File size: 14,627 Bytes
cda0cc0
 
ce15e85
 
 
 
 
3eb9780
9e2e26a
 
4773f00
 
 
 
 
 
 
 
 
 
 
 
 
c92a90d
 
4773f00
 
 
 
3e3ad89
4773f00
 
 
 
3602082
4773f00
c92a90d
4773f00
 
 
c92a90d
3602082
4773f00
c92a90d
3e3ad89
4773f00
 
 
 
3602082
4773f00
c92a90d
3e3ad89
4773f00
 
 
9f612cf
 
 
 
d53ca8e
 
 
 
9f612cf
 
d53ca8e
 
 
9f612cf
d53ca8e
b700ceb
c92a90d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60f3847
9f612cf
c92a90d
 
 
9f612cf
 
 
c92a90d
 
 
9f612cf
b700ceb
9f612cf
c92a90d
9f612cf
 
3e3ad89
 
 
 
 
9f612cf
 
eda6dd3
3e3ad89
c92a90d
9f612cf
 
b700ceb
eda6dd3
c92a90d
9f612cf
b700ceb
c92a90d
60f3847
c92a90d
60f3847
c92a90d
b700ceb
 
60f3847
9f612cf
 
 
60f3847
 
 
 
9f612cf
 
 
 
 
 
 
 
def6f3f
9f612cf
 
 
b700ceb
 
 
c92a90d
9f612cf
 
def6f3f
60f3847
def6f3f
60f3847
 
9f612cf
7d230f4
9f612cf
 
 
 
 
c92a90d
9f612cf
 
 
 
ce15e85
 
b700ceb
3602082
 
b700ceb
60f3847
ce15e85
 
60f3847
d53ca8e
ce15e85
60f3847
ce15e85
 
60f3847
7d230f4
ce15e85
b700ceb
ce15e85
 
60f3847
ce15e85
 
 
 
b700ceb
ce15e85
 
 
b700ceb
ce15e85
 
60f3847
b700ceb
ce15e85
3602082
b700ceb
c92a90d
 
 
 
 
 
c9b16b1
c92a90d
 
 
 
b700ceb
ce15e85
 
b700ceb
 
 
 
 
 
c92a90d
 
 
d53ca8e
b700ceb
726835e
 
 
 
 
 
 
 
 
 
 
 
 
 
b700ceb
 
 
 
 
94edb2b
b89c92c
 
94edb2b
b89c92c
94edb2b
 
b89c92c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b700ceb
 
c92a90d
b700ceb
ce15e85
 
3602082
 
b89c92c
3602082
b89c92c
3602082
 
 
 
 
 
 
94edb2b
 
 
 
 
 
 
 
9f612cf
c92a90d
3602082
94edb2b
 
7d230f4
 
 
 
 
 
3602082
 
 
94edb2b
3602082
 
 
 
 
 
7d230f4
 
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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
import os
import requests
import zipfile
import gradio as gr
import shutil
from PIL import Image
import random
import time
import logging

# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

# Configuration
OUTPUT_DIR = "downloaded_images"
IMAGES_DIR = os.path.join(OUTPUT_DIR, "images")
ZIP_FILE = os.path.join(OUTPUT_DIR, "images.zip")

os.makedirs(OUTPUT_DIR, exist_ok=True)

# Constants
ITEMS_PER_PAGE = 40
DAILY_IMAGE_LIMIT = 2000
MAX_PAGES = min(DAILY_IMAGE_LIMIT // ITEMS_PER_PAGE, 10)
IMAGES_PER_ROW = 4
MAX_ROWS = 6
TOTAL_IMAGES = IMAGES_PER_ROW * MAX_ROWS

