File size: 36,294 Bytes
9203871
 
 
 
 
 
 
e42012b
 
 
 
 
9203871
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e42012b
 
 
9203871
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e42012b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3d2be9c
e42012b
 
 
 
 
 
 
 
 
df34cc7
 
e42012b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9203871
7be2df4
9203871
 
 
e42012b
 
9203871
 
 
e40f945
 
 
 
9203871
 
e42012b
 
9203871
 
7be2df4
9203871
7be2df4
e42012b
7be2df4
 
e42012b
7be2df4
e42012b
 
 
7be2df4
 
e42012b
7be2df4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e40f945
 
 
 
7be2df4
 
 
 
 
e40f945
 
 
 
7be2df4
 
 
e42012b
7be2df4
 
9203871
 
e42012b
 
7be2df4
9203871
 
e42012b
 
 
 
 
 
e40f945
 
 
 
9203871
 
7be2df4
9203871
 
e40f945
 
 
 
9203871
 
7be2df4
e40f945
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
08d910a
e40f945
 
08d910a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e40f945
 
 
08d910a
 
 
e40f945
08d910a
 
 
 
 
 
 
 
 
 
 
 
 
 
e40f945
 
08d910a
 
 
 
e40f945
56e62ce
e40f945
56e62ce
e40f945
56e62ce
9203871
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5c27f2d
9203871
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e42012b
e40f945
9203871
 
 
e40f945
9203871
 
e40f945
9203871
e40f945
 
9203871
 
e40f945
08d910a
 
 
 
e42012b
9203871
 
 
 
e40f945
 
08d910a
e40f945
9203871
 
 
08d910a
e40f945
9203871
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56e62ce
71361a4
e40f945
40eeaea
 
 
 
71361a4
 
40eeaea
71361a4
40eeaea
 
71361a4
40eeaea
 
71361a4
 
40eeaea
9203871
 
 
 
 
e40f945
 
 
 
9203871
 
 
 
 
40eeaea
 
 
e40f945
9203871
5c27f2d
 
 
 
 
 
 
 
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
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
import gradio as gr
import requests
import json
import os
from datetime import datetime, timedelta
from huggingface_hub import InferenceClient

from bs4 import BeautifulSoup
import concurrent.futures
import time
import re

MAX_COUNTRY_RESULTS = 100    # ꡭ가별 μ΅œλŒ€ κ²°κ³Ό 수
MAX_GLOBAL_RESULTS = 1000    # 전세계 μ΅œλŒ€ κ²°κ³Ό 수

def create_article_components(max_results):
    article_components = []
    for i in range(max_results):
        with gr.Group(visible=False) as article_group:
            title = gr.Markdown()
            image = gr.Image(width=200, height=150)
            snippet = gr.Markdown()
            info = gr.Markdown()
            
            article_components.append({
                'group': article_group,
                'title': title,
                'image': image,
                'snippet': snippet,
                'info': info,
                'index': i,
            })
    return article_components
    
API_KEY = os.getenv("SERPHOUSE_API_KEY")
hf_client = InferenceClient("CohereForAI/c4ai-command-r-plus-08-2024", token=os.getenv("HF_TOKEN"))

# ꡭ가별 μ–Έμ–΄ μ½”λ“œ λ§€ν•‘
COUNTRY_LANGUAGES = {
    "United States": "en",
    "United Kingdom": "en",
    "Taiwan": "zh-TW",  # λŒ€λ§Œμ–΄(번체 쀑ꡭ어)
    "Canada": "en",
    "Australia": "en",
    "Germany": "de",
    "France": "fr",
    "Japan": "ja",
#    "South Korea": "ko",
    "China": "zh",
    "India": "hi",
    "Brazil": "pt",
    "Mexico": "es",
    "Russia": "ru",
    "Italy": "it",
    "Spain": "es",
    "Netherlands": "nl",
    "Singapore": "en",
    "Hong Kong": "zh-HK",
    "Indonesia": "id",
    "Malaysia": "ms",
    "Philippines": "tl",
    "Thailand": "th",
    "Vietnam": "vi",
    "Belgium": "nl",
    "Denmark": "da",
    "Finland": "fi",
    "Ireland": "en",
    "Norway": "no",
    "Poland": "pl",
    "Sweden": "sv",
    "Switzerland": "de",
    "Austria": "de",
    "Czech Republic": "cs",
    "Greece": "el",
    "Hungary": "hu",
    "Portugal": "pt",
    "Romania": "ro",
    "Turkey": "tr",
    "Israel": "he",
    "Saudi Arabia": "ar",
    "United Arab Emirates": "ar",
    "South Africa": "en",
    "Argentina": "es",
    "Chile": "es",
    "Colombia": "es",
    "Peru": "es",
    "Venezuela": "es",
    "New Zealand": "en",
    "Bangladesh": "bn",
    "Pakistan": "ur",
    "Egypt": "ar",
    "Morocco": "ar",
    "Nigeria": "en",
    "Kenya": "sw",
    "Ukraine": "uk",
    "Croatia": "hr",
    "Slovakia": "sk",
    "Bulgaria": "bg",
    "Serbia": "sr",
    "Estonia": "et",
    "Latvia": "lv",
    "Lithuania": "lt",
    "Slovenia": "sl",
    "Luxembourg": "fr",
    "Malta": "mt",
    "Cyprus": "el",
    "Iceland": "is"
}

