Markdown("# Image Downloader")
        gr.Markdown("Tải ảnh từ Google Images và nén thành file zip.")
        
        with gr.Row():
            with gr.Column():
                initial_query = gr.Textbox(label="Từ khóa ban đầu", value="free images")
                target_images = gr.Number(label="Số lượng ảnh cần tải", value=10000, precision=0)
                max_per_term = gr.Number(label="Số ảnh tối đa mỗi từ khóa", value=20, precision=0)
                save_folder = gr.Textbox(label="Thư mục lưu", value="free_images")
            
            with gr.Column():
                output = gr.Textbox(label="Trạng thái", lines=20, interactive=False)
                submit_btn = gr.Button("Bắt đầu tải")
        
        def run_download(query, target, max_term, folder):
            return start_download(query, int(target), int(max_term), folder)
        
        submit_btn.click(
            fn=run_download,
            inputs=[initial_query, target_images, max_per_term, save_folder],
            outputs=output
        )
    
    return demo

# Chạy ứng dụng
if __name__ == "__main__":
    interface = create_interface()
    interface.launch()