File size: 32,565 Bytes
03c0888 |
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 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "6yLvrXn7yZQI"
},
"source": [
"# Crawl4AI: Advanced Web Crawling and Data Extraction\n",
"\n",
"Welcome to this interactive notebook showcasing Crawl4AI, an advanced asynchronous web crawling and data extraction library.\n",
"\n",
"- GitHub Repository: [https://github.com/unclecode/crawl4ai](https://github.com/unclecode/crawl4ai)\n",
"- Twitter: [@unclecode](https://twitter.com/unclecode)\n",
"- Website: [https://crawl4ai.com](https://crawl4ai.com)\n",
"\n",
"Let's explore the powerful features of Crawl4AI!"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "KIn_9nxFyZQK"
},
"source": [
"## Installation\n",
"\n",
"First, let's install Crawl4AI from GitHub:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "mSnaxLf3zMog"
},
"outputs": [],
"source": [
"!sudo apt-get update && sudo apt-get install -y libwoff1 libopus0 libwebp6 libwebpdemux2 libenchant1c2a libgudev-1.0-0 libsecret-1-0 libhyphen0 libgdk-pixbuf2.0-0 libegl1 libnotify4 libxslt1.1 libevent-2.1-7 libgles2 libvpx6 libxcomposite1 libatk1.0-0 libatk-bridge2.0-0 libepoxy0 libgtk-3-0 libharfbuzz-icu0"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "xlXqaRtayZQK"
},
"outputs": [],
"source": [
"!pip install crawl4ai\n",
"!pip install nest-asyncio\n",
"!playwright install"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "qKCE7TI7yZQL"
},
"source": [
"Now, let's import the necessary libraries:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "I67tr7aAyZQL"
},
"outputs": [],
"source": [
"import asyncio\n",
"import nest_asyncio\n",
"from crawl4ai import AsyncWebCrawler\n",
"from crawl4ai.extraction_strategy import JsonCssExtractionStrategy, LLMExtractionStrategy\n",
"import json\n",
"import time\n",
"from pydantic import BaseModel, Field\n",
"\n",
"nest_asyncio.apply()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "h7yR_Rt_yZQM"
},
"source": [
"## Basic Usage\n",
"\n",
"Let's start with a simple crawl example:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "yBh6hf4WyZQM",
"outputId": "0f83af5c-abba-4175-ed95-70b7512e6bcc"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[LOG] 🌤️ Warming up the AsyncWebCrawler\n",
"[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
"[LOG] 🚀 Content extracted for https://www.nbcnews.com/business, success: True, time taken: 0.05 seconds\n",
"[LOG] 🚀 Extraction done for https://www.nbcnews.com/business, time taken: 0.05 seconds.\n",
"18102\n"
]
}
],
"source": [
"async def simple_crawl():\n",
" async with AsyncWebCrawler(verbose=True) as crawler:\n",
" result = await crawler.arun(url=\"https://www.nbcnews.com/business\")\n",
" print(len(result.markdown))\n",
"await simple_crawl()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "9rtkgHI28uI4"
},
"source": [
"💡 By default, **Crawl4AI** caches the result of every URL, so the next time you call it, you’ll get an instant result. But if you want to bypass the cache, just set `bypass_cache=True`."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "MzZ0zlJ9yZQM"
},
"source": [
"## Advanced Features\n",
"\n",
"### Executing JavaScript and Using CSS Selectors"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "gHStF86xyZQM",
"outputId": "34d0fb6d-4dec-4677-f76e-85a1f082829b"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[LOG] 🌤️ Warming up the AsyncWebCrawler\n",
"[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
"[LOG] 🕸️ Crawling https://www.nbcnews.com/business using AsyncPlaywrightCrawlerStrategy...\n",
"[LOG] ✅ Crawled https://www.nbcnews.com/business successfully!\n",
"[LOG] 🚀 Crawling done for https://www.nbcnews.com/business, success: True, time taken: 6.06 seconds\n",