COUNTRY_LOCATIONS = {
    "United States": "United States",
    "United Kingdom": "United Kingdom",
    "Taiwan": "Taiwan",  # κ΅­κ°€λͺ… μ‚¬μš©
    "Canada": "Canada",
    "Australia": "Australia",
    "Germany": "Germany",
    "France": "France",
    "Japan": "Japan",
#    "South Korea": "South Korea",
    "China": "China",
    "India": "India",
    "Brazil": "Brazil",
    "Mexico": "Mexico",
    "Russia": "Russia",
    "Italy": "Italy",
    "Spain": "Spain",
    "Netherlands": "Netherlands",
    "Singapore": "Singapore",
    "Hong Kong": "Hong Kong",
    "Indonesia": "Indonesia",
    "Malaysia": "Malaysia",
    "Philippines": "Philippines",
    "Thailand": "Thailand",
    "Vietnam": "Vietnam",
    "Belgium": "Belgium",
    "Denmark": "Denmark",
    "Finland": "Finland",
    "Ireland": "Ireland",
    "Norway": "Norway",
    "Poland": "Poland",
    "Sweden": "Sweden",
    "Switzerland": "Switzerland",
    "Austria": "Austria",
    "Czech Republic": "Czech Republic",
    "Greece": "Greece",
    "Hungary": "Hungary",
    "Portugal": "Portugal",
    "Romania": "Romania",
    "Turkey": "Turkey",
    "Israel": "Israel",
    "Saudi Arabia": "Saudi Arabia",
    "United Arab Emirates": "United Arab Emirates",
    "South Africa": "South Africa",
    "Argentina": "Argentina",
    "Chile": "Chile",
    "Colombia": "Colombia",
    "Peru": "Peru",
    "Venezuela": "Venezuela",
    "New Zealand": "New Zealand",
    "Bangladesh": "Bangladesh",
    "Pakistan": "Pakistan",
    "Egypt": "Egypt",
    "Morocco": "Morocco",
    "Nigeria": "Nigeria",
    "Kenya": "Kenya",
    "Ukraine": "Ukraine",
    "Croatia": "Croatia",
    "Slovakia": "Slovakia",
    "Bulgaria": "Bulgaria",
    "Serbia": "Serbia",
    "Estonia": "Estonia",
    "Latvia": "Latvia",
    "Lithuania": "Lithuania",
    "Slovenia": "Slovenia",
    "Luxembourg": "Luxembourg",
    "Malta": "Malta",
    "Cyprus": "Cyprus",
    "Iceland": "Iceland"
}

MAJOR_COUNTRIES = list(COUNTRY_LOCATIONS.keys())

def translate_query(query, country):
    try:
        # μ˜μ–΄ μž…λ ₯ 확인
        if is_english(query):
            print(f"μ˜μ–΄ 검색어 감지 - 원본 μ‚¬μš©: {query}")
            return query
            
        # μ„ νƒλœ κ΅­κ°€κ°€ λ²ˆμ—­ 지원 ꡭ가인 경우    
        if country in COUNTRY_LANGUAGES:
            # South Korea μ„ νƒμ‹œ ν•œκΈ€ μž…λ ₯은 κ·ΈλŒ€λ‘œ μ‚¬μš©    
            if country == "South Korea":
                print(f"ν•œκ΅­ 선택 - 원본 μ‚¬μš©: {query}")
                return query
                
            target_lang = COUNTRY_LANGUAGES[country]
            print(f"λ²ˆμ—­ μ‹œλ„: {query} -> {country}({target_lang})")
            
            url = f"https://translate.googleapis.com/translate_a/single"
            params = {
                "client": "gtx",
                "sl": "auto",
                "tl": target_lang,
                "dt": "t",
                "q": query
            }
            
            response = requests.get(url, params=params)
            translated_text = response.json()[0][0][0]
            print(f"λ²ˆμ—­ μ™„λ£Œ: {query} -> {translated_text} ({country})")
            return translated_text
            
        return query
        
    except Exception as e:
        print(f"λ²ˆμ—­ 였λ₯˜: {str(e)}")
        return query

def translate_to_korean(text):
    try:
        url = "https://translate.googleapis.com/translate_a/single"
        params = {
            "client": "gtx",
            "sl": "auto",
            "tl": "ko",
            "dt": "t",
            "q": text
        }
        
        response = requests.get(url, params=params)
        translated_text = response.json()[0][0][0]
        return translated_text
    except Exception as e:
        print(f"ν•œκΈ€ λ²ˆμ—­ 였λ₯˜: {str(e)}")
        return text

def is_english(text):
    return all(ord(char) < 128 for char in text.replace(' ', '').replace('-', '').replace('_', ''))
    
def is_korean(text):
    return any('\uAC00' <= char <= '\uD7A3' for char in text)
    
def search_serphouse(query, country, page=1, num_result=10):
    url = "https://api.serphouse.com/serp/live"
    
