fix
Browse files
main.py
CHANGED
|
@@ -1,858 +1,879 @@
|
|
| 1 |
-
# main.py
|
| 2 |
-
import os
|
| 3 |
-
import re
|
| 4 |
-
import logging
|
| 5 |
-
import asyncio
|
| 6 |
-
import json
|
| 7 |
-
from flask import Flask, request, Response # For web server
|
| 8 |
-
|
| 9 |
-
from telegram import Update, InlineKeyboardButton, InlineKeyboardMarkup
|
| 10 |
-
from telegram.ext import (
|
| 11 |
-
Application,
|
| 12 |
-
CommandHandler,
|
| 13 |
-
MessageHandler,
|
| 14 |
-
filters,
|
| 15 |
-
ContextTypes,
|
| 16 |
-
CallbackQueryHandler
|
| 17 |
-
)
|
| 18 |
-
from telegram.constants import ParseMode # Import ParseMode explicitly
|
| 19 |
-
|
| 20 |
-
# Import specific libraries (Ensure these are covered in requirements.txt)
|
| 21 |
-
from youtube_transcript_api import YouTubeTranscriptApi
|
| 22 |
-
import requests
|
| 23 |
-
from bs4 import BeautifulSoup
|
| 24 |
-
# Only import ApifyClient if you might use it (i.e., have the secret)
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
#
|
| 31 |
-
|
| 32 |
-
nest_asyncio
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
#
|
| 42 |
-
logging.
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
)
|
| 46 |
-
|
| 47 |
-
logging.getLogger("
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
logger
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
logger.
|
| 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 |
-
logger.
|
| 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 |
-
logger.info(f"User {
|
| 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 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# main.py (Revised for Hugging Face - Corrected Logs & Added Debugging)
|
| 2 |
+
import os
|
| 3 |
+
import re
|
| 4 |
+
import logging
|
| 5 |
+
import asyncio
|
| 6 |
+
import json
|
| 7 |
+
from flask import Flask, request, Response # For web server
|
| 8 |
+
|
| 9 |
+
from telegram import Update, InlineKeyboardButton, InlineKeyboardMarkup
|
| 10 |
+
from telegram.ext import (
|
| 11 |
+
Application,
|
| 12 |
+
CommandHandler,
|
| 13 |
+
MessageHandler,
|
| 14 |
+
filters,
|
| 15 |
+
ContextTypes,
|
| 16 |
+
CallbackQueryHandler
|
| 17 |
+
)
|
| 18 |
+
from telegram.constants import ParseMode # Import ParseMode explicitly
|
| 19 |
+
|
| 20 |
+
# Import specific libraries (Ensure these are covered in requirements.txt)
|
| 21 |
+
from youtube_transcript_api import YouTubeTranscriptApi
|
| 22 |
+
import requests
|
| 23 |
+
from bs4 import BeautifulSoup
|
| 24 |
+
# Only import ApifyClient if you might use it (i.e., have the secret)
|
| 25 |
+
# Check environment variable existence *before* conditional import
|
| 26 |
+
_apify_token_exists = bool(os.environ.get('APIFY_API_TOKEN'))
|
| 27 |
+
if _apify_token_exists:
|
| 28 |
+
from apify_client import ApifyClient
|
| 29 |
+
else:
|
| 30 |
+
ApifyClient = None # Define it as None if not used, to avoid errors later
|
| 31 |
+
|
| 32 |
+
# Apply nest_asyncio early, can help prevent event loop conflicts in web frameworks
|
| 33 |
+
import nest_asyncio
|
| 34 |
+
nest_asyncio.apply()
|
| 35 |
+
|
| 36 |
+
# --- Logging Setup ---
|
| 37 |
+
logging.basicConfig(
|
| 38 |
+
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
|
| 39 |
+
level=logging.INFO # Set to INFO to see processing steps, DEBUG for finer detail
|
| 40 |
+
)
|
| 41 |
+
# Reduce noise from libraries
|
| 42 |
+
logging.getLogger("httpx").setLevel(logging.WARNING)
|
| 43 |
+
if ApifyClient: # Only set level if imported
|
| 44 |
+
logging.getLogger("apify_client").setLevel(logging.WARNING)
|
| 45 |
+
logging.getLogger("telegram.ext").setLevel(logging.INFO)
|
| 46 |
+
logging.getLogger('telegram.bot').setLevel(logging.INFO)
|
| 47 |
+
logging.getLogger("urllib3").setLevel(logging.INFO) # From requests
|
| 48 |
+
logging.getLogger('gunicorn.error').setLevel(logging.INFO) # Gunicorn logs
|
| 49 |
+
logger = logging.getLogger(__name__)
|
| 50 |
+
logger.info("Logging configured.")
|
| 51 |
+
|
| 52 |
+
# --- Environment Variable Loading & Debugging ---
|
| 53 |
+
logger.info("Attempting to load secrets from environment variables...")
|
| 54 |
+
|
| 55 |
+
def get_secret(secret_name):
|
| 56 |
+
"""Reads secret and logs the attempt and result."""
|
| 57 |
+
logger.debug(f"Attempting to read secret: {secret_name}")
|
| 58 |
+
value = os.environ.get(secret_name)
|
| 59 |
+
if value:
|
| 60 |
+
logger.info(f"Secret '{secret_name}': Found (Value length: {len(value)})") # Log length, not value itself
|
| 61 |
+
else:
|
| 62 |
+
logger.warning(f"Secret '{secret_name}': Not Found")
|
| 63 |
+
return value
|
| 64 |
+
|
| 65 |
+
TELEGRAM_TOKEN = get_secret('TELEGRAM_TOKEN')
|
| 66 |
+
OPENROUTER_API_KEY = get_secret('OPENROUTER_API_KEY')
|
| 67 |
+
URLTOTEXT_API_KEY = get_secret('URLTOTEXT_API_KEY') # Will be None if not set in Secrets
|
| 68 |
+
SUPADATA_API_KEY = get_secret('SUPADATA_API_KEY') # Will be None if not set in Secrets
|
| 69 |
+
APIFY_API_TOKEN = get_secret('APIFY_API_TOKEN') # Will be None if not set in Secrets
|
| 70 |
+
|
| 71 |
+
logger.info("Secret loading attempt finished.")
|
| 72 |
+
|
| 73 |
+
# --- Initial Validation ---
|
| 74 |
+
# Perform validation *after* attempting to load all secrets
|
| 75 |
+
if not TELEGRAM_TOKEN:
|
| 76 |
+
logger.critical("FATAL: TELEGRAM_TOKEN environment variable not found or empty!")
|
| 77 |
+
# In a deployed environment, exiting might not be helpful. Log critical error.
|
| 78 |
+
# exit("Telegram Token Missing")
|
| 79 |
+
else:
|
| 80 |
+
logger.info("TELEGRAM_TOKEN seems present.")
|
| 81 |
+
|
| 82 |
+
if not OPENROUTER_API_KEY:
|
| 83 |
+
# Log error but allow running, summaries will just fail gracefully later
|
| 84 |
+
logger.error("OPENROUTER_API_KEY not found or empty! Summarization will fail.")
|
| 85 |
+
else:
|
| 86 |
+
logger.info("OPENROUTER_API_KEY seems present.")
|
| 87 |
+
|
| 88 |
+
# (Optional checks log warnings if keys were not found by get_secret)
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
# --- Bot Logic Functions (Simplified Version - No Crawl4AI) ---
|
| 92 |
+
# (Functions: is_youtube_url, extract_youtube_id, get_transcript_via_supadata,
|
| 93 |
+
# get_transcript_via_apify, get_youtube_transcript, get_website_content_via_requests,
|
| 94 |
+
# get_website_content_via_urltotext_api, generate_summary remain EXACTLY THE SAME
|
| 95 |
+
# as in the previous complete main.py code block. Ensure they are included here.)
|
| 96 |
+
|
| 97 |
+
# --- [PASTE ALL BOT LOGIC FUNCTIONS HERE - FROM is_youtube_url to generate_summary ] ---
|
| 98 |
+
# Helper Functions
|
| 99 |
+
def is_youtube_url(url):
|
| 100 |
+
"""Checks if the URL is a valid YouTube video or shorts URL."""