"[LOG] 🚀 Content extracted for https://www.nbcnews.com/business, success: True, time taken: 0.10 seconds\n",
"[LOG] 🔥 Extracting semantic blocks for https://www.nbcnews.com/business, Strategy: AsyncWebCrawler\n",
"[LOG] 🚀 Extraction done for https://www.nbcnews.com/business, time taken: 0.11 seconds.\n",
"41135\n"
]
}
],
"source": [
"async def js_and_css():\n",
" async with AsyncWebCrawler(verbose=True) as crawler:\n",
" js_code = [\"const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();\"]\n",
" result = await crawler.arun(\n",
" url=\"https://www.nbcnews.com/business\",\n",
" js_code=js_code,\n",
" # css_selector=\"YOUR_CSS_SELECTOR_HERE\",\n",
" bypass_cache=True\n",
" )\n",
" print(len(result.markdown))\n",
"\n",
"await js_and_css()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "cqE_W4coyZQM"
},
"source": [
"### Using a Proxy\n",
"\n",
"Note: You'll need to replace the proxy URL with a working proxy for this example to run successfully."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "QjAyiAGqyZQM"
},
"outputs": [],
"source": [
"async def use_proxy():\n",
" async with AsyncWebCrawler(verbose=True, proxy=\"http://your-proxy-url:port\") as crawler:\n",
" result = await crawler.arun(\n",
" url=\"https://www.nbcnews.com/business\",\n",
" bypass_cache=True\n",
" )\n",
" print(result.markdown[:500]) # Print first 500 characters\n",
"\n",
"# Uncomment the following line to run the proxy example\n",
"# await use_proxy()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "XTZ88lbayZQN"
},
"source": [
"### Extracting Structured Data with OpenAI\n",
"\n",
"Note: You'll need to set your OpenAI API key as an environment variable for this example to work."
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "fIOlDayYyZQN",
"outputId": "cb8359cc-dee0-4762-9698-5dfdcee055b8"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[LOG] 🌤️ Warming up the AsyncWebCrawler\n",
"[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
"[LOG] 🕸️ Crawling https://openai.com/api/pricing/ using AsyncPlaywrightCrawlerStrategy...\n",
"[LOG] ✅ Crawled https://openai.com/api/pricing/ successfully!\n",
"[LOG] 🚀 Crawling done for https://openai.com/api/pricing/, success: True, time taken: 3.77 seconds\n",
"[LOG] 🚀 Content extracted for https://openai.com/api/pricing/, success: True, time taken: 0.21 seconds\n",
"[LOG] 🔥 Extracting semantic blocks for https://openai.com/api/pricing/, Strategy: AsyncWebCrawler\n",
"[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 0\n",
"[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 1\n",
"[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 2\n",
"[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 3\n",
"[LOG] Extracted 4 blocks from URL: https://openai.com/api/pricing/ block index: 3\n",
"[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 4\n",
"[LOG] Extracted 5 blocks from URL: https://openai.com/api/pricing/ block index: 0\n",
"[LOG] Extracted 1 blocks from URL: https://openai.com/api/pricing/ block index: 4\n",
"[LOG] Extracted 8 blocks from URL: https://openai.com/api/pricing/ block index: 1\n",
"[LOG] Extracted 12 blocks from URL: https://openai.com/api/pricing/ block index: 2\n",
"[LOG] 🚀 Extraction done for https://openai.com/api/pricing/, time taken: 8.55 seconds.\n",
"5029\n"
]
}
],
"source": [
"import os\n",
"from google.colab import userdata\n",
"os.environ['OPENAI_API_KEY'] = userdata.get('OPENAI_API_KEY')\n",
"\n",
"class OpenAIModelFee(BaseModel):\n",
" model_name: str = Field(..., description=\"Name of the OpenAI model.\")\n",
" input_fee: str = Field(..., description=\"Fee for input token for the OpenAI model.\")\n",
" output_fee: str = Field(..., description=\"Fee for output token for the OpenAI model.\")\n",
"\n",
"async def extract_openai_fees():\n",
" async with AsyncWebCrawler(verbose=True) as crawler:\n",