    now = datetime.utcnow()
    yesterday = now - timedelta(days=1)
    date_range = f"{yesterday.strftime('%Y-%m-%d')},{now.strftime('%Y-%m-%d')}"
    
    translated_query = translate_query(query, country)
    print(f"Original query: {query}")
    print(f"Translated query: {translated_query}")
    
    payload = {
        "data": {
            "q": translated_query,
            "domain": "google.com",
            "loc": COUNTRY_LOCATIONS.get(country, "United States"),
            "lang": COUNTRY_LANGUAGES.get(country, "en"),
            "device": "desktop",
            "serp_type": "news",
            "page": "1",
            "num": "10",
            "date_range": date_range,
            "sort_by": "date"
        }
    }

    headers = {
        "accept": "application/json",
        "content-type": "application/json",
        "authorization": f"Bearer {API_KEY}"
    }

    try:
        response = requests.post(url, json=payload, headers=headers)
        print("Request payload:", json.dumps(payload, indent=2, ensure_ascii=False))
        print("Response status:", response.status_code)
        
        response.raise_for_status()
        return {"results": response.json(), "translated_query": translated_query}
    except requests.RequestException as e:
        return {"error": f"Error: {str(e)}", "translated_query": query}

def format_results_from_raw(response_data):
    if "error" in response_data:
        return "Error: " + response_data["error"], []

    try:
        results = response_data["results"]
        translated_query = response_data["translated_query"]
        
        news_results = results.get('results', {}).get('results', {}).get('news', [])
        if not news_results:
            return "검색 κ²°κ³Όκ°€ μ—†μŠ΅λ‹ˆλ‹€.", []

        articles = []
        for idx, result in enumerate(news_results, 1):
            articles.append({
                "index": idx,
                "title": result.get("title", "제λͺ© μ—†μŒ"),
                "link": result.get("url", result.get("link", "#")),
                "snippet": result.get("snippet", "λ‚΄μš© μ—†μŒ"),
                "channel": result.get("channel", result.get("source", "μ•Œ 수 μ—†μŒ")),
                "time": result.get("time", result.get("date", "μ•Œ 수 μ—†λŠ” μ‹œκ°„")),
                "image_url": result.get("img", result.get("thumbnail", "")),
                "translated_query": translated_query
            })
        return "", articles
    except Exception as e:
        return f"κ²°κ³Ό 처리 쀑 였λ₯˜ λ°œμƒ: {str(e)}", []

def serphouse_search(query, country):
    response_data = search_serphouse(query, country)
    return format_results_from_raw(response_data)





# Hacker News API κ΄€λ ¨ ν•¨μˆ˜λ“€ λ¨Όμ € μΆ”κ°€
def get_hn_item(item_id):
    """κ°œλ³„ μ•„μ΄ν…œ 정보 κ°€μ Έμ˜€κΈ°"""
    try:
        response = requests.get(f"https://hacker-news.firebaseio.com/v0/item/{item_id}.json")
        return response.json()
    except:
        return None

def get_recent_stories():
    """μ΅œμ‹  μŠ€ν† λ¦¬ κ°€μ Έμ˜€κΈ°"""
    try:
        response = requests.get("https://hacker-news.firebaseio.com/v0/newstories.json")
        story_ids = response.json()
        
        recent_stories = []
        current_time = datetime.now().timestamp()
        day_ago = current_time - (24 * 60 * 60)
        
        for story_id in story_ids:
            story = get_hn_item(story_id)
            if story and 'time' in story and story['time'] > day_ago:
                recent_stories.append(story)
            
            if len(recent_stories) >= 100:
                break
                
        return recent_stories
    except Exception as e:
        print(f"Error fetching HN stories: {str(e)}")
        return []

def format_hn_time(timestamp):
    """Unix timestampλ₯Ό 읽기 μ‰¬μš΄ ν˜•μ‹μœΌλ‘œ λ³€ν™˜"""
    try:
        dt = datetime.fromtimestamp(timestamp)
        return dt.strftime("%Y-%m-%d %H:%M:%S")
    except:
        return "Unknown time"


def clean_text(text):
    """HTML νƒœκ·Έ 제거 및 ν…μŠ€νŠΈ 정리"""
    text = re.sub(r'\s+', ' ', text)
    text = re.sub(r'<[^>]+>', '', text)
    return text.strip()

def get_article_content(url):
    """URLμ—μ„œ 기사 λ‚΄μš© μŠ€ν¬λž˜ν•‘"""
    if not url or 'github.com' in url or 'twitter.com' in url:
        return None
        
    try:
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
        response = requests.get(url, headers=headers, timeout=10)
        soup = BeautifulSoup(response.text, 'html.parser')
        