# API Configurations (Your original keys)
API_CONFIGS = {
    "pexels": {
        "base_url": "https://api.pexels.com/v1/search",
        "headers": {"Authorization": "klHADHclpse2e2xSP9h747AgfE1Rx0wioemGhXYtedjZzvJ1WBUKwz7g"},
        "image_key": ["src", "medium"],
        "result_key": "photos",
        "delay": 2
    },
    "unsplash": {
        "base_url": "https://api.unsplash.com/search/photos",
        "headers": {},
        "image_key": ["urls", "small"],
        "result_key": "results",
        "delay": 2,
        "client_id": "UKkhpD_Rs5-s1gIlVX28iNs_8E4ysPhQniyIpDpKUnU"
    },
    "pixabay": {
        "base_url": "https://pixabay.com/api/",
        "headers": {},
        "image_key": ["webformatURL"],
        "result_key": "hits",
        "delay": 1,
        "api_key": "45122300-cd3621e1539e8e95430ee3efc"
    }
}

def fetch_image_urls(api_name, category, num_images):
    config = API_CONFIGS[api_name]
    num_pages_needed = (num_images + ITEMS_PER_PAGE - 1) // ITEMS_PER_PAGE
    
    # Select random pages to fetch from (no tracking)
    all_pages = list(range(1, MAX_PAGES + 1))
    if len(all_pages) < num_pages_needed:
        logger.warning(f"Insufficient pages available: {len(all_pages)} < {num_pages_needed}")
        return []
    
    selected_pages = random.sample(all_pages, num_pages_needed)
    logger.info(f"Selected pages for {api_name}: {selected_pages}")
    
    image_urls = []
    for page in selected_pages:
        if api_name == "pixabay":
            url = f"{config['base_url']}?key={config['api_key']}&q={category.lower()}&per_page={ITEMS_PER_PAGE}&page={page}"
            params = {}
        elif api_name == "unsplash":
            url = config["base_url"]
            params = {
                "query": category.lower(),
                "per_page": ITEMS_PER_PAGE,
                "page": page,
                "client_id": config["client_id"]
            }
        else:  # pexels
            url = config["base_url"]
            params = {
                "query": category.lower(),
                "per_page": ITEMS_PER_PAGE,
                "page": page
            }

        try:
            logger.info(f"Requesting {url} with params {params} for {api_name}")
            time.sleep(config.get("delay", 0))
            response = requests.get(url, headers=config["headers"], params=params, timeout=10)
            response.raise_for_status()
            data_response = response.json()
            
            results = data_response.get(config["result_key"], [])
            if not results:
                logger.warning(f"No {config['result_key']} in response for {api_name}, page {page}: {data_response}")
                continue
            
            page_urls = []
            for item in results:
                if len(image_urls) >= num_images:
                    break
                image_url = item
                for key in config["image_key"]:
                    image_url = image_url.get(key) if isinstance(image_url, dict) else None
                    if image_url is None:
                        break
                if image_url:
                    page_urls.append(image_url)
                else:
                    logger.warning(f"No image URL found in item for {api_name}: {item}")
            
            if page_urls:
                image_urls.extend(page_urls)
                logger.info(f"Successfully fetched {len(page_urls)} images from page {page} for {api_name}")
            else:
                logger.warning(f"No valid URLs extracted from page {page} for {api_name}")
        except requests.exceptions.RequestException as e:
            logger.error(f"Error fetching page {page} from {api_name}: {e}")
            logger.error(f"Response: {response.text}")
            if response.status_code == 401:
                logger.error(f"401 Unauthorized for {api_name}. Replace API key.")
            elif response.status_code == 429:
                logger.error(f"429 Rate Limit Exceeded for {api_name}. Increase delay or wait.")
            break
    
    logger.info(f"Total URLs fetched for {api_name}: {len(image_urls)}")
    return image_urls[:num_images]

def download_images(image_urls):
    if not image_urls:
        logger.warning("No image URLs provided to download")
        return 0, []
    
    if os.path.exists(IMAGES_DIR):
        shutil.rmtree(IMAGES_DIR)
    os.makedirs(IMAGES_DIR, exist_ok=True)

    downloaded_count = 0
    image_paths = []
    for idx, url in enumerate(image_urls, 1):
        try:
            response = requests.get(url, stream=True, timeout=10)
            response.raise_for_status()
            image_path = os.path.join(IMAGES_DIR, f"img{idx}.jpg")
            with open(image_path, "wb") as f:
                for chunk in response.iter_content(chunk_size=8192):
                    if chunk:
                        f.write(chunk)
            Image.open(image_path).verify()
            downloaded_count += 1
            image_paths.append(image_path)
            logger.info(f"Downloaded {idx}/{len(image_urls)}: {url}")
        except requests.exceptions.RequestException as e:
            logger.error(f"Error downloading {url}: {e}")
        except Exception as e:
            logger.error(f"Invalid image or error saving {url}: {e}")
    