" result = await crawler.arun(\n",
" url='https://openai.com/api/pricing/',\n",
" word_count_threshold=1,\n",
" extraction_strategy=LLMExtractionStrategy(\n",
" provider=\"openai/gpt-4o\", api_token=os.getenv('OPENAI_API_KEY'),\n",
" schema=OpenAIModelFee.schema(),\n",
" extraction_type=\"schema\",\n",
" instruction=\"\"\"From the crawled content, extract all mentioned model names along with their fees for input and output tokens.\n",
" Do not miss any models in the entire content. One extracted model JSON format should look like this:\n",
" {\"model_name\": \"GPT-4\", \"input_fee\": \"US$10.00 / 1M tokens\", \"output_fee\": \"US$30.00 / 1M tokens\"}.\"\"\"\n",
" ),\n",
" bypass_cache=True,\n",
" )\n",
" print(len(result.extracted_content))\n",
"\n",
"# Uncomment the following line to run the OpenAI extraction example\n",
"await extract_openai_fees()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "BypA5YxEyZQN"
},
"source": [
"### Advanced Multi-Page Crawling with JavaScript Execution"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "tfkcVQ0b7mw-"
},
"source": [
"## Advanced Multi-Page Crawling with JavaScript Execution\n",
"\n",
"This example demonstrates Crawl4AI's ability to handle complex crawling scenarios, specifically extracting commits from multiple pages of a GitHub repository. The challenge here is that clicking the \"Next\" button doesn't load a new page, but instead uses asynchronous JavaScript to update the content. This is a common hurdle in modern web crawling.\n",
"\n",
"To overcome this, we use Crawl4AI's custom JavaScript execution to simulate clicking the \"Next\" button, and implement a custom hook to detect when new data has loaded. Our strategy involves comparing the first commit's text before and after \"clicking\" Next, waiting until it changes to confirm new data has rendered. This showcases Crawl4AI's flexibility in handling dynamic content and its ability to implement custom logic for even the most challenging crawling tasks."
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "qUBKGpn3yZQN",
"outputId": "3e555b6a-ed33-42f4-cce9-499a923fbe17"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[LOG] 🌤️ Warming up the AsyncWebCrawler\n",
"[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
"[LOG] 🕸️ Crawling https://github.com/microsoft/TypeScript/commits/main using AsyncPlaywrightCrawlerStrategy...\n",
"[LOG] ✅ Crawled https://github.com/microsoft/TypeScript/commits/main successfully!\n",
"[LOG] 🚀 Crawling done for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 5.16 seconds\n",
"[LOG] 🚀 Content extracted for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.28 seconds\n",
"[LOG] 🔥 Extracting semantic blocks for https://github.com/microsoft/TypeScript/commits/main, Strategy: AsyncWebCrawler\n",
"[LOG] 🚀 Extraction done for https://github.com/microsoft/TypeScript/commits/main, time taken: 0.28 seconds.\n",
"Page 1: Found 35 commits\n",
"[LOG] 🕸️ Crawling https://github.com/microsoft/TypeScript/commits/main using AsyncPlaywrightCrawlerStrategy...\n",
"[LOG] ✅ Crawled https://github.com/microsoft/TypeScript/commits/main successfully!\n",
"[LOG] 🚀 Crawling done for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.78 seconds\n",
"[LOG] 🚀 Content extracted for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.90 seconds\n",
"[LOG] 🔥 Extracting semantic blocks for https://github.com/microsoft/TypeScript/commits/main, Strategy: AsyncWebCrawler\n",
"[LOG] 🚀 Extraction done for https://github.com/microsoft/TypeScript/commits/main, time taken: 0.90 seconds.\n",
"Page 2: Found 35 commits\n",
"[LOG] 🕸️ Crawling https://github.com/microsoft/TypeScript/commits/main using AsyncPlaywrightCrawlerStrategy...\n",
"[LOG] ✅ Crawled https://github.com/microsoft/TypeScript/commits/main successfully!\n",