        # λΆˆν•„μš”ν•œ μš”μ†Œ 제거
        for tag in soup(['script', 'style', 'nav', 'footer', 'header']):
            tag.decompose()
            
        paragraphs = soup.find_all('p')
        text = ' '.join(p.get_text() for p in paragraphs)
        text = clean_text(text)
        
        return text[:4000]  # ν…μŠ€νŠΈ 길이 μ œν•œ
    except Exception as e:
        print(f"Scraping error for {url}: {str(e)}")
        return None

def generate_summary(text):
    """CohereForAI λͺ¨λΈμ„ μ‚¬μš©ν•œ μš”μ•½ 생성"""
    if not text:
        return None
        
    prompt = """λ°˜λ“œμ‹œ ν•œκΈ€(ν•œκ΅­μ–΄)둜 μž‘μ„±ν•˜λΌ. Please analyze and summarize the following text in 2-3 sentences. 
    Focus on the main points and key information:

    Text: {text}
    
    Summary:"""
    
    try:
        response = hf_client.text_generation(
            prompt.format(text=text),
            max_new_tokens=500,
            temperature=0.5,
            repetition_penalty=1.2
        )
        return response
    except Exception as e:
        print(f"Summary generation error: {str(e)}")
        return None

def process_hn_story(story, progress=None):
    """κ°œλ³„ μŠ€ν† λ¦¬ 처리 및 μš”μ•½"""
    try:
        url = story.get('url')
        if not url:
            return story, None
            
        content = get_article_content(url)
        if not content:
            return story, None
            
        summary_en = generate_summary(content)
        if not summary_en:
            return story, None
            
        summary_ko = translate_to_korean(summary_en)
        return story, summary_ko
        
    except Exception as e:
        print(f"Story processing error: {str(e)}")
        return story, None

def refresh_hn_stories():
    """Hacker News μŠ€ν† λ¦¬ μƒˆλ‘œκ³ μΉ¨ (μ‹€μ‹œκ°„ 좜λ ₯ 버전)"""
    status_msg = "Hacker News 포슀트λ₯Ό κ°€μ Έμ˜€λŠ” 쀑..."
    outputs = [gr.update(value=status_msg, visible=True)]
    
    # μ»΄ν¬λ„ŒνŠΈ μ΄ˆκΈ°ν™”
    for comp in hn_article_components:
        outputs.extend([
            gr.update(visible=False),
            gr.update(),
            gr.update(),
            gr.update(visible=False),  # report_button
            gr.update(visible=False),  # show_report
            gr.update(visible=False)   # report_content
        ])
    
    yield outputs
    
    # μ΅œμ‹  μŠ€ν† λ¦¬ κ°€μ Έμ˜€κΈ°
    stories = get_recent_stories()
    processed_count = 0
    
    # μ‹€μ‹œκ°„ 처리 및 좜λ ₯을 μœ„ν•œ 리슀트
    processed_stories = []
    
    with concurrent.futures.ThreadPoolExecutor(max_workers=10) as executor:
        future_to_story = {executor.submit(process_hn_story, story): story 
                          for story in stories[:100]}
        
        for future in concurrent.futures.as_completed(future_to_story):
            story, summary = future.result()
            processed_count += 1
            
            if summary:
                # μƒˆλ‘œμš΄ κ²°κ³Όλ₯Ό 리슀트 맨 μ•žμ— μΆ”κ°€
                processed_stories.insert(0, (story, summary))
                
                # ν˜„μž¬κΉŒμ§€μ˜ κ²°κ³Ό 좜λ ₯
                outputs = [gr.update(value=f"처리 쀑... ({processed_count}/{len(stories)})", visible=True)]
                
                # λͺ¨λ“  μ»΄ν¬λ„ŒνŠΈ μ—…λ°μ΄νŠΈ
                for idx, comp in enumerate(hn_article_components):
                    if idx < len(processed_stories):
                        current_story, current_summary = processed_stories[idx]
                        outputs.extend([
                            gr.update(visible=True),
                            gr.update(value=f"### [{current_story.get('title', 'Untitled')}]({current_story.get('url', '#')})"),
                            gr.update(value=f"""
                            **μž‘μ„±μž:** {current_story.get('by', 'unknown')} | 
                            **μ‹œκ°„:** {format_hn_time(current_story.get('time', 0))} | 
                            **점수:** {current_story.get('score', 0)} | 
                            **λŒ“κΈ€:** {len(current_story.get('kids', []))}개\n
                            **AI μš”μ•½:** {current_summary}
                            """),
                            gr.update(visible=True),  # report_button
                            gr.update(visible=False),  # show_report
                            gr.update(visible=False)   # report_content
                        ])
                    else:
                        outputs.extend([
                            gr.update(visible=False),
                            gr.update(),
                            gr.update(),
                            gr.update(visible=False),
                            gr.update(visible=False),
                            gr.update(visible=False)
                        ])
                
                yield outputs
    
    # μ΅œμ’… μƒνƒœ μ—…λ°μ΄νŠΈ
    final_outputs = [gr.update(value=f"총 {len(processed_stories)}개의 ν¬μŠ€νŠΈκ°€ μ²˜λ¦¬λ˜μ—ˆμŠ΅λ‹ˆλ‹€.", visible=True)]
    