|
| 101 |
+
youtube_regex = r'(https?://)?(www\.)?(youtube\.com/(watch\?v=|shorts/)|youtu\.be/)([\w-]{11})'
|
| 102 |
+
return bool(re.search(youtube_regex, url))
|
| 103 |
+
|
| 104 |
+
def extract_youtube_id(url):
|
| 105 |
+
"""Extracts the YouTube video ID from a URL."""
|
| 106 |
+
youtube_id_regex = r'(?:youtube\.com/(?:watch\?v=|shorts/)|youtu\.be/)([\w-]{11})'
|
| 107 |
+
match = re.search(youtube_id_regex, url)
|
| 108 |
+
if match:
|
| 109 |
+
return match.group(1)
|
| 110 |
+
logger.warning(f"Could not extract YouTube ID from URL: {url}")
|
| 111 |
+
return None
|
| 112 |
+
|
| 113 |
+
# Supadata Transcript Fetching
|
| 114 |
+
async def get_transcript_via_supadata(video_id: str, api_key: str):
|
| 115 |
+
"""Fetches YouTube transcript via Supadata API."""
|
| 116 |
+
if not video_id: logger.error("[Supadata] get_transcript_via_supadata called with no video_id"); return None
|
| 117 |
+
if not api_key: logger.error("[Supadata] API key is missing."); return None # Already checked before calling
|
| 118 |
+
logger.info(f"[Supadata] Attempting fetch for video ID: {video_id}")
|
| 119 |
+
api_endpoint = f"https://api.supadata.net/v1/youtube/transcript"
|
| 120 |
+
params = {"videoId": video_id, "format": "text"}
|
| 121 |
+
headers = {"X-API-Key": api_key}
|
| 122 |
+
try:
|
| 123 |
+
# Use asyncio.to_thread to run blocking requests.get in a separate thread
|
| 124 |
+
response = await asyncio.to_thread(requests.get, api_endpoint, headers=headers, params=params, timeout=30)
|
| 125 |
+
logger.debug(f"[Supadata] Received status code {response.status_code} for {video_id}")
|
| 126 |
+
if response.status_code == 200:
|
| 127 |
+
try:
|
| 128 |
+
data = response.json()
|
| 129 |
+
content = data if isinstance(data, str) else data.get("transcript") or data.get("text") or data.get("data")
|
| 130 |
+
if content and isinstance(content, str):
|
| 131 |
+
logger.info(f"[Supadata] Successfully fetched transcript for {video_id}. Length: {len(content)}")
|
| 132 |
+
return content.strip()
|
| 133 |
+
else:
|
| 134 |
+
logger.warning(f"[Supadata] API success but content empty/invalid for {video_id}. Response: {data}")
|
| 135 |
+
return None
|
| 136 |
+
except json.JSONDecodeError: # Handle cases where API might return plain text on success
|
| 137 |
+
if response.text:
|
| 138 |
+
logger.info(f"[Supadata] Successfully fetched transcript (plain text) for {video_id}. Length: {len(response.text)}")
|
| 139 |
+
return response.text.strip()
|
| 140 |
+
else:
|
| 141 |
+
logger.error(f"[Supadata] Failed to decode JSON response (and no text body) for {video_id}. Response: {response.text[:200]}...")
|
| 142 |
+
return None
|
| 143 |
+
except Exception as e:
|
| 144 |
+
logger.error(f"[Supadata] Error processing successful response for {video_id}: {e}", exc_info=True)
|
| 145 |
+
return None
|
| 146 |
+
elif response.status_code in [401, 403]:
|
| 147 |
+
logger.error(f"[Supadata] Authentication error ({response.status_code}). Check API key.")
|
| 148 |
+
return None # Don't retry if key is bad
|
| 149 |
+
elif response.status_code == 404:
|
| 150 |
+
logger.warning(f"[Supadata] Transcript not found ({response.status_code}) for {video_id}.")
|
| 151 |
+
return None
|
| 152 |
+
else:
|
| 153 |
+
logger.error(f"[Supadata] Unexpected status code {response.status_code} for {video_id}. Response: {response.text[:200]}...")
|
| 154 |
+
return None
|
| 155 |
+
except requests.exceptions.Timeout:
|
| 156 |
+
logger.error(f"[Supadata] Timeout error connecting to API for {video_id}")
|
| 157 |
+
return None
|
| 158 |
+
except requests.exceptions.RequestException as e:
|
| 159 |
+
logger.error(f"[Supadata] Request error connecting to API for {video_id}: {e}")
|
| 160 |
+
return None
|
| 161 |
+
except Exception as e:
|
| 162 |
+
logger.error(f"[Supadata] Unexpected error during API call for {video_id}: {e}", exc_info=True)
|
| 163 |
+
return None
|
| 164 |
+
|
| 165 |
+
# Apify Transcript Fetching
|
| 166 |
+
async def get_transcript_via_apify(video_url: str, api_token: str):
|
| 167 |
+
"""Fetches YouTube transcript via Apify API."""
|
| 168 |
+
if not video_url: logger.error("[Apify] get_transcript_via_apify called with no video_url"); return None
|
| 169 |
+
if not api_token: logger.error("[Apify] API token is missing."); return None # Already checked
|
| 170 |
+
if not ApifyClient: logger.error("[Apify] ApifyClient not available/imported."); return None
|
| 171 |
+
|
| 172 |
+
logger.info(f"[Apify] Attempting fetch for URL: {video_url}")
|
| 173 |
+
actor_id = "karamelo~youtube-transcripts"
|
| 174 |
+
api_endpoint = f"https://api.apify.com/v2/acts/{actor_id}/run-sync-get-dataset-items"
|
| 175 |
+
params = {"token": api_token}
|
| 176 |
+
payload = json.dumps({
|
| 177 |
+
"urls": [video_url],
|
| 178 |
+
"outputFormat": "singleStringText",
|
| 179 |
+
"maxRetries": 5,
|
| 180 |
+
"channelHandleBoolean": False,
|
| 181 |
+
"channelNameBoolean": False,
|
| 182 |
+
"datePublishedBoolean": False,
|
| 183 |
+
"relativeDateTextBoolean": False,
|
| 184 |
+
})
|
| 185 |
+
headers = {"Content-Type": "application/json"}
|
| 186 |
+
try:
|
| 187 |
+
logger.debug(f"[Apify] Sending request to run actor {actor_id} synchronously for {video_url}")
|
| 188 |
+
response = await asyncio.to_thread(requests.post, api_endpoint, headers=headers, params=params, data=payload, timeout=90) # Longer timeout for actor run
|
| 189 |
+
logger.debug(f"[Apify] Received status code {response.status_code} for {video_url}")
|
| 190 |
+
if response.status_code == 200:
|
| 191 |
+
try:
|
| 192 |
+
results = response.json()
|
| 193 |
+
if isinstance(results, list) and len(results) > 0:
|
| 194 |
+
item = results[0]
|
| 195 |
+
content = item.get("text") or item.get("transcript") or item.get("captions_concatenated")
|
| 196 |
+
if not content and item.get("captions") and isinstance(item["captions"], list): # Handle 'captions' format if primary keys fail
|
| 197 |
+
logger.info("[Apify] Processing 'captions' format.")
