AI Web Scraper - Powered by Crawl4AI avatar

AI Web Scraper - Powered by Crawl4AI

Try for free

Pay $25.00 for 1,000 Results

Go to Store
AI Web Scraper - Powered by Crawl4AI

AI Web Scraper - Powered by Crawl4AI

raizen/ai-web-scraper
Try for free

Pay $25.00 for 1,000 Results

A blazing-fast AI web scraper powered by Crawl4AI. Perfect for LLMs, AI agents, AI automation, model training, sentiment analysis, and content generation. Supports deep crawling, multiple extraction strategies and flexible output (Markdown/JSON). Seamlessly integrates with Make.com, n8n, and Zapier.

Developer
Maintained by Community

Actor Metrics

  • 3 monthly users

  • No reviews yet

  • No bookmarks yet

  • Created in Mar 2025

  • Modified 7 hours ago

You can access the AI Web Scraper - Powered by Crawl4AI programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.

1echo '{
2  "browserConfig": {
3    "browser_type": "chromium",
4    "headless": true,
5    "verbose_logging": false,
6    "ignore_https_errors": true,
7    "user_agent": "random",
8    "proxy": "",
9    "viewport_width": 1280,
10    "viewport_height": 720,
11    "accept_downloads": false,
12    "extra_headers": {}
13  },
14  "crawlerConfig": {
15    "cache_mode": "BYPASS",
16    "page_timeout": 20000,
17    "simulate_user": true,
18    "remove_overlay_elements": true,
19    "delay_before_return_html": 1,
20    "wait_for": "1",
21    "screenshot": false,
22    "pdf": false,
23    "enable_rate_limiting": false,
24    "semaphore_count": 10,
25    "memory_threshold_percent": 70,
26    "word_count_threshold": 200,
27    "css_selector": "",
28    "excluded_tags": [],
29    "excluded_selector": "",
30    "only_text": false,
31    "prettify": false,
32    "keep_data_attributes": false,
33    "remove_forms": false,
34    "bypass_cache": false,
35    "disable_cache": false,
36    "no_cache_read": false,
37    "no_cache_write": false,
38    "wait_until": "domcontentloaded",
39    "wait_for_images": false,
40    "check_robots_txt": false,
41    "mean_delay": 0.1,
42    "max_range": 0.3,
43    "js_code": "",
44    "js_only": false,
45    "ignore_body_visibility": true,
46    "scan_full_page": false,
47    "scroll_delay": 0.2,
48    "process_iframes": false,
49    "override_navigator": false,
50    "magic": false,
51    "adjust_viewport_to_content": false,
52    "screenshot_wait_for": 0,
53    "screenshot_height_threshold": 20000,
54    "image_description_min_word_threshold": 50,
55    "image_score_threshold": 3,
56    "exclude_external_images": false,
57    "exclude_social_media_domains": [],
58    "exclude_external_links": false,
59    "exclude_social_media_links": false,
60    "exclude_domains": [],
61    "verbose": true,
62    "log_console": false,
63    "stream": false
64  },
65  "deepCrawlConfig": {
66    "max_pages": 100,
67    "max_depth": 3,
68    "include_external": false,
69    "score_threshold": 0.5,
70    "filter_chain": [],
71    "url_scorer": {}
72  },
73  "markdownConfig": {
74    "ignore_links": false,
75    "ignore_images": false,
76    "escape_html": true,
77    "skip_internal_links": false,
78    "include_sup_sub": false,
79    "citations": false,
80    "body_width": 80,
81    "fit_markdown": false
82  },
83  "contentFilterConfig": {
84    "type": "pruning",
85    "user_query": "",
86    "threshold": 0.45,
87    "min_word_threshold": 5,
88    "bm25_threshold": 1.2,
89    "apply_llm_filter": false,
90    "semantic_filter": "",
91    "word_count_threshold": 10,
92    "sim_threshold": 0.3,
93    "max_dist": 0.2,
94    "top_k": 3,
95    "linkage_method": "ward"
96  },
97  "userAgentConfig": {
98    "user_agent_mode": "random",
99    "device_type": "desktop",
100    "browser_type": "chrome",
101    "num_browsers": 3
102  },
103  "llmConfig": {
104    "provider": "groq/deepseek-r1-distill-llama-70b",
105    "api_token": "",
106    "instruction": "Summarize content in clean markdown.",
107    "base_url": "",
108    "chunk_token_threshold": 2048,
109    "apply_chunking": true,
110    "input_format": "markdown",
111    "temperature": 0.7,
112    "max_tokens": 4096
113  },
114  "extractionSchema": {
115    "name": "Custom Extraction",
116    "baseSelector": "div.article",
117    "fields": [
118      {
119        "name": "title",
120        "selector": "h1",
121        "type": "text"
122      },
123      {
124        "name": "link",
125        "selector": "a",
126        "type": "attribute",
127        "attribute": "href"
128      }
129    ]
130  }
131}' |
132apify call raizen/ai-web-scraper --silent --output-dataset

AI Web Scraper - Crawl4AI for LLMs, AI Agents & Automation API through CLI

The Apify CLI is the official tool that allows you to use AI Web Scraper - Powered by Crawl4AI locally, providing convenience functions and automatic retries on errors.

Install the Apify CLI

1npm i -g apify-cli
2apify login

Other API clients include: