Spaces:
Running
Running
File size: 27,037 Bytes
94ec243 | 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 | from pathlib import Path
from subprocess import check_output
from sys import executable as python_executable
from scrapling.core.utils import log
from scrapling.engines.toolbelt.custom import Response
from scrapling.core.utils._shell import _CookieParser, _ParseHeaders
from scrapling.core._types import List, Optional, Dict, Tuple, Any, Callable
from orjson import loads as json_loads, JSONDecodeError
try:
from click import command, option, Choice, group, argument
except (ImportError, ModuleNotFoundError) as e:
raise ModuleNotFoundError(
"You need to install scrapling with any of the extras to enable Shell commands. See: https://scrapling.readthedocs.io/en/latest/#installation"
) from e
__OUTPUT_FILE_HELP__ = "The output file path can be an HTML file, a Markdown file of the HTML content, or the text content itself. Use file extensions (`.html`/`.md`/`.txt`) respectively."
__PACKAGE_DIR__ = Path(__file__).parent
def __Execute(cmd: List[str], help_line: str) -> None: # pragma: no cover
print(f"Installing {help_line}...")
_ = check_output(cmd, shell=False) # nosec B603
# I meant to not use try except here
def __ParseJSONData(json_string: Optional[str] = None) -> Optional[Dict[str, Any]]:
"""Parse JSON string into a Python object"""
if not json_string:
return None
try:
return json_loads(json_string)
except JSONDecodeError as err: # pragma: no cover
raise ValueError(f"Invalid JSON data '{json_string}': {err}")
def __Request_and_Save(
fetcher_func: Callable[..., Response],
url: str,
output_file: str,
css_selector: Optional[str] = None,
**kwargs,
) -> None:
"""Make a request using the specified fetcher function and save the result"""
from scrapling.core.shell import Convertor
# Handle relative paths - convert to an absolute path based on the current working directory
output_path = Path(output_file)
if not output_path.is_absolute():
output_path = Path.cwd() / output_file
response = fetcher_func(url, **kwargs)
Convertor.write_content_to_file(response, str(output_path), css_selector)
log.info(f"Content successfully saved to '{output_path}'")
def __ParseExtractArguments(
headers: List[str], cookies: str, params: str, json: Optional[str] = None
) -> Tuple[Dict[str, str], Dict[str, str], Dict[str, str], Optional[Dict[str, str]]]:
"""Parse arguments for extract command"""
parsed_headers, parsed_cookies = _ParseHeaders(headers)
if cookies:
for key, value in _CookieParser(cookies):
try:
parsed_cookies[key] = value
except Exception as err:
raise ValueError(f"Could not parse cookies '{cookies}': {err}")
parsed_json = __ParseJSONData(json)
parsed_params = {}
for param in params:
if "=" in param:
key, value = param.split("=", 1)
parsed_params[key] = value
return parsed_headers, parsed_cookies, parsed_params, parsed_json
def __BuildRequest(headers: List[str], cookies: str, params: str, json: Optional[str] = None, **kwargs) -> Dict:
"""Build a request object using the specified arguments"""
# Parse parameters
parsed_headers, parsed_cookies, parsed_params, parsed_json = __ParseExtractArguments(headers, cookies, params, json)
# Build request arguments
request_kwargs: Dict[str, Any] = {
"headers": parsed_headers if parsed_headers else None,
"cookies": parsed_cookies if parsed_cookies else None,
}
if parsed_json:
request_kwargs["json"] = parsed_json
if parsed_params:
request_kwargs["params"] = parsed_params
if "proxy" in kwargs:
request_kwargs["proxy"] = kwargs.pop("proxy")
# Parse impersonate parameter if it contains commas (for random selection)
if "impersonate" in kwargs and "," in (kwargs.get("impersonate") or ""):
kwargs["impersonate"] = [browser.strip() for browser in kwargs["impersonate"].split(",")]
return {**request_kwargs, **kwargs}
@command(help="Install all Scrapling's Fetchers dependencies")
@option(
"-f",
"--force",
"force",
is_flag=True,
default=False,
type=bool,
help="Force Scrapling to reinstall all Fetchers dependencies",
)
def install(force): # pragma: no cover
if force or not __PACKAGE_DIR__.joinpath(".scrapling_dependencies_installed").exists():
__Execute(
[python_executable, "-m", "playwright", "install", "chromium"],
"Playwright browsers",
)
__Execute(
[
python_executable,
"-m",
"playwright",
"install-deps",
"chromium",
],
"Playwright dependencies",
)
from tld.utils import update_tld_names
update_tld_names(fail_silently=True)
# if no errors raised by the above commands, then we add the below file
__PACKAGE_DIR__.joinpath(".scrapling_dependencies_installed").touch()
else:
print("The dependencies are already installed")
@command(help="Run Scrapling's MCP server (Check the docs for more info).")