|
| 198 |
+
content = " ".join(cap.get("text", "") for cap in item["captions"] if cap.get("text"))
|
| 199 |
+
if content and isinstance(content, str):
|
| 200 |
+
logger.info(f"[Apify] Successfully fetched transcript for {video_url}. Length: {len(content)}")
|
| 201 |
+
return content.strip()
|
| 202 |
+
else:
|
| 203 |
+
logger.warning(f"[Apify] Actor run successful but transcript content not found/empty in result for {video_url}. Result item: {item}")
|
| 204 |
+
return None
|
| 205 |
+
else:
|
| 206 |
+
logger.warning(f"[Apify] Actor run successful but dataset was empty for {video_url}. Response: {results}")
|
| 207 |
+
return None
|
| 208 |
+
except json.JSONDecodeError:
|
| 209 |
+
logger.error(f"[Apify] Failed to decode JSON response for {video_url}. Status: {response.status_code}. Response text: {response.text[:200]}...")
|
| 210 |
+
return None
|
| 211 |
+
except Exception as e:
|
| 212 |
+
logger.error(f"[Apify] Error processing successful response for {video_url}: {e}", exc_info=True)
|
| 213 |
+
return None
|
| 214 |
+
elif response.status_code == 400:
|
| 215 |
+
logger.error(f"[Apify] Bad Request (400) for {video_url}. Check input payload. Response: {response.text[:200]}...")
|
| 216 |
+
return None
|
| 217 |
+
elif response.status_code == 401:
|
| 218 |
+
logger.error("[Apify] Authentication error (401). Check API token.")
|
| 219 |
+
return None # Don't retry if token is bad
|
| 220 |
+
else:
|
| 221 |
+
logger.error(f"[Apify] Unexpected status code {response.status_code} for {video_url}. Response: {response.text[:200]}...")
|
| 222 |
+
return None
|
| 223 |
+
except requests.exceptions.Timeout:
|
| 224 |
+
logger.error(f"[Apify] Timeout error running actor for {video_url}")
|
| 225 |
+
return None
|
| 226 |
+
except requests.exceptions.RequestException as e:
|
| 227 |
+
logger.error(f"[Apify] Request error running actor for {video_url}: {e}")
|
| 228 |
+
return None
|
| 229 |
+
except Exception as e:
|
| 230 |
+
logger.error(f"[Apify] Unexpected error during Apify call for {video_url}: {e}", exc_info=True)
|
| 231 |
+
return None
|
| 232 |
+
|
| 233 |
+
# Combined YouTube Transcript Function (with Fallbacks)
|
| 234 |
+
async def get_youtube_transcript(video_id: str, video_url: str, supadata_key: str | None, apify_token: str | None):
|
| 235 |
+
"""Fetches YouTube transcript using library, then Supadata, then Apify."""
|
| 236 |
+
if not video_id: logger.error("get_youtube_transcript called with no video_id"); return None
|
| 237 |
+
logger.info(f"Fetching transcript for video ID: {video_id} (URL: {video_url})")
|
| 238 |
+
transcript_text = None
|
| 239 |
+
|
| 240 |
+
# 1. Primary Method: youtube-transcript-api
|
| 241 |
+
logger.info("[Primary YT] Attempting youtube-transcript-api...")
|
| 242 |
+
try:
|
| 243 |
+
# Run synchronous library call in a thread
|
| 244 |
+
transcript_list = await asyncio.to_thread(
|
| 245 |
+
YouTubeTranscriptApi.get_transcript,
|
| 246 |
+
video_id,
|
| 247 |
+
languages=['en', 'en-GB', 'en-US'] # Prioritize English variations
|
| 248 |
+
)
|
| 249 |
+
if transcript_list:
|
| 250 |
+
transcript_text = " ".join([item['text'] for item in transcript_list if 'text' in item])
|
| 251 |
+
if transcript_text:
|
| 252 |
+
logger.info(f"[Primary YT] Successfully fetched transcript via library for {video_id} (length: {len(transcript_text)})")
|
| 253 |
+
return transcript_text # Return immediately on success
|
| 254 |
+
else:
|
| 255 |
+
logger.warning(f"[Primary YT] Joined transcript text is empty for {video_id}")
|
| 256 |
+
transcript_text = None # Ensure it's None if empty after join
|
| 257 |
+
else:
|
| 258 |
+
logger.warning(f"[Primary YT] Transcript list empty for {video_id}")
|
| 259 |
+
transcript_text = None
|
| 260 |
+
except Exception as e:
|
| 261 |
+
logger.warning(f"[Primary YT] Error getting transcript via library for {video_id}: {e}")
|
| 262 |
+
if "No transcript found" in str(e): logger.warning(f"[Primary YT] No transcript found for {video_id}. May be unavailable/private.")
|
| 263 |
+
elif "disabled" in str(e): logger.warning(f"[Primary YT] Transcripts disabled for {video_id}.")
|
| 264 |
+
transcript_text = None # Ensure it's None on error
|
| 265 |
+
|
| 266 |
+
# 2. Fallback 1: Supadata API
|
| 267 |
+
if transcript_text is None:
|
| 268 |
+
logger.info("[Fallback YT 1] Primary method failed. Trying Supadata API...")
|
| 269 |
+
if supadata_key:
|
| 270 |
+
transcript_text = await get_transcript_via_supadata(video_id, supadata_key)
|
| 271 |
+
if transcript_text:
|
| 272 |
+
logger.info(f"[Fallback YT 1] Successfully fetched transcript via Supadata for {video_id}")
|
| 273 |
+
return transcript_text # Return on success
|
| 274 |
+
else:
|
| 275 |
+
logger.warning(f"[Fallback YT 1] Supadata API failed or returned no content for {video_id}.")
|
| 276 |
+
else:
|
| 277 |
+
logger.warning("[Fallback YT 1] Supadata API key not available. Skipping.")
|
| 278 |
+
|
| 279 |
+
# 3. Fallback 2: Apify API
|
| 280 |
+
if transcript_text is None:
|
| 281 |
+
logger.info("[Fallback YT 2] Primary & Supadata failed. Trying Apify API...")
|
| 282 |
+
if apify_token:
|
| 283 |
+
transcript_text = await get_transcript_via_apify(video_url, apify_token)
|
| 284 |
+
if transcript_text:
|
| 285 |
+
logger.info(f"[Fallback YT 2] Successfully fetched transcript via Apify for {video_url}")
|
| 286 |
+
return transcript_text # Return on success
|
| 287 |
+
else:
|
| 288 |
+
logger.warning(f"[Fallback YT 2] Apify API failed or returned no content for {video_url}.")
|
| 289 |
+
else:
|
| 290 |
+
logger.warning("[Fallback YT 2] Apify API token not available. Skipping.")
|
| 291 |
+
|
| 292 |
+
# If all methods failed
|
| 293 |
+
if transcript_text is None:
|
| 294 |
+
logger.error(f"All methods failed to fetch transcript for video ID: {video_id}")
|
| 295 |
+
return None
|
| 296 |
+
|
| 297 |
+
# Should not be reached if logic above is correct, but as a safeguard
|
| 298 |
+
return transcript_text
|
| 299 |
+
|
| 300 |
+
# Website Content via Requests/BS4 (Primary Method for Simplified Bot)
|
| 301 |
+
async def get_website_content_via_requests(url):
|
| 302 |
+
"""Attempts to scrape website content using requests/BeautifulSoup (Primary Method)."""