"[LOG] 🚀 Crawling done for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 2.00 seconds\n",
"[LOG] 🚀 Content extracted for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.74 seconds\n",
"[LOG] 🔥 Extracting semantic blocks for https://github.com/microsoft/TypeScript/commits/main, Strategy: AsyncWebCrawler\n",
"[LOG] 🚀 Extraction done for https://github.com/microsoft/TypeScript/commits/main, time taken: 0.75 seconds.\n",
"Page 3: Found 35 commits\n",
"Successfully crawled 105 commits across 3 pages\n"
]
}
],
"source": [
"import re\n",
"from bs4 import BeautifulSoup\n",
"\n",
"async def crawl_typescript_commits():\n",
" first_commit = \"\"\n",
" async def on_execution_started(page):\n",
" nonlocal first_commit\n",
" try:\n",
" while True:\n",
" await page.wait_for_selector('li.Box-sc-g0xbh4-0 h4')\n",
" commit = await page.query_selector('li.Box-sc-g0xbh4-0 h4')\n",
" commit = await commit.evaluate('(element) => element.textContent')\n",
" commit = re.sub(r'\\s+', '', commit)\n",
" if commit and commit != first_commit:\n",
" first_commit = commit\n",
" break\n",
" await asyncio.sleep(0.5)\n",
" except Exception as e:\n",
" print(f\"Warning: New content didn't appear after JavaScript execution: {e}\")\n",
"\n",
" async with AsyncWebCrawler(verbose=True) as crawler:\n",
" crawler.crawler_strategy.set_hook('on_execution_started', on_execution_started)\n",
"\n",
" url = \"https://github.com/microsoft/TypeScript/commits/main\"\n",
" session_id = \"typescript_commits_session\"\n",
" all_commits = []\n",
"\n",
" js_next_page = \"\"\"\n",
" const button = document.querySelector('a[data-testid=\"pagination-next-button\"]');\n",
" if (button) button.click();\n",
" \"\"\"\n",
"\n",
" for page in range(3): # Crawl 3 pages\n",
" result = await crawler.arun(\n",
" url=url,\n",
" session_id=session_id,\n",
" css_selector=\"li.Box-sc-g0xbh4-0\",\n",
" js=js_next_page if page > 0 else None,\n",
" bypass_cache=True,\n",
" js_only=page > 0\n",
" )\n",
"\n",
" assert result.success, f\"Failed to crawl page {page + 1}\"\n",
"\n",
" soup = BeautifulSoup(result.cleaned_html, 'html.parser')\n",
" commits = soup.select(\"li\")\n",
" all_commits.extend(commits)\n",
"\n",
" print(f\"Page {page + 1}: Found {len(commits)} commits\")\n",
"\n",
" await crawler.crawler_strategy.kill_session(session_id)\n",
" print(f\"Successfully crawled {len(all_commits)} commits across 3 pages\")\n",
"\n",
"await crawl_typescript_commits()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "EJRnYsp6yZQN"
},
"source": [
"### Using JsonCssExtractionStrategy for Fast Structured Output"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "1ZMqIzB_8SYp"
},
"source": [
"The JsonCssExtractionStrategy is a powerful feature of Crawl4AI that allows for precise, structured data extraction from web pages. Here's how it works:\n",
"\n",
"1. You define a schema that describes the pattern of data you're interested in extracting.\n",
"2. The schema includes a base selector that identifies repeating elements on the page.\n",
"3. Within the schema, you define fields, each with its own selector and type.\n",
"4. These field selectors are applied within the context of each base selector element.\n",
"5. The strategy supports nested structures, lists within lists, and various data types.\n",
"6. You can even include computed fields for more complex data manipulation.\n",
"\n",
"This approach allows for highly flexible and precise data extraction, transforming semi-structured web content into clean, structured JSON data. It's particularly useful for extracting consistent data patterns from pages like product listings, news articles, or search results.\n",
"\n",
"For more details and advanced usage, check out the full documentation on the Crawl4AI website."
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "trCMR2T9yZQN",
"outputId": "718d36f4-cccf-40f4-8d8c-c3ba73524d16"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[LOG] 🌤️ Warming up the AsyncWebCrawler\n",
"[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
"[LOG] 🕸️ Crawling https://www.nbcnews.com/business using AsyncPlaywrightCrawlerStrategy...\n",
"[LOG] ✅ Crawled https://www.nbcnews.com/business successfully!\n",
"[LOG] 🚀 Crawling done for https://www.nbcnews.com/business, success: True, time taken: 7.00 seconds\n",
"[LOG] 🚀 Content extracted for https://www.nbcnews.com/business, success: True, time taken: 0.32 seconds\n",
"[LOG] 🔥 Extracting semantic blocks for https://www.nbcnews.com/business, Strategy: AsyncWebCrawler\n",
"[LOG] 🚀 Extraction done for https://www.nbcnews.com/business, time taken: 0.48 seconds.\n",
"Successfully extracted 11 news teasers\n",
"{\n",
" \"category\": \"Business News\",\n",
" \"headline\": \"NBC ripped up its Olympics playbook for 2024 \\u2014 so far, the new strategy paid off\",\n",
" \"summary\": \"The Olympics have long been key to NBCUniversal. Paris marked the 18th Olympic Games broadcast by NBC in the U.S.\",\n",
" \"time\": \"13h ago\",\n",
" \"image\": {\n",
" \"src\": \"https://media-cldnry.s-nbcnews.com/image/upload/t_focal-200x100,f_auto,q_auto:best/rockcms/2024-09/240903-nbc-olympics-ch-1344-c7a486.jpg\",\n",
" \"alt\": \"Mike Tirico.\"\n",
" },\n",
" \"link\": \"https://www.nbcnews.com/business\"\n",
"}\n"
]
}
],
"source": [
"async def extract_news_teasers():\n",
" schema = {\n",
" \"name\": \"News Teaser Extractor\",\n",
" \"baseSelector\": \".wide-tease-item__wrapper\",\n",
" \"fields\": [\n",
" {\n",
" \"name\": \"category\",\n",
" \"selector\": \".unibrow span[data-testid='unibrow-text']\",\n",
" \"type\": \"text\",\n",
" },\n",
" {\n",
" \"name\": \"headline\",\n",
" \"selector\": \".wide-tease-item__headline\",\n",
" \"type\": \"text\",\n",
" },\n",
" {\n",
" \"name\": \"summary\",\n",
" \"selector\": \".wide-tease-item__description\",\n",
" \"type\": \"text\",\n",
" },\n",
" {\n",
" \"name\": \"time\",\n",
" \"selector\": \"[data-testid='wide-tease-date']\",\n",
" \"type\": \"text\",\n",
" },\n",
" {\n",
" \"name\": \"image\",\n",
" \"type\": \"nested\",\n",
" \"selector\": \"picture.teasePicture img\",\n",
" \"fields\": [\n",
" {\"name\": \"src\", \"type\": \"attribute\", \"attribute\": \"src\"},\n",
" {\"name\": \"alt\", \"type\": \"attribute\", \"attribute\": \"alt\"},\n",
" ],\n",
" },\n",
" {\n",
" \"name\": \"link\",\n",
" \"selector\": \"a[href]\",\n",
" \"type\": \"attribute\",\n",
" \"attribute\": \"href\",\n",
" },\n",
" ],\n",
" }\n",
"\n",
" extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)\n",
"\n",
" async with AsyncWebCrawler(verbose=True) as crawler:\n",
" result = await crawler.arun(\n",
" url=\"https://www.nbcnews.com/business\",\n",
" extraction_strategy=extraction_strategy,\n",
" bypass_cache=True,\n",
" )\n",
"\n",
" assert result.success, \"Failed to crawl the page\"\n",
"\n",
" news_teasers = json.loads(result.extracted_content)\n",
" print(f\"Successfully extracted {len(news_teasers)} news teasers\")\n",
" print(json.dumps(news_teasers[0], indent=2))\n",
"\n",
"await extract_news_teasers()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "FnyVhJaByZQN"
},
"source": [
"## Speed Comparison\n",
"\n",
"Let's compare the speed of Crawl4AI with Firecrawl, a paid service. Note that we can't run Firecrawl in this Colab environment, so we'll simulate its performance based on previously recorded data."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "agDD186f3wig"
},
"source": [
"💡 **Note on Speed Comparison:**\n",
"\n",
"The speed test conducted here is running on Google Colab, where the internet speed and performance can vary and may not reflect optimal conditions. When we call Firecrawl's API, we're seeing its best performance, while Crawl4AI's performance is limited by Colab's network speed.\n",
"\n",
"For a more accurate comparison, it's recommended to run these tests on your own servers or computers with a stable and fast internet connection. Despite these limitations, Crawl4AI still demonstrates faster performance in this environment.\n",
"\n",
"If you run these tests locally, you may observe an even more significant speed advantage for Crawl4AI compared to other services."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "F7KwHv8G1LbY"