@option(
"--http",
is_flag=True,
default=False,
help="Whether to run the MCP server in streamable-http transport or leave it as stdio (Default: False)",
)
@option(
"--host",
type=str,
default="0.0.0.0",
help="The host to use if streamable-http transport is enabled (Default: '0.0.0.0')",
)
@option(
"--port", type=int, default=8000, help="The port to use if streamable-http transport is enabled (Default: 8000)"
)
def mcp(http, host, port):
from scrapling.core.ai import ScraplingMCPServer
server = ScraplingMCPServer()
server.serve(http, host, port)
@command(help="Interactive scraping console")
@option(
"-c",
"--code",
"code",
is_flag=False,
default="",
type=str,
help="Evaluate the code in the shell, print the result and exit",
)
@option(
"-L",
"--loglevel",
"level",
is_flag=False,
default="debug",
type=Choice(["debug", "info", "warning", "error", "critical", "fatal"], case_sensitive=False),
help="Log level (default: DEBUG)",
)
def shell(code, level):
from scrapling.core.shell import CustomShell
console = CustomShell(code=code, log_level=level)
console.start()
@group(
help="Fetch web pages using various fetchers and extract full/selected HTML content as HTML, Markdown, or extract text content."
)
def extract():
"""Extract content from web pages and save to files"""
pass
@extract.command(help=f"Perform a GET request and save the content to a file.\n\n{__OUTPUT_FILE_HELP__}")
@argument("url", required=True)
@argument("output_file", required=True)
@option(
"--headers",
"-H",
multiple=True,
help='HTTP headers in format "Key: Value" (can be used multiple times)',
)
@option("--cookies", help='Cookies string in format "name1=value1; name2=value2"')
@option("--timeout", type=int, default=30, help="Request timeout in seconds (default: 30)")
@option("--proxy", help='Proxy URL in format "http://username:password@host:port"')
@option(
"--css-selector",
"-s",
help="CSS selector to extract specific content from the page. It returns all matches.",
)
@option(
"--params",
"-p",
multiple=True,
help='Query parameters in format "key=value" (can be used multiple times)',
)
@option(
"--follow-redirects/--no-follow-redirects",
default=True,
help="Whether to follow redirects (default: True)",
)
@option(
"--verify/--no-verify",
default=True,
help="Whether to verify SSL certificates (default: True)",
)
@option(
"--impersonate",
help="Browser to impersonate. Can be a single browser (e.g., chrome) or comma-separated list for random selection (e.g., chrome,firefox,safari).",
)
@option(
"--stealthy-headers/--no-stealthy-headers",
default=True,
help="Use stealthy browser headers (default: True)",
)
def get(
url,
output_file,
headers,
cookies,
timeout,
proxy,
css_selector,
params,
follow_redirects,
verify,
impersonate,
stealthy_headers,
):
"""
Perform a GET request and save the content to a file.
:param url: Target URL for the request.
:param output_file: Output file path (.md for Markdown, .html for HTML).
:param headers: HTTP headers to include in the request.
:param cookies: Cookies to use in the request.
:param timeout: Number of seconds to wait before timing out.
:param proxy: Proxy URL to use. (Format: "http://username:password@localhost:8030")
:param css_selector: CSS selector to extract specific content.