|
| 303 |
+
if not url: logger.error("[Web Scraper - Requests/BS4] called with no URL"); return None
|
| 304 |
+
logger.info(f"[Web Scraper - Requests/BS4] Fetching website content for: {url}")
|
| 305 |
+
try:
|
| 306 |
+
headers = {
|
| 307 |
+
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36', # Updated UA
|
| 308 |
+
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
|
| 309 |
+
'Accept-Language': 'en-US,en;q=0.9',
|
| 310 |
+
'Connection': 'keep-alive',
|
| 311 |
+
'DNT': '1', # Do Not Track
|
| 312 |
+
'Upgrade-Insecure-Requests': '1'
|
| 313 |
+
}
|
| 314 |
+
logger.debug(f"[Web Scraper - Requests/BS4] Sending request to {url}")
|
| 315 |
+
# Run blocking I/O in a separate thread
|
| 316 |
+
response = await asyncio.to_thread(requests.get, url, headers=headers, timeout=25, allow_redirects=True)
|
| 317 |
+
response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx)
|
| 318 |
+
logger.debug(f"[Web Scraper - Requests/BS4] Received response {response.status_code} from {url}")
|
| 319 |
+
|
| 320 |
+
content_type = response.headers.get('content-type', '').lower()
|
| 321 |
+
if 'html' not in content_type:
|
| 322 |
+
logger.warning(f"[Web Scraper - Requests/BS4] Non-HTML content type received from {url}: {content_type}")
|
| 323 |
+
return None # Don't try to parse non-html
|
| 324 |
+
|
| 325 |
+
# Use html.parser, it's built-in
|
| 326 |
+
soup = BeautifulSoup(response.text, 'html.parser')
|
| 327 |
+
|
| 328 |
+
# Remove common unwanted tags more aggressively
|
| 329 |
+
for element in soup(["script", "style", "header", "footer", "nav", "aside", "form", "button", "input", "textarea", "select", "option", "label", "iframe", "img", "svg", "link", "meta", "noscript", "figure", "figcaption", "video", "audio"]):
|
| 330 |
+
element.extract()
|
| 331 |
+
|
| 332 |
+
# Try finding common main content containers
|
| 333 |
+
main_content = soup.find('main') or \
|
| 334 |
+
soup.find('article') or \
|
| 335 |
+
soup.find(id='content') or \
|
| 336 |
+
soup.find(class_='content') or \
|
| 337 |
+
soup.find(id='main-content') or \
|
| 338 |
+
soup.find(class_='main-content') or \
|
| 339 |
+
soup.find(role='main')
|
| 340 |
+
|
| 341 |
+
# Fallback to body if no specific container found
|
| 342 |
+
target_element = main_content if main_content else soup.body
|
| 343 |
+
|
| 344 |
+
if not target_element:
|
| 345 |
+
logger.warning(f"[Web Scraper - Requests/BS4] Could not find body or main content container for parsing {url}")
|
| 346 |
+
return None # Nothing to parse
|
| 347 |
+
|
| 348 |
+
# Get text, joining lines smartly
|
| 349 |
+
lines = [line.strip() for line in target_element.get_text(separator='\n', strip=True).splitlines() if line.strip()]
|
| 350 |
+
text = "\n".join(lines) # Join with newlines to preserve some structure
|
| 351 |
+
|
| 352 |
+
# Basic length check
|
| 353 |
+
if not text or len(text) < 50: # Arbitrary short length check
|
| 354 |
+
logger.warning(f"[Web Scraper - Requests/BS4] Extracted text is very short or empty after cleaning for {url} (Length: {len(text)})")
|
| 355 |
+
# Consider returning None if too short, depends on use case
|
| 356 |
+
# return None
|
| 357 |
+
|
| 358 |
+
logger.info(f"[Web Scraper - Requests/BS4] Successfully scraped content for {url} (final length: {len(text)})")
|
| 359 |
+
return text
|
| 360 |
+
|
| 361 |
+
except requests.exceptions.Timeout:
|
| 362 |
+
logger.error(f"[Web Scraper - Requests/BS4] Timeout error scraping website: {url}")
|
| 363 |
+
return None
|
| 364 |
+
except requests.exceptions.TooManyRedirects:
|
| 365 |
+
logger.error(f"[Web Scraper - Requests/BS4] Too many redirects error scraping website: {url}")
|
| 366 |
+
return None
|
| 367 |
+
except requests.exceptions.RequestException as e:
|
| 368 |
+
# This catches ConnectTimeout, HTTPError, ConnectionError etc.
|
| 369 |
+
logger.error(f"[Web Scraper - Requests/BS4] Request error scraping website {url}: {e}")
|
| 370 |
+
return None
|
| 371 |
+
except Exception as e:
|
| 372 |
+
# Catch-all for unexpected errors during parsing etc.
|
| 373 |
+
logger.error(f"[Web Scraper - Requests/BS4] Error scraping or parsing website {url}: {e}", exc_info=True)
|
| 374 |
+
return None
|
| 375 |
+
|
| 376 |
+
# Website Content via URLToText API (Fallback Method)
|
| 377 |
+
async def get_website_content_via_urltotext_api(url: str, api_key: str):
|
| 378 |
+
"""Fetches website content using the URLToText API (Fallback)."""
|
| 379 |
+
if not url: logger.error("[Web Scraper - URLToText API] called with no URL"); return None
|
| 380 |
+
if not api_key: logger.error("[Web Scraper - URLToText API] API key is missing."); return None # Already checked
|
| 381 |
+
logger.info(f"[Web Scraper - URLToText API] Attempting to fetch content for: {url}")
|
| 382 |
+
api_endpoint = "https://urltotext.com/api/v1/urltotext/"
|
| 383 |
+
payload = json.dumps({
|
| 384 |
+
"url": url,
|
| 385 |
+
"output_format": "text",
|
| 386 |
+
"extract_main_content": True,
|
| 387 |
+
"render_javascript": True, # Often needed for modern sites
|
| 388 |
+
"residential_proxy": False, # Start with standard
|
| 389 |
+
})
|
| 390 |
+
headers = {
|
| 391 |
+
"Authorization": f"Token {api_key}",
|
| 392 |
+
"Content-Type": "application/json"
|
| 393 |
+
}
|
| 394 |
+
try:
|
| 395 |
+
logger.debug(f"[Web Scraper - URLToText API] Sending request for {url}")
|
| 396 |
+
response = await asyncio.to_thread(requests.post, api_endpoint, headers=headers, data=payload, timeout=45)
|
| 397 |
+
logger.debug(f"[Web Scraper - URLToText API] Received status code {response.status_code} for {url}")
|
| 398 |
+
if response.status_code == 200:
|
| 399 |
+
try:
|
| 400 |
+
data = response.json()
|
| 401 |
+
content = data.get("data", {}).get("content")
|
| 402 |
+
credits = data.get("credits_used", "N/A")
|
| 403 |
+
warning = data.get("data", {}).get("warning")
|
| 404 |
+
if warning: logger.warning(f"[Web Scraper - URLToText API] Warning for {url}: {warning}")
|
| 405 |
+
if content:
|
| 406 |
+
logger.info(f"[Web Scraper - URLToText API] Successfully fetched content via API for {url}. Length: {len(content)}. Credits: {credits}")
|
| 407 |
+
return content.strip()
|
| 408 |
+
else:
|
| 409 |
+
logger.warning(f"[Web Scraper - URLToText API] API returned success but content was empty for {url}. Response: {data}")
|
| 410 |
+
return None
|
| 411 |
+
except json.JSONDecodeError:
|
| 412 |
+
logger.error(f"[Web Scraper - URLToText API] Failed to decode JSON response for {url}. Response: {response.text[:500]}...")
|
| 413 |
+
return None
|
| 414 |
+
except Exception as e:
|
| 415 |
+
logger.error(f"[Web Scraper - URLToText API] Error processing successful API response for {url}: {e}", exc_info=True)
|
| 416 |
+
return None
|
| 417 |
+
elif response.status_code in [400, 402, 422, 500]: # Known client/server errors
|
| 418 |
+
logger.error(f"[Web Scraper - URLToText API] Error {response.status_code} from API for {url}. Response: {response.text[:200]}...")
|
| 419 |
+
return None
|
| 420 |
+
else: # Other unexpected codes
|
| 421 |
+
logger.error(f"[Web Scraper - URLToText API] Unexpected status {response.status_code} from API for {url}. Response: {response.text[:200]}...")
|
| 422 |
+
return None
|
| 423 |
+
except requests.exceptions.Timeout:
|
| 424 |
+
logger.error(f"[Web Scraper - URLToText API] Timeout error connecting to API for {url}")
|
| 425 |
+
return None
|
| 426 |
+
except requests.exceptions.RequestException as e:
|
| 427 |
+
logger.error(f"[Web Scraper - URLToText API] Request error connecting to API for {url}: {e}")
|
| 428 |
+
return None
|
| 429 |
+
except Exception as e:
|
| 430 |
+
logger.error(f"[Web Scraper - URLToText API] Unexpected error during API call for {url}: {e}", exc_info=True)
|
| 431 |
+
return None
|
| 432 |
+
|
| 433 |
+
# DeepSeek Summary Function (via OpenRouter)
|
| 434 |
+
async def generate_summary(text: str, summary_type: str, api_key: str) -> str:
|
| 435 |
+
"""Generates summary using DeepSeek via OpenRouter API."""
|
| 436 |
+
logger.info(f"Generating {summary_type} summary using DeepSeek/OpenRouter. Input text length: {len(text)}")
|
| 437 |
+
if not api_key:
|
| 438 |
+
logger.error("OpenRouter API key was not provided to generate_summary.")
|
| 439 |
+
return "Error: AI model configuration key (OpenRouter) is missing."
|
| 440 |
+
|
| 441 |
+
openrouter_api_endpoint = "https://openrouter.ai/api/v1/chat/completions"
|
| 442 |
+
# Check OpenRouter docs for the latest recommended free/low-cost models
|
| 443 |
+
model_name = "deepseek/deepseek-chat:free"
|
| 444 |
+
|
| 445 |
+
if summary_type == "paragraph":
|
| 446 |
+
prompt = "You are an AI model designed to provide concise summaries using British English spellings. Your output MUST be: • Clear and simple language suitable for someone unfamiliar with the topic. • Uses British English spellings throughout. • Straightforward and understandable vocabulary; avoid complex terms. • Presented as ONE SINGLE PARAGRAPH. • No more than 85 words maximum; but does not have to be exactly 85. • Considers the entire text content equally. • Uses semicolons (;) instead of em dashes (– or —). Here is the text to summarise:"
|
| 447 |
+
else: # points summary
|
| 448 |
+
prompt = """You are an AI model designed to provide concise summaries using British English spellings. Your output MUST strictly follow this Markdown format:
|
| 449 |
+
• For each distinct topic or section identified in the text, create a heading.
|
| 450 |
+
• Each heading MUST be enclosed in double asterisks for bolding (e.g., **Section Title**).
|
| 451 |
+
• Immediately following each heading, list the key points as a bulleted list.
|
| 452 |
+
• Each bullet point MUST start with a hyphen and a space (`- `) on a new line.
|
| 453 |
+
• The text within each bullet point should NOT contain any bold formatting.
|
| 454 |
+
• Use clear, simple, and straightforward language suitable for someone unfamiliar with the topic.
|
| 455 |
+
• Use British English spellings throughout.
|
| 456 |
+
• Avoid overly complex or advanced vocabulary.
|
| 457 |
+
• Keep bullet points concise.
|
| 458 |
+
• Ensure the entire summary takes no more than two minutes to read.
|
| 459 |
+
• Consider the entire text's content, not just the beginning or a few topics.
|
| 460 |
+
• Use semicolons (;) instead of em dashes (– or —).
|
| 461 |
+
|
| 462 |
+
Here is the text to summarise:"""
|
| 463 |
+
|
| 464 |
+
MAX_INPUT_LENGTH = 500000 # Truncate long inputs to avoid high costs/errors
|
| 465 |
+
if len(text) > MAX_INPUT_LENGTH:
|
| 466 |
+
logger.warning(f"Input text length ({len(text)}) exceeds limit ({MAX_INPUT_LENGTH}). Truncating.")
|
| 467 |
+
text = text[:MAX_INPUT_LENGTH] + "... (Content truncated)"
|
| 468 |
+
full_prompt = f"{prompt}\n\n{text}"
|
| 469 |
+
|
| 470 |
+
headers = {
|
| 471 |
+
"Authorization": f"Bearer {api_key}",
|
| 472 |
+
"Content-Type": "application/json",
|
| 473 |
+
# Recommended headers for OpenRouter identification
|
| 474 |
+
"HTTP-Referer": "https://huggingface.co/spaces/", # Identify source as HF Space
|
| 475 |
+
"X-Title": "Telegram Summary Bot (HF Space)", # Identify app
|
| 476 |
+
}
|
| 477 |
+
payload = json.dumps({
|
| 478 |
+
"model": model_name,
|
| 479 |
+
"messages": [
|
| 480 |
+
{"role": "user", "content": full_prompt}
|
| 481 |
+
],
|
| 482 |
+
# Optional: Add max_tokens if needed, check model defaults
|
| 483 |
+
# "max_tokens": 1024,
|
| 484 |
+
})
|
| 485 |
+
|
| 486 |
+
try:
|
| 487 |
+
logger.debug(f"Sending request to OpenRouter ({model_name})...")
|
| 488 |
+
# Run blocking request in thread
|
| 489 |
+
response = await asyncio.to_thread(requests.post, openrouter_api_endpoint, headers=headers, data=payload, timeout=60)
|
| 490 |
+
logger.debug(f"Received status code {response.status_code} from OpenRouter.")
|
| 491 |
+
|
| 492 |
+
if response.status_code == 200:
|
| 493 |
+
try:
|
| 494 |
+
data = response.json()
|
| 495 |
+
if data.get("choices") and isinstance(data["choices"], list) and len(data["choices"]) > 0:
|
| 496 |
+
message = data["choices"][0].get("message")
|
| 497 |
+
if message and isinstance(message, dict):
|
| 498 |
+
summary = message.get("content")
|
| 499 |
+
if summary:
|
| 500 |
+
logger.info(f"Successfully generated summary via OpenRouter. Output length: {len(summary)}")
|
| 501 |
+
return summary.strip()
|
| 502 |
+
else:
|
| 503 |
+
logger.warning(f"OpenRouter response successful, but content was empty. Response: {data}")
|
| 504 |
+
return "Sorry, the AI model returned an empty summary."
|
| 505 |
+
else:
|
| 506 |
+
logger.error(f"Unexpected message structure in OpenRouter response: {message}. Full response: {data}")
|
| 507 |
+
return "Sorry, could not parse the AI model's response (unexpected format)."
|
| 508 |
+
else:
|
| 509 |
+
# Handle cases like moderation flags, empty choices list
|
| 510 |
+
if data.get("error"): logger.error(f"OpenRouter API Error: {data['error']}")
|
| 511 |
+
else: logger.error(f"Unexpected choices structure in OpenRouter response: {data.get('choices')}. Full response: {data}")
|
| 512 |
+
return "Sorry, could not parse the AI model's response (choices missing/invalid or API error)."
|
| 513 |
+
|
| 514 |
+
except json.JSONDecodeError:
|
| 515 |
+
logger.error(f"Failed to decode JSON response from OpenRouter. Status: {response.status_code}. Response text: {response.text[:500]}...")
|
| 516 |
+
return "Sorry, failed to understand the response from the AI model."
|
| 517 |
+
except Exception as e:
|
| 518 |
+
logger.error(f"Error processing successful OpenRouter response: {e}", exc_info=True)
|
| 519 |
+
return "Sorry, an error occurred while processing the AI model's response."
|
| 520 |
+
|
| 521 |
+
elif response.status_code == 401:
|
| 522 |
+
logger.error("OpenRouter API key is invalid (401 Unauthorized). Check HF Space Secrets.")
|
| 523 |
+
return "Error: The AI model configuration key (OpenRouter) is invalid."
|
| 524 |
+
elif response.status_code == 402:
|
| 525 |
+
logger.error("OpenRouter Payment Required (402). Check credits/limits on OpenRouter.")
|
| 526 |
+
return "Sorry, there might be an issue with the AI model service limits or payment. Please try again later or check OpenRouter account."
|
| 527 |
+
elif response.status_code == 429:
|
| 528 |
+
logger.warning("OpenRouter Rate Limit Exceeded (429).")
|
| 529 |
+
return "Sorry, the AI model is currently busy due to high demand. Please try again in a moment."
|
| 530 |
+
elif response.status_code == 500:
|
| 531 |
+
logger.error(f"OpenRouter Internal Server Error (500). Response: {response.text[:500]}...")
|
| 532 |
+
return "Sorry, the AI model service encountered an internal error. Please try again later."
|
| 533 |
+
else:
|
| 534 |
+
# Handle other potential errors (e.g., 400 Bad Request, 404 Not Found for model)
|
| 535 |
+
logger.error(f"Unexpected status code {response.status_code} from OpenRouter. Response: {response.text[:500]}...")
|
| 536 |
+
try: # Try to parse error message from response body
|
| 537 |
+
error_data = response.json()
|
| 538 |
+
error_msg = error_data.get("error", {}).get("message", response.text[:100])
|
| 539 |
+
return f"Sorry, the AI model service returned an error ({response.status_code}): {error_msg}"
|
| 540 |
+
except: # Fallback if parsing fails
|
| 541 |
+
return f"Sorry, the AI model service returned an unexpected status ({response.status_code})."
|
| 542 |
+
|
| 543 |
+
except requests.exceptions.Timeout:
|
| 544 |
+
logger.error("Timeout error connecting to OpenRouter API.")
|
| 545 |
+
return "Sorry, the request to the AI model timed out. Please try again."
|
| 546 |
+
except requests.exceptions.RequestException as e:
|
| 547 |
+
logger.error(f"Request error connecting to OpenRouter API: {e}")
|
| 548 |
+
return "Sorry, there was an error connecting to the AI model service."
|
| 549 |
+
except Exception as e:
|
| 550 |
+
logger.error(f"Unexpected error in generate_summary (OpenRouter): {e}", exc_info=True)
|
| 551 |
+
return "Sorry, an unexpected error occurred while generating the summary."
|
| 552 |
+
|
| 553 |
+
|
| 554 |
+
|
| 555 |
+
# --- Telegram Bot Handlers (Command, Message, CallbackQuery) ---
|
| 556 |
+
|
| 557 |
+
async def start(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
|
| 558 |
+
"""Sends a welcome message when the /start command is issued."""
|
| 559 |
+
user = update.effective_user
|
| 560 |
+
logger.info(f"User {user.id} ({user.username or 'NoUsername'}) used /start.")
|
| 561 |
+
mention = user.mention_html() if user.username else user.first_name
|
| 562 |
+
await update.message.reply_html(
|
| 563 |
+
f"👋 Hello {mention}! I can summarize YouTube links or website URLs.\n\n"
|
| 564 |
+
"Just send me a link anytime!",
|
| 565 |
+
# Optional: disable_web_page_preview=True
|
| 566 |
+
)
|
| 567 |
+
|
| 568 |
+
async def help_command(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
|
| 569 |
+
"""Sends a help message when the /help command is issued."""
|
| 570 |
+
logger.info(f"User {update.effective_user.id} used /help.")
|
| 571 |
+
await update.message.reply_text(
|
| 572 |
+
"🔍 **How to use this bot:**\n\n"
|
| 573 |
+
"1. Send me any YouTube video link or website URL.\n"
|
| 574 |
+
"2. I'll ask how you want it summarized (paragraph or points).\n"
|
| 575 |
+
"3. Click the button for your choice.\n"
|
| 576 |
+
"4. Wait for the summary!\n\n"
|
| 577 |
+
"I use multiple methods if the first fails (especially for YT transcripts & website content).\n\n"
|
| 578 |
+
"**Commands:**\n"
|
| 579 |
+
"/start - Display welcome message\n"
|
| 580 |
+
"/help - Show this help message",
|
| 581 |
+
parse_mode=ParseMode.MARKDOWN
|
| 582 |
+
)
|
| 583 |
+
|
| 584 |
+
async def handle_potential_url(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
|
| 585 |
+
"""Handles text messages, checks for URLs, and asks for summary type."""
|
| 586 |
+
if not update.message or not update.message.text: return # Ignore empty messages
|
| 587 |
+
url = update.message.text.strip()
|
| 588 |
+
user = update.effective_user
|
| 589 |
+
logger.info(f"User {user.id} ({user.username or 'NoUsername'}) sent potential URL: {url}")
|
| 590 |
+
|
| 591 |
+
# Basic URL validation
|
| 592 |
+
if not (url.startswith('http://') or url.startswith('https://')) or '.' not in url[8:]:
|
| 593 |
+
logger.debug(f"Ignoring non-URL message from user {user.id}: {url}")
|
| 594 |
+
# Optional: Reply if you want to guide the user
|
| 595 |
+
# await update.message.reply_text("Please send a valid URL starting with http:// or https://")
|
| 596 |
+
return
|
| 597 |
+
|
| 598 |
+
# Store URL in user_data (simple state management)
|
| 599 |
+
context.user_data['url_to_summarize'] = url
|
| 600 |
+
logger.debug(f"Stored URL '{url}' for user {user.id} in user_data")
|
| 601 |
+
|
| 602 |
+
# Ask for summary type with Inline Keyboard
|
| 603 |
+
keyboard = [
|
| 604 |
+
[
|
| 605 |
+
InlineKeyboardButton("Paragraph Summary", callback_data="paragraph"),
|
| 606 |
+
InlineKeyboardButton("Points Summary", callback_data="points")
|
| 607 |
+
]
|
| 608 |
+
]
|
| 609 |
+
reply_markup = InlineKeyboardMarkup(keyboard)
|
| 610 |
+
await update.message.reply_text(
|
| 611 |
+
f"Okay, I see this link:\n{url}\n\nHow would you like it summarized?",
|
| 612 |
+
reply_markup=reply_markup,
|
| 613 |
+
disable_web_page_preview=True
|
| 614 |
+
)
|
| 615 |
+
|
| 616 |
+
async def handle_summary_type_callback(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
|
| 617 |
+
"""Handles button presses for summary type selection."""
|
| 618 |
+
query = update.callback_query
|
| 619 |
+
if not query: return
|
| 620 |
+
await query.answer() # Acknowledge button press immediately
|
| 621 |
+
|
| 622 |
+
summary_type = query.data
|
| 623 |
+
user = update.effective_user or query.from_user # Get user info
|
| 624 |
+
url = context.user_data.get('url_to_summarize', None) # Retrieve stored URL
|
| 625 |
+
|
| 626 |
+
logger.info(f"User {user.id} chose '{summary_type}' summary. Checking for URL '{url}' in context.")
|
| 627 |
+
|
| 628 |
+
# Check if URL is still in context (it might expire or be lost)
|
| 629 |
+
if not url:
|
| 630 |
+
logger.warning(f"User {user.id} pressed button, but NO URL found in user_data context.")
|
| 631 |
+
try:
|
| 632 |
+
# Edit the message where the button was, informing the user
|
| 633 |
+
await query.edit_message_text(text="Sorry, I couldn't find the URL associated with this request. Please send the link again.")
|
| 634 |
+
except Exception as edit_err:
|
| 635 |
+
# If editing fails (e.g., message too old), log it but don't crash
|
| 636 |
+
logger.warning(f"Failed to edit message for missing URL context: {edit_err}")
|
| 637 |
+
# Maybe send a new message as a fallback? Depends on desired behavior.
|
| 638 |
+
# await context.bot.send_message(chat_id=user.id, text="Sorry, context lost. Please send link again.")
|
| 639 |
+
return # Stop processing if URL is missing
|
| 640 |
+
|
| 641 |
+
# Clear the URL from context now that we're processing it
|
| 642 |
+
context.user_data.pop('url_to_summarize', None)
|
| 643 |
+
logger.debug(f"Retrieved and cleared URL {url} from user_data for user {user.id}")
|
| 644 |
+
|
| 645 |
+
# --- Get API Keys (Read fresh from environment - cheap operation) ---
|
| 646 |
+
# This ensures if secrets are updated in HF UI, the next request uses them
|
| 647 |
+
logger.debug("Reading API keys from environment variables within handler...")