},
"outputs": [],
"source": [
"!pip install firecrawl"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "91813zILyZQN",
"outputId": "663223db-ab89-4976-b233-05ceca62b19b"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Firecrawl (simulated):\n",
"Time taken: 4.38 seconds\n",
"Content length: 41967 characters\n",
"Images found: 49\n",
"\n",
"Crawl4AI (simple crawl):\n",
"Time taken: 4.22 seconds\n",
"Content length: 18221 characters\n",
"Images found: 49\n",
"\n",
"Crawl4AI (with JavaScript execution):\n",
"Time taken: 9.13 seconds\n",
"Content length: 34243 characters\n",
"Images found: 89\n"
]
}
],
"source": [
"import os\n",
"from google.colab import userdata\n",
"os.environ['FIRECRAWL_API_KEY'] = userdata.get('FIRECRAWL_API_KEY')\n",
"import time\n",
"from firecrawl import FirecrawlApp\n",
"\n",
"async def speed_comparison():\n",
" # Simulated Firecrawl performance\n",
" app = FirecrawlApp(api_key=os.environ['FIRECRAWL_API_KEY'])\n",
" start = time.time()\n",
" scrape_status = app.scrape_url(\n",
" 'https://www.nbcnews.com/business',\n",
" params={'formats': ['markdown', 'html']}\n",
" )\n",
" end = time.time()\n",
" print(\"Firecrawl (simulated):\")\n",
" print(f\"Time taken: {end - start:.2f} seconds\")\n",
" print(f\"Content length: {len(scrape_status['markdown'])} characters\")\n",
" print(f\"Images found: {scrape_status['markdown'].count('cldnry.s-nbcnews.com')}\")\n",
" print()\n",
"\n",
" async with AsyncWebCrawler() as crawler:\n",
" # Crawl4AI simple crawl\n",
" start = time.time()\n",
" result = await crawler.arun(\n",
" url=\"https://www.nbcnews.com/business\",\n",
" word_count_threshold=0,\n",
" bypass_cache=True,\n",
" verbose=False\n",
" )\n",
" end = time.time()\n",
" print(\"Crawl4AI (simple crawl):\")\n",
" print(f\"Time taken: {end - start:.2f} seconds\")\n",
" print(f\"Content length: {len(result.markdown)} characters\")\n",
" print(f\"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}\")\n",
" print()\n",
"\n",
" # Crawl4AI with JavaScript execution\n",
" start = time.time()\n",
" result = await crawler.arun(\n",
" url=\"https://www.nbcnews.com/business\",\n",
" js_code=[\"const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();\"],\n",
" word_count_threshold=0,\n",
" bypass_cache=True,\n",
" verbose=False\n",
" )\n",
" end = time.time()\n",
" print(\"Crawl4AI (with JavaScript execution):\")\n",
" print(f\"Time taken: {end - start:.2f} seconds\")\n",
" print(f\"Content length: {len(result.markdown)} characters\")\n",
" print(f\"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}\")\n",
"\n",
"await speed_comparison()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "OBFFYVJIyZQN"
},
"source": [
"If you run on a local machine with a proper internet speed:\n",
"- Simple crawl: Crawl4AI is typically over 3-4 times faster than Firecrawl.\n",
"- With JavaScript execution: Even when executing JavaScript to load more content (potentially doubling the number of images found), Crawl4AI is still faster than Firecrawl's simple crawl.\n",
"\n",
"Please note that actual performance may vary depending on network conditions and the specific content being crawled."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "A6_1RK1_yZQO"
},
"source": [
"## Conclusion\n",
"\n",
"In this notebook, we've explored the powerful features of Crawl4AI, including:\n",
"\n",
"1. Basic crawling\n",
"2. JavaScript execution and CSS selector usage\n",
"3. Proxy support\n",
"4. Structured data extraction with OpenAI\n",
"5. Advanced multi-page crawling with JavaScript execution\n",
"6. Fast structured output using JsonCssExtractionStrategy\n",
"7. Speed comparison with other services\n",
"\n",
"Crawl4AI offers a fast, flexible, and powerful solution for web crawling and data extraction tasks. Its asynchronous architecture and advanced features make it suitable for a wide range of applications, from simple web scraping to complex, multi-page data extraction scenarios.\n",
"\n",
"For more information and advanced usage, please visit the [Crawl4AI documentation](https://crawl4ai.com/mkdocs/).\n",
"\n",
"Happy crawling!"
]
}
],
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"display_name": "venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.13"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|