    logger.info(f"Total images downloaded: {downloaded_count}/{len(image_urls)}")
    return downloaded_count, image_paths

def create_zip_file(selected_image_paths):
    if os.path.exists(ZIP_FILE):
        os.remove(ZIP_FILE)
    with zipfile.ZipFile(ZIP_FILE, "w", zipfile.ZIP_DEFLATED) as zipf:
        for image_path in selected_image_paths:
            arcname = os.path.relpath(image_path, OUTPUT_DIR)
            zipf.write(image_path, arcname)
    return ZIP_FILE

def process_and_display(api_name, category, num_images):
    num_images = int(num_images)
    if num_images > TOTAL_IMAGES:
        num_images = TOTAL_IMAGES

    logger.info(f"Starting process for {api_name} with category '{category}' and {num_images} images")
    image_urls = fetch_image_urls(api_name, category, num_images)
    if not image_urls:
        logger.warning(f"No images fetched from {api_name}")
        return "No images available or API limit reached. Check logs for details.", None, [], [None] * TOTAL_IMAGES, [False] * TOTAL_IMAGES

    logger.info(f"Proceeding to download {len(image_urls)} images from {api_name}")
    downloaded_count, image_paths = download_images(image_urls)
    if downloaded_count == 0:
        logger.warning(f"No images downloaded from {api_name}")
        return "No images were successfully downloaded. Check logs for details.", None, [], [None] * TOTAL_IMAGES, [False] * TOTAL_IMAGES

    status = f"Successfully downloaded {downloaded_count}/{num_images} images from {api_name}. Select images to include in ZIP below."
    image_outputs = [image_paths[i] if i < len(image_paths) else None for i in range(TOTAL_IMAGES)]
    checkbox_outputs = [True if i < len(image_paths) else False for i in range(TOTAL_IMAGES)]
    logger.info(f"Process completed for {api_name}: {downloaded_count} images prepared for display")
    return status, None, image_paths, image_outputs, checkbox_outputs

def process_zip_submission(image_paths, *checkbox_states):
    if not image_paths:
        return "No images available to process.", None
    
    selected_image_paths = [image_paths[i] for i, state in enumerate(checkbox_states) if state]
    if not selected_image_paths:
        return "No images selected for ZIP.", None
    
    zip_path = create_zip_file(selected_image_paths)
    logger.info(f"ZIP file created with {len(selected_image_paths)} images at {zip_path}")
    return f"ZIP file created with {len(selected_image_paths)} images at {zip_path}", zip_path

# Gradio Interface
css = """
    .fetch-button { background-color: #4CAF50; color: white; padding: 10px 20px; border: none; border-radius: 5px; cursor: pointer; }
    .fetch-button:hover { background-color: #45a049; }
    .zip-button { background-color: #2196F3; color: white; padding: 10px 20px; border: none; border-radius: 5px; cursor: pointer; }
    .zip-button:hover { background-color: #1e88e5; }
    .status-box { border: 1px solid #ddd; background-color: #f9f9f9; padding: 10px; border-radius: 5px; }
    .input-group { border: 1px solid #ddd; padding: 15px; border-radius: 5px; background-color: #f0f0f0; }
    .image-container { position: relative; width: 100%; height: 150px; overflow: hidden; border-radius: 5px; }
    .image-container img { width: 100%; height: 100%; object-fit: cover; }
    .overlay { position: absolute; bottom: 5px; right: 5px; background-color: rgba(0, 0, 0, 0.6); padding: 5px; border-radius: 5px; display: flex; align-items: center; gap: 5px; color: white; font-size: 12px; }
    .overlay label { margin: 0; color: white; }
    .overlay input[type="checkbox"] { margin: 0; }
"""

with gr.Blocks(title="Stock Photo Downloader", css=css) as demo:
    gr.Markdown("<h1 style='text-align: center; color: #333;'>📸 Stock Photo Downloader</h1>")
    gr.Markdown("<p style='text-align: center; color: #666;'>Fetch high-quality stock photos from Pexels, Unsplash, and Pixabay.</p>")