|
| 648 |
+
current_openrouter_key = os.environ.get('OPENROUTER_API_KEY')
|
| 649 |
+
current_urltotext_key = os.environ.get('URLTOTEXT_API_KEY')
|
| 650 |
+
current_supadata_key = os.environ.get('SUPADATA_API_KEY')
|
| 651 |
+
current_apify_token = os.environ.get('APIFY_API_TOKEN')
|
| 652 |
+
logger.debug(f"Keys read: OpenRouter={'Yes' if current_openrouter_key else 'No'}, URLToText={'Yes' if current_urltotext_key else 'No'}, Supadata={'Yes' if current_supadata_key else 'No'}, Apify={'Yes' if current_apify_token else 'No'}")
|
| 653 |
+
|
| 654 |
+
|
| 655 |
+
# Check *essential* key for summarization
|
| 656 |
+
if not current_openrouter_key:
|
| 657 |
+
logger.error("OpenRouter API key missing in handler. Cannot generate summary.")
|
| 658 |
+
# Inform user and clean up the button message
|
| 659 |
+
await context.bot.send_message(chat_id=user.id, text="Error: AI model configuration key (OpenRouter) is missing. Cannot generate summary.")
|
| 660 |
+
try: await query.delete_message() # Delete the message with buttons
|
| 661 |
+
except Exception: pass
|
| 662 |
+
return
|
| 663 |
+
|
| 664 |
+
# --- Start Processing ---
|
| 665 |
+
processing_message = f"Got it! Generating '{summary_type}' summary for:\n{url}\n\nThis might take a moment..."
|
| 666 |
+
message_to_delete_later = None # In case editing fails
|
| 667 |
+
try:
|
| 668 |
+
# Edit the message to show processing status
|
| 669 |
+
await query.edit_message_text(processing_message)
|
| 670 |
+
except Exception as e:
|
| 671 |
+
# If editing fails (e.g., message too old), send a new status message
|
| 672 |
+
logger.warning(f"Could not edit original message: {e}, sending new status message.")
|
| 673 |
+
try:
|
| 674 |
+
message_to_delete_later = await context.bot.send_message(chat_id=user.id, text=processing_message)
|
| 675 |
+
except Exception as send_err:
|
| 676 |
+
# If even sending fails, log and give up on this request
|
| 677 |
+
logger.error(f"Failed to send status message after edit failure: {send_err}")
|
| 678 |
+
return
|
| 679 |
+
|
| 680 |
+
content = None
|
| 681 |
+
user_feedback_message = None # Stores error messages for the user
|
| 682 |
+
success = False
|
| 683 |
+
is_youtube = is_youtube_url(url)
|
| 684 |
+
|
| 685 |
+
try:
|
| 686 |
+
# Show "typing..." status in Telegram chat
|
| 687 |
+
await context.bot.send_chat_action(chat_id=user.id, action='typing')
|
| 688 |
+
|
| 689 |
+
# --- Content Fetching Logic ---
|
| 690 |
+
if is_youtube:
|
| 691 |
+
video_id = extract_youtube_id(url)
|
| 692 |
+
if video_id:
|
| 693 |
+
# Fetch YT transcript using the function with fallbacks
|
| 694 |
+
content = await get_youtube_transcript(
|
| 695 |
+
video_id,
|
| 696 |
+
url, # Pass full URL for Apify
|
| 697 |
+
current_supadata_key,
|
| 698 |
+
current_apify_token
|
| 699 |
+
)
|
| 700 |
+
# Set feedback message only if content fetching failed
|
| 701 |
+
user_feedback_message = None if content else "Sorry, I couldn't get the transcript for that YouTube video using any available method (unavailable/private/no captions?)."
|
| 702 |
+
else:
|
| 703 |
+
user_feedback_message = "Sorry, I couldn't understand that YouTube URL format."
|
| 704 |
+
else: # Website Logic (Requests/BS4 -> URLToText API)
|
| 705 |
+
logger.info(f"Attempting website scrape (Requests/BS4) for {url}")
|
| 706 |
+
content = await get_website_content_via_requests(url)
|
| 707 |
+
|
| 708 |
+
if content:
|
| 709 |
+
logger.info("Primary website scraping (Requests/BS4) successful.")
|
| 710 |
+
user_feedback_message = None
|
| 711 |
+
else:
|
| 712 |
+
logger.warning(f"Primary web scraping failed for {url}. Attempting fallback API (URLToText).")
|
| 713 |
+
if current_urltotext_key:
|
| 714 |
+
await context.bot.send_chat_action(chat_id=user.id, action='typing') # Show activity for fallback
|
| 715 |
+
content = await get_website_content_via_urltotext_api(url, current_urltotext_key)
|
| 716 |
+
if content:
|
| 717 |
+
user_feedback_message = None
|
| 718 |
+
logger.info("Fallback URLToText API scraping successful.")
|
| 719 |
+
else:
|
| 720 |
+
user_feedback_message = "Sorry, I couldn't fetch content from that website using either method (blocked/inaccessible/empty?)."
|
| 721 |
+
logger.error(f"Both primary (Requests/BS4) and fallback API failed for website {url}.")
|
| 722 |
+
else:
|
| 723 |
+
# Primary failed, and fallback key is missing
|
| 724 |
+
user_feedback_message = "Sorry, I couldn't fetch content from that website (blocked/inaccessible/empty?). The fallback method is not configured."
|
| 725 |
+
logger.warning(f"Primary web scraping failed for {url}, and fallback API key (URLToText) is missing.")
|
| 726 |
+
# --- End Content Fetching ---
|
| 727 |
+
|
| 728 |
+
# --- Generate Summary if Content was Fetched ---
|
| 729 |
+
if content:
|
| 730 |
+
logger.info("Content fetched successfully, proceeding to generate summary.")
|
| 731 |
+
await context.bot.send_chat_action(chat_id=user.id, action='typing')
|
| 732 |
+
# Pass the OpenRouter key to the summary function
|
| 733 |
+
summary = await generate_summary(content, summary_type, current_openrouter_key)
|
| 734 |
+
|
| 735 |
+
# Check if summary generation returned an error message
|
| 736 |
+
if summary.startswith("Error:") or summary.startswith("Sorry,"):
|
| 737 |
+
user_feedback_message = summary # Use the error from the summary function
|
| 738 |
+
success = False
|
| 739 |
+
logger.warning(f"Summary generation failed or returned error: {summary}")
|
| 740 |
+
else:
|
| 741 |
+
# Send the successful summary
|
| 742 |
+
await context.bot.send_message(
|
| 743 |
+
chat_id=user.id,
|
| 744 |
+
text=summary,
|
| 745 |
+
parse_mode=ParseMode.MARKDOWN,
|
| 746 |
+
disable_web_page_preview=True
|
| 747 |
+
)
|
| 748 |
+
success = True
|
| 749 |
+
user_feedback_message = None # Clear any previous failure message from fetching stage
|
| 750 |
+
elif not user_feedback_message:
|
| 751 |
+
# If content is None but no specific error message was set during fetching
|
| 752 |
+
user_feedback_message = "Sorry, couldn't retrieve any content to summarize from the provided link."
|
| 753 |
+
logger.warning(f"Content fetching resulted in None for {url}, but no specific user feedback message was set.")
|
| 754 |
+
|
| 755 |
+
# --- Send Feedback if any step failed ---
|
| 756 |
+
if user_feedback_message and not success:
|
| 757 |
+
await context.bot.send_message(chat_id=user.id, text=user_feedback_message)
|
| 758 |
+
|
| 759 |
+
except Exception as e:
|
| 760 |
+
# Catch unexpected errors during the whole process
|
| 761 |
+
logger.error(f"Unexpected error during processing callback for {url}: {e}", exc_info=True)
|
| 762 |
+
try:
|
| 763 |
+
# Send a generic error message to the user
|
| 764 |
+
await context.bot.send_message(chat_id=user.id, text="Oops! Something went really wrong while processing your request. Please try again later.")