:param params: Query string parameters for the request.
:param follow_redirects: Whether to follow redirects.
:param verify: Whether to verify HTTPS certificates.
:param impersonate: Browser version to impersonate.
:param stealthy_headers: If enabled, creates and adds real browser headers.
"""
kwargs = __BuildRequest(
headers,
cookies,
params,
None,
timeout=timeout,
follow_redirects=follow_redirects,
verify=verify,
stealthy_headers=stealthy_headers,
impersonate=impersonate,
proxy=proxy,
)
from scrapling.fetchers import Fetcher
__Request_and_Save(Fetcher.get, url, output_file, css_selector, **kwargs)
@extract.command(help=f"Perform a POST request and save the content to a file.\n\n{__OUTPUT_FILE_HELP__}")
@argument("url", required=True)
@argument("output_file", required=True)
@option(
"--data",
"-d",
help='Form data to include in the request body (as string, ex: "param1=value1¶m2=value2")',
)
@option("--json", "-j", help="JSON data to include in the request body (as string)")
@option(
"--headers",
"-H",
multiple=True,
help='HTTP headers in format "Key: Value" (can be used multiple times)',
)
@option("--cookies", help='Cookies string in format "name1=value1; name2=value2"')
@option("--timeout", type=int, default=30, help="Request timeout in seconds (default: 30)")
@option("--proxy", help='Proxy URL in format "http://username:password@host:port"')
@option(
"--css-selector",
"-s",
help="CSS selector to extract specific content from the page. It returns all matches.",
)
@option(
"--params",
"-p",
multiple=True,
help='Query parameters in format "key=value" (can be used multiple times)',
)
@option(
"--follow-redirects/--no-follow-redirects",
default=True,
help="Whether to follow redirects (default: True)",
)
@option(
"--verify/--no-verify",
default=True,
help="Whether to verify SSL certificates (default: True)",
)
@option(
"--impersonate",
help="Browser to impersonate. Can be a single browser (e.g., chrome) or comma-separated list for random selection (e.g., chrome,firefox,safari).",
)
@option(
"--stealthy-headers/--no-stealthy-headers",
default=True,
help="Use stealthy browser headers (default: True)",
)
def post(
url,
output_file,
data,
json,
headers,
cookies,
timeout,
proxy,
css_selector,
params,
follow_redirects,
verify,
impersonate,
stealthy_headers,
):
"""
Perform a POST request and save the content to a file.
:param url: Target URL for the request.
:param output_file: Output file path (.md for Markdown, .html for HTML).
:param data: Form data to include in the request body. (as string, ex: "param1=value1¶m2=value2")
:param json: A JSON serializable object to include in the body of the request.
:param headers: Headers to include in the request.
:param cookies: Cookies to use in the request.
:param timeout: Number of seconds to wait before timing out.
:param proxy: Proxy URL to use.
:param css_selector: CSS selector to extract specific content.
:param params: Query string parameters for the request.
:param follow_redirects: Whether to follow redirects.
:param verify: Whether to verify HTTPS certificates.
:param impersonate: Browser version to impersonate.
:param stealthy_headers: If enabled, creates and adds real browser headers.