    for idx, comp in enumerate(hn_article_components):
        if idx < len(processed_stories):
            story, summary = processed_stories[idx]
            final_outputs.extend([
                gr.update(visible=True),
                gr.update(value=f"### [{story.get('title', 'Untitled')}]({story.get('url', '#')})"),
                gr.update(value=f"""
                **μž‘μ„±μž:** {story.get('by', 'unknown')} | 
                **μ‹œκ°„:** {format_hn_time(story.get('time', 0))} | 
                **점수:** {story.get('score', 0)} | 
                **λŒ“κΈ€:** {len(story.get('kids', []))}개\n
                **AI μš”μ•½:** {summary}
                """),
                gr.update(visible=True),  # report_button
                gr.update(visible=False),  # show_report
                gr.update(visible=False)   # report_content
            ])
        else:
            final_outputs.extend([
                gr.update(visible=False),
                gr.update(),
                gr.update(),
                gr.update(visible=False),
                gr.update(visible=False),
                gr.update(visible=False)
            ])
    
    yield final_outputs
    
    # μ΅œμ’… μƒνƒœ μ—…λ°μ΄νŠΈ
    final_outputs = [gr.update(value=f"총 {len(processed_stories)}개의 ν¬μŠ€νŠΈκ°€ μ²˜λ¦¬λ˜μ—ˆμŠ΅λ‹ˆλ‹€.", visible=True)]
    
    for idx, comp in enumerate(hn_article_components):
        if idx < len(processed_stories):
            story, summary = processed_stories[idx]
            final_outputs.extend([
                gr.update(visible=True),
                gr.update(value=f"### [{story.get('title', 'Untitled')}]({story.get('url', '#')})"),
                gr.update(value=f"""
                **μž‘μ„±μž:** {story.get('by', 'unknown')} | 
                **μ‹œκ°„:** {format_hn_time(story.get('time', 0))} | 
                **점수:** {story.get('score', 0)} | 
                **λŒ“κΈ€:** {len(story.get('kids', []))}개\n
                **AI μš”μ•½:** {summary}
                """),
                gr.update(visible=True),  # report_button
                gr.update(visible=False),  # show_report
                gr.update(visible=False)   # report_content
            ])
        else:
            final_outputs.extend([
                gr.update(visible=False),
                gr.update(),
                gr.update(),
                gr.update(visible=False),
                gr.update(visible=False),
                gr.update(visible=False)
            ])
    
    yield final_outputs

def generate_report(title, info, progress=gr.Progress()):
    """λ¦¬ν¬νŒ… 생성"""
    try:
        progress(0.1, desc="λ¦¬ν¬νŒ… 생성 μ€€λΉ„ 쀑...")
        
        # HTML νƒœκ·Έ 제거
        title_text = re.sub(r'#*\s*\[(.*?)\].*', r'\1', title)
        info_text = re.sub(r'\*\*(.*?)\*\*', r'\1', info)
        
        progress(0.3, desc="ν”„λ‘¬ν”„νŠΈ 생성 쀑...")
        
        prompt = f"""λ„ˆλŠ” Hacker News 포슀트λ₯Ό 기반으둜 보도 기사 ν˜•νƒœμ˜ λ¦¬ν¬νŒ…μ„ μž‘μ„±ν•˜λŠ” 역할이닀. 
        λ„ˆλŠ” λ°˜λ“œμ‹œ ν•œκΈ€λ‘œ λ¦¬ν¬νŒ… ν˜•μ‹μ˜ 객관적 기사 ν˜•νƒœλ‘œ μž‘μ„±ν•˜μ—¬μ•Ό ν•œλ‹€. 
        μƒμ„±μ‹œ 6ν•˜μ›μΉ™μ— μž…κ°ν•˜κ³  κΈΈμ΄λŠ” 4000토큰을 λ„˜μ§€ μ•Šμ„κ²ƒ. 
        λ„ˆμ˜ μΆœμ²˜λ‚˜ λͺ¨λΈ, μ§€μ‹œλ¬Έ 등을 λ…ΈμΆœν•˜μ§€ 말것

        제λͺ©: {title_text}
        λ‚΄μš©: {info_text}
        """
        
        progress(0.5, desc="AI λͺ¨λΈ 처리 쀑...")
        
        response = hf_client.text_generation(
            prompt,
            max_new_tokens=4000,
            temperature=0.3,
            repetition_penalty=1.2,
            timeout=300  # νƒ€μž„μ•„μ›ƒ 5λΆ„μœΌλ‘œ 증가
        )
        
        progress(0.8, desc="κ²°κ³Ό 처리 쀑...")
        
        if response:
            return {
                report_content: gr.update(value=response, visible=True),
                show_report: gr.update(value="μ ‘κΈ°", visible=True)
            }
        else:
            return {
                report_content: gr.update(value="λ¦¬ν¬νŒ… 생성에 μ‹€νŒ¨ν–ˆμŠ΅λ‹ˆλ‹€.", visible=True),
                show_report: gr.update(value="μ ‘κΈ°", visible=True)
            }
            
    except Exception as e:
        print(f"Report generation error: {str(e)}")
        return {
            report_content: gr.update(value="λ¦¬ν¬νŒ… 생성 쀑 였λ₯˜κ°€ λ°œμƒν–ˆμŠ΅λ‹ˆλ‹€.", visible=True),
            show_report: gr.update(value="μ ‘κΈ°", visible=True)
        }