|
| 765 |
+
except Exception as final_err:
|
| 766 |
+
# If even sending the error message fails... log it.
|
| 767 |
+
logger.error(f"Failed to send final error message to user {user.id}: {final_err}")
|
| 768 |
+
finally:
|
| 769 |
+
# --- Cleanup ---
|
| 770 |
+
# Delete the "Processing..." status message or the original message with buttons
|
| 771 |
+
try:
|
| 772 |
+
if message_to_delete_later: # If we sent a separate status message
|
| 773 |
+
await context.bot.delete_message(chat_id=user.id, message_id=message_to_delete_later.message_id)
|
| 774 |
+
elif query: # Otherwise, delete the original message with the buttons
|
| 775 |
+
# We might have already edited it, but deleting ensures cleanup
|
| 776 |
+
await query.delete_message()
|
| 777 |
+
except Exception as del_e:
|
| 778 |
+
# Log if deletion fails, but don't let it stop anything
|
| 779 |
+
logger.warning(f"Could not delete status/button message: {del_e}")
|
| 780 |
+
|
| 781 |
+
|
| 782 |
+
async def error_handler(update: object, context: ContextTypes.DEFAULT_TYPE) -> None:
|
| 783 |
+
"""Log Errors caused by Updates."""
|
| 784 |
+
logger.error("Exception while handling an update:", exc_info=context.error)
|
| 785 |
+
# Optionally, notify the developer or user about the error
|
| 786 |
+
# developer_chat_id = 12345678 # Replace with your chat ID if desired
|
| 787 |
+
# if update and hasattr(update, 'effective_chat') and update.effective_chat:
|
| 788 |
+
# chat_id = update.effective_chat.id
|
| 789 |
+
# error_message = f"Error processing update {update.update_id} for chat {chat_id}. Error: {context.error}"
|
| 790 |
+
# else:
|
| 791 |
+
# error_message = f"Error in handler: {context.error}"
|
| 792 |
+
# try:
|
| 793 |
+
# await context.bot.send_message(chat_id=developer_chat_id, text=error_message)
|
| 794 |
+
# except Exception as e:
|
| 795 |
+
# logger.error(f"Failed to send error notification to developer: {e}")
|
| 796 |
+
|
| 797 |
+
|
| 798 |
+
# --- Initialize Telegram Bot Application ---
|
| 799 |
+
# Do this setup once when the script starts
|
| 800 |
+
logger.info("Initializing Telegram Application...")
|
| 801 |
+
if not TELEGRAM_TOKEN: # Check again, as initialization needs it
|
| 802 |
+
logger.critical("Cannot initialize PTB Application: TELEGRAM_TOKEN not found.")
|
| 803 |
+
ptb_app = None
|
| 804 |
+
else:
|
| 805 |
+
# Build PTB Application instance
|
| 806 |
+
ptb_app_builder = Application.builder().token(TELEGRAM_TOKEN)
|
| 807 |
+
# Removed concurrency settings for simplicity, PTB defaults should be okay with Flask + asyncio.create_task
|
| 808 |
+
# ptb_app_builder.concurrent_updates(True)
|
| 809 |
+
ptb_app = ptb_app_builder.build()
|
| 810 |
+
|
| 811 |
+
# Register handlers with the PTB application instance
|
| 812 |
+
ptb_app.add_handler(CommandHandler("start", start))
|
| 813 |
+
ptb_app.add_handler(CommandHandler("help", help_command))
|
| 814 |
+
ptb_app.add_handler(MessageHandler(filters.TEXT & ~filters.COMMAND, handle_potential_url))
|
| 815 |
+
ptb_app.add_handler(CallbackQueryHandler(handle_summary_type_callback))
|
| 816 |
+
# Add the error handler
|
| 817 |
+
ptb_app.add_error_handler(error_handler)
|
| 818 |
+
logger.info("Telegram handlers registered.")
|
| 819 |
+
|
| 820 |
+
|
| 821 |
+
# --- Flask App Setup ---
|
| 822 |
+
app = Flask(__name__) # Create Flask web server instance
|
| 823 |
+
logger.info("Flask app created.")
|
| 824 |
+
|
| 825 |
+
|
| 826 |
+
# --- Webhook Endpoint ---
|
| 827 |
+
@app.route('/webhook', methods=['POST'])
|
| 828 |
+
async def webhook() -> Response:
|
| 829 |
+
"""Webhook endpoint to receive updates from Telegram"""
|
| 830 |
+
logger.info("Webhook request received...")
|
| 831 |
+
if not ptb_app: # Check if PTB initialization failed
|
| 832 |
+
logger.error("Telegram application not initialized. Cannot process update.")
|
| 833 |
+
return Response('Bot not configured properly', status=500)
|
| 834 |
+
|
| 835 |
+
if request.is_json:
|
| 836 |
+
try:
|
| 837 |
+
update_data = request.get_json()
|
| 838 |
+
# Use PTB's built-in deserialization
|
| 839 |
+
update = Update.de_json(update_data, ptb_app.bot)
|
| 840 |
+
logger.debug(f"Processing update ID: {update.update_id}")
|
| 841 |
+
|
| 842 |
+
# Process the update using PTB's internal dispatcher in a background task
|
| 843 |
+
asyncio.create_task(ptb_app.process_update(update))
|
| 844 |
+
|
| 845 |
+
# Respond quickly to Telegram that we received the update
|
| 846 |
+
return Response('ok', status=200)
|
| 847 |
+
except json.JSONDecodeError:
|
| 848 |
+
logger.error("Failed to decode JSON from Telegram webhook.")
|
| 849 |
+
return Response('Bad Request - Invalid JSON', status=400)
|
| 850 |
+
except Exception as e:
|
| 851 |
+
logger.error(f"Error processing update in webhook handler: {e}", exc_info=True)
|
| 852 |
+
return Response('Internal Server Error', status=500)
|
| 853 |
+
else:
|
| 854 |
+
logger.warning("Received non-JSON request to webhook endpoint.")
|
| 855 |
+
return Response('Bad Request - Expected JSON', status=400)
|
| 856 |
+
|
| 857 |
+
@app.route('/')
|
| 858 |
+
def index():
|
| 859 |
+
"""A simple health check endpoint for the web server"""
|
| 860 |
+
logger.debug("Health check endpoint '/' accessed.")
|
| 861 |
+
# You could add more checks here if needed (e.g., check PTB status)
|
| 862 |
+
bot_status = "PTB App Initialized" if ptb_app else "PTB App FAILED Initialization"
|
| 863 |
+
return f"Hello! Telegram Bot Webhook Listener ({bot_status}) is running."
|
| 864 |
+
|
| 865 |
+
|
| 866 |
+
# --- Main Execution Block ---
|
| 867 |
+
# This part runs the Flask web server when the Docker container starts via Gunicorn
|
| 868 |
+
if __name__ == '__main__':
|
| 869 |
+
# This block might not run when deployed via Gunicorn as specified in Dockerfile CMD
|
| 870 |
+
# Gunicorn imports the 'app' object directly from 'main.py'.
|
| 871 |
+
# However, it's good practice to have for potential local testing.
|
| 872 |
+
if not ptb_app:
|
| 873 |
+
logger.critical("Aborting Flask server start (local test?) because Telegram App failed initialization.")
|
| 874 |
+
else:
|
| 875 |
+
logger.info("Starting Flask web server directly (for local testing?)...")
|
| 876 |
+
# Use a development server port like 5000 for local testing
|
| 877 |
+
port = int(os.environ.get('PORT', 5000)) # Changed default for local test
|
| 878 |
+
# Run with debug=True ONLY for local testing, NEVER in production/deployment
|
| 879 |
+
app.run(host='0.0.0.0', port=port, debug=True)
|