"""
kwargs = __BuildRequest(
headers,
cookies,
params,
json,
timeout=timeout,
follow_redirects=follow_redirects,
verify=verify,
stealthy_headers=stealthy_headers,
impersonate=impersonate,
proxy=proxy,
data=data,
)
from scrapling.fetchers import Fetcher
__Request_and_Save(Fetcher.post, url, output_file, css_selector, **kwargs)
@extract.command(help=f"Perform a PUT request and save the content to a file.\n\n{__OUTPUT_FILE_HELP__}")
@argument("url", required=True)
@argument("output_file", required=True)
@option("--data", "-d", help="Form data to include in the request body")
@option("--json", "-j", help="JSON data to include in the request body (as string)")
@option(
"--headers",
"-H",
multiple=True,
help='HTTP headers in format "Key: Value" (can be used multiple times)',
)
@option("--cookies", help='Cookies string in format "name1=value1; name2=value2"')
@option("--timeout", type=int, default=30, help="Request timeout in seconds (default: 30)")
@option("--proxy", help='Proxy URL in format "http://username:password@host:port"')
@option(
"--css-selector",
"-s",
help="CSS selector to extract specific content from the page. It returns all matches.",
)
@option(
"--params",
"-p",
multiple=True,
help='Query parameters in format "key=value" (can be used multiple times)',
)
@option(
"--follow-redirects/--no-follow-redirects",
default=True,
help="Whether to follow redirects (default: True)",
)
@option(
"--verify/--no-verify",
default=True,
help="Whether to verify SSL certificates (default: True)",
)
@option(
"--impersonate",
help="Browser to impersonate. Can be a single browser (e.g., chrome) or comma-separated list for random selection (e.g., chrome,firefox,safari).",
)
@option(
"--stealthy-headers/--no-stealthy-headers",
default=True,
help="Use stealthy browser headers (default: True)",
)
def put(
url,
output_file,
data,
json,
headers,
cookies,
timeout,
proxy,
css_selector,
params,
follow_redirects,
verify,
impersonate,
stealthy_headers,
):
"""
Perform a PUT request and save the content to a file.
:param url: Target URL for the request.
:param output_file: Output file path (.md for Markdown, .html for HTML).
:param data: Form data to include in the request body.
:param json: A JSON serializable object to include in the body of the request.
:param headers: Headers to include in the request.
:param cookies: Cookies to use in the request.
:param timeout: Number of seconds to wait before timing out.
:param proxy: Proxy URL to use.
:param css_selector: CSS selector to extract specific content.
:param params: Query string parameters for the request.
:param follow_redirects: Whether to follow redirects.
:param verify: Whether to verify HTTPS certificates.
:param impersonate: Browser version to impersonate.
:param stealthy_headers: If enabled, creates and adds real browser headers.
"""
kwargs = __BuildRequest(
headers,
cookies,
params,
json,
timeout=timeout,
follow_redirects=follow_redirects,
verify=verify,
stealthy_headers=stealthy_headers,
impersonate=impersonate,
proxy=proxy,
data=data,
)
from scrapling.fetchers import Fetcher
__Request_and_Save(Fetcher.put, url, output_file, css_selector, **kwargs)
@extract.command(help=f"Perform a DELETE request and save the content to a file.\n\n{__OUTPUT_FILE_HELP__}")
@argument("url", required=True)
@argument("output_file", required=True)
@option(
"--headers",
"-H",
multiple=True,
help='HTTP headers in format "Key: Value" (can be used multiple times)',
)
@option("--cookies", help='Cookies string in format "name1=value1; name2=value2"')
@option("--timeout", type=int, default=30, help="Request timeout in seconds (default: 30)")
@option("--proxy", help='Proxy URL in format "http://username:password@host:port"')
@option(
"--css-selector",
"-s",
help="CSS selector to extract specific content from the page. It returns all matches.",
)
@option(
"--params",
"-p",
multiple=True,
help='Query parameters in format "key=value" (can be used multiple times)',
)
@option(
"--follow-redirects/--no-follow-redirects",
default=True,
help="Whether to follow redirects (default: True)",
)
@option(
"--verify/--no-verify",
default=True,
help="Whether to verify SSL certificates (default: True)",
)
@option(
"--impersonate",
help="Browser to impersonate. Can be a single browser (e.g., chrome) or comma-separated list for random selection (e.g., chrome,firefox,safari).",
)
@option(
"--stealthy-headers/--no-stealthy-headers",
default=True,
help="Use stealthy browser headers (default: True)",
)
def delete(
url,
output_file,
headers,
cookies,
timeout,
proxy,
css_selector,
params,
follow_redirects,
verify,
impersonate,
stealthy_headers,
):
"""
Perform a DELETE request and save the content to a file.
:param url: Target URL for the request.
:param output_file: Output file path (.md for Markdown, .html for HTML).
:param headers: Headers to include in the request.
:param cookies: Cookies to use in the request.
:param timeout: Number of seconds to wait before timing out.
