
AI Web Scraper - Powered by Crawl4AI
Pricing
$25.00 / 1,000 results

AI Web Scraper - Powered by Crawl4AI
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.
0.0 (0)
Pricing
$25.00 / 1,000 results
2
Monthly users
32
Runs succeeded
98%
Last modified
a month 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 "startUrls": [
3 {
4 "url": "https://www.cnbc.com/2025/03/12/googles-deepmind-says-it-will-use-ai-models-to-power-physical-robots.html"
5 }
6 ],
7 "browserConfig": {
8 "browser_type": "chromium",
9 "headless": true,
10 "verbose_logging": false,
11 "ignore_https_errors": true,
12 "user_agent": "random",
13 "proxy": "",
14 "viewport_width": 1280,
15 "viewport_height": 720,
16 "accept_downloads": false,
17 "extra_headers": {}
18 },
19 "crawlerConfig": {
20 "cache_mode": "BYPASS",
21 "page_timeout": 20000,
22 "simulate_user": true,
23 "override_navigator": true,
24 "magic": true,
25 "remove_overlay_elements": true,
26 "delay_before_return_html": 0.75,
27 "wait_for": "",
28 "screenshot": false,
29 "pdf": false,
30 "enable_rate_limiting": false,
31 "memory_threshold_percent": 90,
32 "word_count_threshold": 200,
33 "css_selector": "",
34 "excluded_tags": [],
35 "excluded_selector": "",
36 "only_text": false,
37 "prettify": false,
38 "keep_data_attributes": false,
39 "remove_forms": false,
40 "bypass_cache": false,
41 "disable_cache": false,
42 "no_cache_read": false,
43 "no_cache_write": false,
44 "wait_until": "domcontentloaded",
45 "wait_for_images": false,
46 "check_robots_txt": false,
47 "mean_delay": 0.1,
48 "max_range": 0.3,
49 "js_code": "",
50 "js_only": false,
51 "ignore_body_visibility": true,
52 "scan_full_page": false,
53 "scroll_delay": 0.2,
54 "process_iframes": false,
55 "adjust_viewport_to_content": false,
56 "screenshot_wait_for": 0,
57 "screenshot_height_threshold": 20000,
58 "image_description_min_word_threshold": 50,
59 "image_score_threshold": 3,
60 "exclude_external_images": false,
61 "exclude_social_media_domains": [],
62 "exclude_external_links": false,
63 "exclude_social_media_links": false,
64 "exclude_domains": [],
65 "verbose": true,
66 "log_console": false,
67 "stream": false
68 },
69 "deepCrawlConfig": {
70 "max_pages": 100,
71 "max_depth": 3,
72 "include_external": false,
73 "score_threshold": 0.5,
74 "filter_chain": [],
75 "keywords": [
76 "crawl",
77 "example",
78 "async",
79 "configuration"
80 ],
81 "weight": 0.7
82 },
83 "markdownConfig": {
84 "ignore_links": false,
85 "ignore_images": false,
86 "escape_html": true,
87 "skip_internal_links": false,
88 "include_sup_sub": false,
89 "citations": false,
90 "body_width": 80,
91 "fit_markdown": false
92 },
93 "contentFilterConfig": {
94 "type": "pruning",
95 "user_query": "",
96 "threshold": 0.45,
97 "min_word_threshold": 5,
98 "bm25_threshold": 1.2,
99 "apply_llm_filter": false,
100 "semantic_filter": "",
101 "word_count_threshold": 10,
102 "sim_threshold": 0.3,
103 "max_dist": 0.2,
104 "top_k": 3,
105 "linkage_method": "ward"
106 },
107 "userAgentConfig": {
108 "user_agent_mode": "random",
109 "device_type": "desktop",
110 "browser_type": "chrome",
111 "num_browsers": 1
112 },
113 "llmConfig": {
114 "provider": "groq/deepseek-r1-distill-llama-70b",
115 "api_token": "",
116 "instruction": "Summarize content in clean markdown.",
117 "base_url": "",
118 "chunk_token_threshold": 2048,
119 "apply_chunking": true,
120 "input_format": "markdown",
121 "temperature": 0.7,
122 "max_tokens": 4096
123 },
124 "extractionSchema": {
125 "name": "Custom Extraction",
126 "baseSelector": "div.article",
127 "fields": [
128 {
129 "name": "title",
130 "selector": "h1",
131 "type": "text"
132 },
133 {
134 "name": "link",
135 "selector": "a",
136 "type": "attribute",
137 "attribute": "href"
138 }
139 ]
140 }
141}' |
142apify 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:
Pricing
Pricing model
Pay per resultThis Actor is paid per result. You are not charged for the Apify platform usage, but only a fixed price for each dataset of 1,000 items in the Actor outputs.
Price per 1,000 items
$25.00