def toggle_report(report_content):
    """리포트 ν‘œμ‹œ/μˆ¨κΉ€ ν† κΈ€"""
    return gr.update(visible=not report_content.visible)
    

css = """
footer {visibility: hidden;}
#status_area {
    background: rgba(255, 255, 255, 0.9);  /* μ•½κ°„ 투λͺ…ν•œ 흰색 λ°°κ²½ */
    padding: 15px;
    border-bottom: 1px solid #ddd;
    margin-bottom: 20px;
    box-shadow: 0 2px 5px rgba(0,0,0,0.1);  /* λΆ€λ“œλŸ¬μš΄ 그림자 효과 */
}
#results_area {
    padding: 10px;
    margin-top: 10px;
}
/* νƒ­ μŠ€νƒ€μΌ κ°œμ„  */
.tabs {
    border-bottom: 2px solid #ddd !important;
    margin-bottom: 20px !important;
}
.tab-nav {
    border-bottom: none !important;
    margin-bottom: 0 !important;
}
.tab-nav button {
    font-weight: bold !important;
    padding: 10px 20px !important;
}
.tab-nav button.selected {
    border-bottom: 2px solid #1f77b4 !important;  /* μ„ νƒλœ νƒ­ κ°•μ‘° */
    color: #1f77b4 !important;
}
/* 검색 μƒνƒœ λ©”μ‹œμ§€ μŠ€νƒ€μΌ */
#status_area .markdown-text {
    font-size: 1.1em;
    color: #2c3e50;
    padding: 10px 0;
}
/* 검색 κ²°κ³Ό μ»¨ν…Œμ΄λ„ˆ μŠ€νƒ€μΌ */
.group {
    border: 1px solid #eee;
    padding: 15px;
    margin-bottom: 15px;
    border-radius: 5px;
    background: white;
}
/* 검색 λ²„νŠΌ μŠ€νƒ€μΌ */
.primary-btn {
    background: #1f77b4 !important;
    border: none !important;
}
/* 검색어 μž…λ ₯μ°½ μŠ€νƒ€μΌ */
.textbox {
    border: 1px solid #ddd !important;
    border-radius: 4px !important;
}
"""

with gr.Blocks(theme="Nymbo/Nymbo_Theme", css=css, title="NewsAI μ„œλΉ„μŠ€") as iface:
    with gr.Tabs():
        # ꡭ가별 νƒ­
        with gr.Tab("ꡭ가별"):
            gr.Markdown("검색어λ₯Ό μž…λ ₯ν•˜κ³  μ›ν•˜λŠ” κ΅­κ°€(ν•œκ΅­ μ œμ™Έ)λ₯Όλ₯Ό μ„ νƒν•˜λ©΄, 검색어와 μΌμΉ˜ν•˜λŠ” 24μ‹œκ°„ 이내 λ‰΄μŠ€λ₯Ό μ΅œλŒ€ 100개 좜λ ₯ν•©λ‹ˆλ‹€.")
            gr.Markdown("κ΅­κ°€ 선택후 검색어에 'ν•œκΈ€'을 μž…λ ₯ν•˜λ©΄ ν˜„μ§€ μ–Έμ–΄λ‘œ λ²ˆμ—­λ˜μ–΄ κ²€μƒ‰ν•©λ‹ˆλ‹€. 예: 'Taiwan' κ΅­κ°€ 선택후 'μ‚Όμ„±' μž…λ ₯μ‹œ 'δΈ‰ζ˜Ÿ'으둜 μžλ™ 검색")
            
            with gr.Column():
                with gr.Row():
                    query = gr.Textbox(label="검색어")
                    country = gr.Dropdown(MAJOR_COUNTRIES, label="κ΅­κ°€", value="United States")
                
                status_message = gr.Markdown("", visible=True)
                translated_query_display = gr.Markdown(visible=False)
                search_button = gr.Button("검색", variant="primary")
                
                progress = gr.Progress()
                articles_state = gr.State([])

                article_components = []
                for i in range(100):
                    with gr.Group(visible=False) as article_group:
                        title = gr.Markdown()
                        image = gr.Image(width=200, height=150)
                        snippet = gr.Markdown()
                        info = gr.Markdown()
                        
                        article_components.append({
                            'group': article_group,
                            'title': title,
                            'image': image,
                            'snippet': snippet,
                            'info': info,
                            'index': i,
                        })

        # 전세계 νƒ­
        with gr.Tab("전세계"):
            gr.Markdown("검색어λ₯Ό μž…λ ₯ν•˜λ©΄ 67개ꡭ(ν•œκ΅­ μ œμ™Έ) 전체에 λŒ€ν•΄ κ΅­κ°€λ³„λ‘œ κ΅¬λΆ„ν•˜μ—¬ 24μ‹œκ°„ 이내 λ‰΄μŠ€κ°€ μ΅œλŒ€ 1000개 순차 좜λ ₯λ©λ‹ˆλ‹€.")
            gr.Markdown("κ΅­κ°€ 선택후 검색어에 'ν•œκΈ€'을 μž…λ ₯ν•˜λ©΄ ν˜„μ§€ μ–Έμ–΄λ‘œ λ²ˆμ—­λ˜μ–΄ κ²€μƒ‰ν•©λ‹ˆλ‹€. 예: 'Taiwan' κ΅­κ°€ 선택후 'μ‚Όμ„±' μž…λ ₯μ‹œ 'δΈ‰ζ˜Ÿ'으둜 μžλ™ 검색") 
            