:param proxy: Proxy URL to use.
:param css_selector: CSS selector to extract specific content.
:param params: Query string parameters for the request.
:param follow_redirects: Whether to follow redirects.
:param verify: Whether to verify HTTPS certificates.
:param impersonate: Browser version to impersonate.
:param stealthy_headers: If enabled, creates and adds real browser headers.
"""
kwargs = __BuildRequest(
headers,
cookies,
params,
None,
timeout=timeout,
follow_redirects=follow_redirects,
verify=verify,
stealthy_headers=stealthy_headers,
impersonate=impersonate,
proxy=proxy,
)
from scrapling.fetchers import Fetcher
__Request_and_Save(Fetcher.delete, url, output_file, css_selector, **kwargs)
@extract.command(help=f"Use DynamicFetcher to fetch content with browser automation.\n\n{__OUTPUT_FILE_HELP__}")
@argument("url", required=True)
@argument("output_file", required=True)
@option(
"--headless/--no-headless",
default=True,
help="Run browser in headless mode (default: True)",
)
@option(
"--disable-resources/--enable-resources",
default=False,
help="Drop unnecessary resources for speed boost (default: False)",
)
@option(
"--network-idle/--no-network-idle",
default=False,
help="Wait for network idle (default: False)",
)
@option(
"--timeout",
type=int,
default=30000,
help="Timeout in milliseconds (default: 30000)",
)
@option(
"--wait",
type=int,
default=0,
help="Additional wait time in milliseconds after page load (default: 0)",
)
@option(
"--css-selector",
"-s",
help="CSS selector to extract specific content from the page. It returns all matches.",
)
@option("--wait-selector", help="CSS selector to wait for before proceeding")
@option("--locale", default=None, help="Specify user locale. Defaults to the system default locale.")
@option(
"--real-chrome/--no-real-chrome",
default=False,
help="If you have a Chrome browser installed on your device, enable this, and the Fetcher will launch an instance of your browser and use it. (default: False)",
)
@option("--proxy", help='Proxy URL in format "http://username:password@host:port"')
@option(
"--extra-headers",
"-H",
multiple=True,
help='Extra headers in format "Key: Value" (can be used multiple times)',
)
def fetch(
url,
output_file,
headless,
disable_resources,
network_idle,
timeout,
wait,
css_selector,
wait_selector,
locale,
real_chrome,
proxy,
extra_headers,
):
"""
Opens up a browser and fetch content using DynamicFetcher.
:param url: Target url.
:param output_file: Output file path (.md for Markdown, .html for HTML).
:param headless: Run the browser in headless/hidden or headful/visible mode.
:param disable_resources: Drop requests of unnecessary resources for a speed boost.
:param network_idle: Wait for the page until there are no network connections for at least 500 ms.
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page.
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before returning.
:param css_selector: CSS selector to extract specific content.
:param wait_selector: Wait for a specific CSS selector to be in a specific state.
:param locale: Set the locale for the browser.
:param real_chrome: If you have a Chrome browser installed on your device, enable this, and the Fetcher will launch an instance of your browser and use it.
:param proxy: The proxy to be used with requests.
:param extra_headers: Extra headers to add to the request.