    with gr.Group(elem_classes=["input-group"]):
        gr.Markdown("### 🔍 Choose Your Parameters")
        with gr.Row():
            api_input = gr.Dropdown(label="API Source", choices=["pexels", "unsplash", "pixabay"], value="pexels", info="Select the stock photo provider.")
            category_input = gr.Dropdown(label="Category", choices=["nature", "business", "people", "technology", "food", "travel", "animals", "fashion"], value="nature", allow_custom_value=True, info="Choose a category or enter a custom keyword.")
            num_images_input = gr.Dropdown(label="Number of Images (Max 24)", choices=["4", "8", "12", "16", "20", "24"], value="4", info="How many images to fetch (up to 24).")
        download_button = gr.Button("Fetch and Display Images", elem_classes=["fetch-button"])

    # Combine Status and Download sections in a single row with two columns
    with gr.Row():
        with gr.Column():
            gr.Markdown("### 📊 Status")
            status_output = gr.Textbox(
                label="Status",
                interactive=False,
                placeholder="Status updates will appear here...",
                elem_classes=["status-box"],
                show_label=False
            )
        with gr.Column():
            gr.Markdown("### 💾 Download Your Images")
            zip_output = gr.File(label="Download ZIP", visible=False)

    gr.Markdown("### 🖼️ Image Gallery")
    gr.Markdown("<p style='color: #666;'>Select images to include in your ZIP file.</p>")
    image_paths_state = gr.State()

    # Fixed grid layout with dynamically visible rows
    image_outputs = []
    checkbox_outputs = []
    gallery_rows = []
    for row in range(MAX_ROWS):
        with gr.Row(visible=False) as row_component:
            gallery_rows.append(row_component)
            for col in range(IMAGES_PER_ROW):
                idx = row * IMAGES_PER_ROW + col
                with gr.Column(min_width=150):
                    with gr.Group(elem_classes=["image-container"]):
                        image_output = gr.Image(
                            label=f"Image {idx+1}",
                            show_label=False,
                            visible=False,
                            height=150,
                            width=150
                        )
                        with gr.Row(elem_classes=["overlay"]):
                            checkbox_output = gr.Checkbox(
                                label=f"Image {idx+1}",
                                value=False,
                                visible=False,
                                scale=0
                            )
                        image_outputs.append(image_output)
                        checkbox_outputs.append(checkbox_output)

    gr.Markdown("### 📦 Create ZIP File")
    submit_button = gr.Button("Create ZIP of Selected Images", elem_classes=["zip-button"])

    def on_download(api_name, category, num_images):
        status, zip_path, image_paths, image_outs, checkbox_outs = process_and_display(api_name, category, num_images)
        num_downloaded = len(image_paths)
        
        # Update visibility for images and checkboxes
        image_updates = [
            gr.Image(value=img, visible=img is not None, label=f"Image {i+1}", height=150, width=150)
            for i, img in enumerate(image_outs)
        ]
        checkbox_updates = [
            gr.Checkbox(value=chk, visible=i < num_downloaded, label=f"Image {i+1}", scale=0)
            for i, chk in enumerate(checkbox_outs)
        ]
        
        # Update row visibility: show a row only if it contains at least one visible image
        row_updates = []
        for row_idx in range(MAX_ROWS):
            start_idx = row_idx * IMAGES_PER_ROW
            end_idx = start_idx + IMAGES_PER_ROW
            row_has_images = any(image_outs[i] is not None for i in range(start_idx, min(end_idx, len(image_outs))))
            row_updates.append(gr.Row(visible=row_has_images))
        
        return (
            status, zip_path, image_paths,
            *image_updates,
            *checkbox_updates,
            *row_updates
        )
    
    def on_submit(image_paths, *checkbox_states):
        status, zip_path = process_zip_submission(image_paths, *checkbox_states)
        return status, gr.File(value=zip_path, visible=True) if zip_path else gr.File(visible=False)

    download_button.click(
        fn=on_download,
        inputs=[api_input, category_input, num_images_input],
        outputs=[status_output, zip_output, image_paths_state] + image_outputs + checkbox_outputs + gallery_rows
    )
    submit_button.click(
        fn=on_submit,
        inputs=[image_paths_state] + checkbox_outputs,
        outputs=[status_output, zip_output]
    )

demo.launch()