            with gr.Column():
                with gr.Column(elem_id="status_area"):
                    with gr.Row():
                        query_global = gr.Textbox(label="검색어")
                        search_button_global = gr.Button("전세계 검색", variant="primary")
            
                    status_message_global = gr.Markdown("")
                    translated_query_display_global = gr.Markdown("")
        
                with gr.Column(elem_id="results_area"):
                    articles_state_global = gr.State([])
            
                    global_article_components = []
                    for i in range(1000):
                        with gr.Group(visible=False) as article_group:
                            title = gr.Markdown()
                            image = gr.Image(width=200, height=150)
                            snippet = gr.Markdown()
                            info = gr.Markdown()
                    
                            global_article_components.append({
                                'group': article_group,
                                'title': title,
                                'image': image,
                                'snippet': snippet,
                                'info': info,
                                'index': i,
                            })

        with gr.Tab("AI 리포터"):
            gr.Markdown("μ§€λ‚œ 24μ‹œκ°„ λ™μ•ˆμ˜ Hacker News 포슀트λ₯Ό AIκ°€ μš”μ•½ν•˜μ—¬ λ³΄μ—¬μ€λ‹ˆλ‹€.")

            with gr.Column():
                refresh_button = gr.Button("μƒˆλ‘œκ³ μΉ¨", variant="primary")
                status_message_hn = gr.Markdown("")
        
                with gr.Column(elem_id="hn_results_area"):
                    hn_articles_state = gr.State([])
        
                    hn_article_components = []
                    for i in range(100):
                        with gr.Group(visible=False, elem_classes="hn-article-group") as article_group:
                            title = gr.Markdown()
                            info = gr.Markdown()
                            with gr.Row():
                                report_button = gr.Button("λ¦¬ν¬νŒ… 생성", size="sm", variant="primary")
                                show_report = gr.Button("펼쳐 보기", size="sm", visible=False)
                            with gr.Column(visible=False) as report_section:
                                report_content = gr.Markdown()
                    
                            hn_article_components.append({
                                'group': article_group,
                                'title': title,
                                'info': info,
                                'report_button': report_button,
                                'show_report': show_report,
                                'report_section': report_section,
                                'report_content': report_content,
                                'index': i,
                            })


 
    
# κΈ°μ‘΄ ν•¨μˆ˜λ“€
    def search_and_display(query, country, articles_state, progress=gr.Progress()):
        status_msg = "검색을 μ§„ν–‰μ€‘μž…λ‹ˆλ‹€. μž μ‹œλ§Œ κΈ°λ‹€λ¦¬μ„Έμš”..."
        
        progress(0, desc="검색어 λ²ˆμ—­ 쀑...")
        translated_query = translate_query(query, country)
        translated_display = f"**원본 검색어:** {query}\n**λ²ˆμ—­λœ 검색어:** {translated_query}" if translated_query != query else f"**검색어:** {query}"
        
        progress(0.2, desc="검색 μ‹œμž‘...")
        error_message, articles = serphouse_search(query, country)
        progress(0.5, desc="κ²°κ³Ό 처리 쀑...")
        
        outputs = []
        outputs.append(gr.update(value=status_msg, visible=True))
        outputs.append(gr.update(value=translated_display, visible=True))
        
        if error_message:
            outputs.append(gr.update(value=error_message, visible=True))
            for comp in article_components:
                outputs.extend([
                    gr.update(visible=False), gr.update(), gr.update(),
                    gr.update(), gr.update()
                ])
            articles_state = []
        else:
            outputs.append(gr.update(value="", visible=False))
            total_articles = len(articles)
            for idx, comp in enumerate(article_components):
                progress((idx + 1) / total_articles, desc=f"κ²°κ³Ό ν‘œμ‹œ 쀑... {idx + 1}/{total_articles}")
                if idx < len(articles):
                    article = articles[idx]
                    image_url = article['image_url']
                    image_update = gr.update(value=image_url, visible=True) if image_url and not image_url.startswith('data:image') else gr.update(value=None, visible=False)
                    
                    korean_summary = translate_to_korean(article['snippet'])
                    
                    outputs.extend([
                        gr.update(visible=True),
                        gr.update(value=f"### [{article['title']}]({article['link']})"),
                        image_update,
                        gr.update(value=f"**μš”μ•½:** {article['snippet']}\n\n**ν•œκΈ€ μš”μ•½:** {korean_summary}"),
                        gr.update(value=f"**좜처:** {article['channel']} | **μ‹œκ°„:** {article['time']}")
                    ])
                else:
                    outputs.extend([
                        gr.update(visible=False), gr.update(), gr.update(),
                        gr.update(), gr.update()
                    ])
            articles_state = articles

        progress(1.0, desc="μ™„λ£Œ!")
        outputs.append(articles_state)
        outputs[0] = gr.update(value="", visible=False)
        