"""
# Parse parameters
parsed_headers, _ = _ParseHeaders(extra_headers, False)
# Build request arguments
kwargs = {
"headless": headless,
"disable_resources": disable_resources,
"network_idle": network_idle,
"timeout": timeout,
"locale": locale,
"real_chrome": real_chrome,
}
if wait > 0:
kwargs["wait"] = wait
if wait_selector:
kwargs["wait_selector"] = wait_selector
if proxy:
kwargs["proxy"] = proxy
if parsed_headers:
kwargs["extra_headers"] = parsed_headers
from scrapling.fetchers import DynamicFetcher
__Request_and_Save(DynamicFetcher.fetch, url, output_file, css_selector, **kwargs)
@extract.command(help=f"Use StealthyFetcher to fetch content with advanced stealth features.\n\n{__OUTPUT_FILE_HELP__}")
@argument("url", required=True)
@argument("output_file", required=True)
@option(
"--headless/--no-headless",
default=True,
help="Run browser in headless mode (default: True)",
)
@option(
"--disable-resources/--enable-resources",
default=False,
help="Drop unnecessary resources for speed boost (default: False)",
)
@option(
"--block-webrtc/--allow-webrtc",
default=False,
help="Block WebRTC entirely (default: False)",
)
@option(
"--solve-cloudflare/--no-solve-cloudflare",
default=False,
help="Solve Cloudflare challenges (default: False)",
)
@option("--allow-webgl/--block-webgl", default=True, help="Allow WebGL (default: True)")
@option(
"--network-idle/--no-network-idle",
default=False,
help="Wait for network idle (default: False)",
)
@option(
"--real-chrome/--no-real-chrome",
default=False,
help="If you have a Chrome browser installed on your device, enable this, and the Fetcher will launch an instance of your browser and use it. (default: False)",
)
@option(
"--hide-canvas/--show-canvas",
default=False,
help="Add noise to canvas operations (default: False)",
)
@option(
"--timeout",
type=int,
default=30000,
help="Timeout in milliseconds (default: 30000)",
)
@option(
"--wait",
type=int,
default=0,
help="Additional wait time in milliseconds after page load (default: 0)",
)
@option(
"--css-selector",
"-s",
help="CSS selector to extract specific content from the page. It returns all matches.",
)
@option("--wait-selector", help="CSS selector to wait for before proceeding")
@option("--proxy", help='Proxy URL in format "http://username:password@host:port"')
@option(
"--extra-headers",
"-H",
multiple=True,
help='Extra headers in format "Key: Value" (can be used multiple times)',
)
def stealthy_fetch(
url,
output_file,
headless,
disable_resources,
block_webrtc,
solve_cloudflare,
allow_webgl,
network_idle,
real_chrome,
hide_canvas,
timeout,
wait,
css_selector,
wait_selector,
proxy,
extra_headers,
):
"""
Opens up a browser with advanced stealth features and fetch content using StealthyFetcher.
:param url: Target url.
:param output_file: Output file path (.md for Markdown, .html for HTML).
:param headless: Run the browser in headless/hidden, or headful/visible mode.
:param disable_resources: Drop requests of unnecessary resources for a speed boost.
:param block_webrtc: Blocks WebRTC entirely.
:param solve_cloudflare: Solves all types of the Cloudflare's Turnstile/Interstitial challenges.
:param allow_webgl: Allow WebGL (recommended to keep enabled).
:param network_idle: Wait for the page until there are no network connections for at least 500 ms.
:param real_chrome: If you have a Chrome browser installed on your device, enable this, and the Fetcher will launch an instance of your browser and use it.
:param hide_canvas: Add random noise to canvas operations to prevent fingerprinting.
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page.
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before returning.
:param css_selector: CSS selector to extract specific content.
:param wait_selector: Wait for a specific CSS selector to be in a specific state.
:param proxy: The proxy to be used with requests.
:param extra_headers: Extra headers to add to the request.
"""
# Parse parameters
parsed_headers, _ = _ParseHeaders(extra_headers, False)
# Build request arguments
kwargs = {
"headless": headless,
"disable_resources": disable_resources,
"block_webrtc": block_webrtc,
"solve_cloudflare": solve_cloudflare,
"allow_webgl": allow_webgl,
"network_idle": network_idle,
"real_chrome": real_chrome,
"hide_canvas": hide_canvas,
"timeout": timeout,
}
if wait > 0:
kwargs["wait"] = wait
if wait_selector:
kwargs["wait_selector"] = wait_selector
if proxy:
kwargs["proxy"] = proxy
if parsed_headers:
kwargs["extra_headers"] = parsed_headers
from scrapling.fetchers import StealthyFetcher
__Request_and_Save(StealthyFetcher.fetch, url, output_file, css_selector, **kwargs)
@group()
def main():
pass
# Adding commands
main.add_command(install)
main.add_command(shell)
main.add_command(extract)
main.add_command(mcp)
|