        return outputs

    def search_global(query, articles_state_global):
        status_msg = "전세계 검색을 μ‹œμž‘ν•©λ‹ˆλ‹€..."
        all_results = []
        
        outputs = [
            gr.update(value=status_msg, visible=True),
            gr.update(value=f"**검색어:** {query}", visible=True),
        ]
        
        for _ in global_article_components:
            outputs.extend([
                gr.update(visible=False), gr.update(), gr.update(),
                gr.update(), gr.update()
            ])
        outputs.append([])
        
        yield outputs
        
        total_countries = len(COUNTRY_LOCATIONS)
        for idx, (country, location) in enumerate(COUNTRY_LOCATIONS.items(), 1):
            try:
                status_msg = f"{country} 검색 쀑... ({idx}/{total_countries} κ΅­κ°€)"
                outputs[0] = gr.update(value=status_msg, visible=True)
                yield outputs
                
                error_message, articles = serphouse_search(query, country)
                if not error_message and articles:
                    for article in articles:
                        article['source_country'] = country
                    
                    all_results.extend(articles)
                    sorted_results = sorted(all_results, key=lambda x: x.get('time', ''), reverse=True)
                    
                    seen_urls = set()
                    unique_results = []
                    for article in sorted_results:
                        url = article.get('link', '')
                        if url not in seen_urls:
                            seen_urls.add(url)
                            unique_results.append(article)
                    
                    unique_results = unique_results[:1000]
                    
                    outputs = [
                        gr.update(value=f"{idx}/{total_countries} κ΅­κ°€ 검색 μ™„λ£Œ\nν˜„μž¬κΉŒμ§€ 발견된 λ‰΄μŠ€: {len(unique_results)}건", visible=True),
                        gr.update(value=f"**검색어:** {query}", visible=True),
                    ]
                    
                    for idx, comp in enumerate(global_article_components):
                        if idx < len(unique_results):
                            article = unique_results[idx]
                            image_url = article.get('image_url', '')
                            image_update = gr.update(value=image_url, visible=True) if image_url and not image_url.startswith('data:image') else gr.update(value=None, visible=False)
                            
                            korean_summary = translate_to_korean(article['snippet'])
                            
                            outputs.extend([
                                gr.update(visible=True),
                                gr.update(value=f"### [{article['title']}]({article['link']})"),
                                image_update,
                                gr.update(value=f"**μš”μ•½:** {article['snippet']}\n\n**ν•œκΈ€ μš”μ•½:** {korean_summary}"),
                                gr.update(value=f"**좜처:** {article['channel']} | **κ΅­κ°€:** {article['source_country']} | **μ‹œκ°„:** {article['time']}")
                            ])
                        else:
                            outputs.extend([
                                gr.update(visible=False), gr.update(), gr.update(),
                                gr.update(), gr.update()
                            ])
                    
                    outputs.append(unique_results)
                    yield outputs
                    
            except Exception as e:
                print(f"Error searching {country}: {str(e)}")
                continue
        
        final_status = f"검색 μ™„λ£Œ! 총 {len(unique_results)}개의 λ‰΄μŠ€κ°€ λ°œκ²¬λ˜μ—ˆμŠ΅λ‹ˆλ‹€."
        outputs[0] = gr.update(value=final_status, visible=True)
        yield outputs






# ꡭ가별 νƒ­ 이벀트 μ—°κ²°
    search_outputs = [
        status_message,
        translated_query_display,
        gr.Markdown(visible=False)
    ]
    
    for comp in article_components:
        search_outputs.extend([
            comp['group'], comp['title'], comp['image'],
            comp['snippet'], comp['info']
        ])
    search_outputs.append(articles_state)

    search_button.click(
        search_and_display,
        inputs=[query, country, articles_state],
        outputs=search_outputs,
        show_progress=True
    )

    # 전세계 νƒ­ 이벀트 μ—°κ²°
    global_search_outputs = [
        status_message_global,
        translated_query_display_global,
    ]



# AI 리포터 νƒ­ 이벀트 μ—°κ²°
    for comp in hn_article_components:
        comp['report_button'].click(
            generate_report,
            inputs=[comp['title'], comp['info']],
            outputs=[comp['report_content'], comp['show_report']],
            show_progress=True
        )
        
        comp['show_report'].click(
            toggle_report,
            inputs=[comp['report_content']],
            outputs=[comp['report_content']]
        )
    


    hn_outputs = [status_message_hn]
    for comp in hn_article_components:
        hn_outputs.extend([
            comp['group'],
            comp['title'],
            comp['info'],
            comp['report_button'],
            comp['show_report'],
            comp['report_content']
        ])

    refresh_button.click(
        refresh_hn_stories,
        outputs=hn_outputs
    )




iface.launch(
    server_name="0.0.0.0",
    server_port=7860,
    share=False,            # μ™ΈλΆ€ 곡유 λΉ„ν™œμ„±ν™”
    auth=("it1","chosun1"),
    ssl_verify=False,       # SSL 검증 λΉ„ν™œμ„±ν™” (ν•„μš”ν•œ 경우)
    show_error=True         # 였λ₯˜ λ©”μ‹œμ§€ ν‘œμ‹œ
)