webscraping-ai

Web Scraping API

Server path: /webscraping-ai | Type: Application | PCID required: Yes

Tools

Tool	Description
webscraping_ai_account	Information about your account calls quota
webscraping_ai_get_fields	Extract structured data fields from a web page
webscraping_ai_get_html	Page HTML by URL
webscraping_ai_get_question	Get an answer to a question about a given web page
webscraping_ai_get_selected	HTML of a selected page area by URL and CSS selector
webscraping_ai_get_selected_multiple	HTML of multiple page areas by URL and CSS selectors
webscraping_ai_get_text	Page text by URL

---

webscraping_ai_account

Information about your account calls quota

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    }
  },
  "required": [
    "PCID"
  ]
}

---

webscraping_ai_get_fields

Extract structured data fields from a web page

Parameters:

Parameter	Type	Required	Default	Description
url	string	Yes	—	URL of the target page.
fields	object	Yes	—	Object describing fields to extract from the page and their descriptions
headers	object	No	—	HTTP headers to pass to the target page. Can be specified either via a nested query parameter (…&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (…&headers={“One”: “value1”, “Another”: “value2”}).
timeout	integer	No	—	Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000).
js	boolean	No	—	Execute on-page JavaScript using a headless browser (true by default).
js_timeout	integer	No	—	Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page.
wait_for	string	No	—	CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout.
proxy	string	No	—	Type of proxy. Use residential if your site restricts traffic from datacenters, or stealth for the most heavily protected sites with advanced anti-bot detection (datacenter by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details.
country	string	No	—	Country of the proxy to use (US by default).
custom_proxy	string	No	—	Your own proxy URL to use instead of our built-in proxy pool in “http://user:password@host:port” format (<a target=“_blank” href=“https://webscraping.ai/proxies/smartproxy”&gt;Smartproxy&lt;/a> for example).
device	string	No	—	Type of device emulation.
error_on_404	boolean	No	—	Return error on 404 HTTP status on the target page (false by default).
error_on_redirect	boolean	No	—	Return error on redirect on the target page (false by default).
js_script	string	No	—	Custom JavaScript code to execute on the target page.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "url": {
      "type": "string",
      "description": "URL of the target page."
    },
    "fields": {
      "type": "object",
      "description": "Object describing fields to extract from the page and their descriptions"
    },
    "headers": {
      "type": "object",
      "description": "HTTP headers to pass to the target page. Can be specified either via a nested query parameter (...&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (...&headers={\"One\": \"value1\", \"Another\": \"value2\"})."
    },
    "timeout": {
      "type": "integer",
      "description": "Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000)."
    },
    "js": {
      "type": "boolean",
      "description": "Execute on-page JavaScript using a headless browser (true by default)."
    },
    "js_timeout": {
      "type": "integer",
      "description": "Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page."
    },
    "wait_for": {
      "type": "string",
      "description": "CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout."
    },
    "proxy": {
      "type": "string",
      "description": "Type of proxy. Use `residential` if your site restricts traffic from datacenters, or `stealth` for the most heavily protected sites with advanced anti-bot detection (`datacenter` by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details.",
      "enum": [
        "datacenter",
        "residential",
        "stealth"
      ]
    },
    "country": {
      "type": "string",
      "description": "Country of the proxy to use (US by default).",
      "enum": [
        "us",
        "gb",
        "de",
        "it",
        "fr",
        "ca",
        "es",
        "ru",
        "jp",
        "kr",
        "in",
        "hk",
        "tr"
      ]
    },
    "custom_proxy": {
      "type": "string",
      "description": "Your own proxy URL to use instead of our built-in proxy pool in \"http://user:password@host:port\" format (<a target=\"_blank\" href=\"https://webscraping.ai/proxies/smartproxy\">Smartproxy</a> for example)."
    },
    "device": {
      "type": "string",
      "description": "Type of device emulation.",
      "enum": [
        "desktop",
        "mobile",
        "tablet"
      ]
    },
    "error_on_404": {
      "type": "boolean",
      "description": "Return error on 404 HTTP status on the target page (false by default)."
    },
    "error_on_redirect": {
      "type": "boolean",
      "description": "Return error on redirect on the target page (false by default)."
    },
    "js_script": {
      "type": "string",
      "description": "Custom JavaScript code to execute on the target page."
    }
  },
  "required": [
    "PCID",
    "url",
    "fields"
  ]
}

---

webscraping_ai_get_html

Page HTML by URL

Parameters:

Parameter	Type	Required	Default	Description
url	string	Yes	—	URL of the target page.
headers	object	No	—	HTTP headers to pass to the target page. Can be specified either via a nested query parameter (…&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (…&headers={“One”: “value1”, “Another”: “value2”}).
timeout	integer	No	—	Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000).
js	boolean	No	—	Execute on-page JavaScript using a headless browser (true by default).
js_timeout	integer	No	—	Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page.
wait_for	string	No	—	CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout.
proxy	string	No	—	Type of proxy. Use residential if your site restricts traffic from datacenters, or stealth for the most heavily protected sites with advanced anti-bot detection (datacenter by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details.
country	string	No	—	Country of the proxy to use (US by default).
custom_proxy	string	No	—	Your own proxy URL to use instead of our built-in proxy pool in “http://user:password@host:port” format (<a target=“_blank” href=“https://webscraping.ai/proxies/smartproxy”&gt;Smartproxy&lt;/a> for example).
device	string	No	—	Type of device emulation.
error_on_404	boolean	No	—	Return error on 404 HTTP status on the target page (false by default).
error_on_redirect	boolean	No	—	Return error on redirect on the target page (false by default).
js_script	string	No	—	Custom JavaScript code to execute on the target page.
return_script_result	boolean	No	—	Return result of the custom JavaScript code (js_script parameter) execution on the target page (false by default, page HTML will be returned).
format	string	No	—	Format of the response (text by default). “json” will return a JSON object with the response, “text” will return a plain text/HTML response.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "url": {
      "type": "string",
      "description": "URL of the target page."
    },
    "headers": {
      "type": "object",
      "description": "HTTP headers to pass to the target page. Can be specified either via a nested query parameter (...&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (...&headers={\"One\": \"value1\", \"Another\": \"value2\"})."
    },
    "timeout": {
      "type": "integer",
      "description": "Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000)."
    },
    "js": {
      "type": "boolean",
      "description": "Execute on-page JavaScript using a headless browser (true by default)."
    },
    "js_timeout": {
      "type": "integer",
      "description": "Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page."
    },
    "wait_for": {
      "type": "string",
      "description": "CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout."
    },
    "proxy": {
      "type": "string",
      "description": "Type of proxy. Use `residential` if your site restricts traffic from datacenters, or `stealth` for the most heavily protected sites with advanced anti-bot detection (`datacenter` by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details.",
      "enum": [
        "datacenter",
        "residential",
        "stealth"
      ]
    },
    "country": {
      "type": "string",
      "description": "Country of the proxy to use (US by default).",
      "enum": [
        "us",
        "gb",
        "de",
        "it",
        "fr",
        "ca",
        "es",
        "ru",
        "jp",
        "kr",
        "in",
        "hk",
        "tr"
      ]
    },
    "custom_proxy": {
      "type": "string",
      "description": "Your own proxy URL to use instead of our built-in proxy pool in \"http://user:password@host:port\" format (<a target=\"_blank\" href=\"https://webscraping.ai/proxies/smartproxy\">Smartproxy</a> for example)."
    },
    "device": {
      "type": "string",
      "description": "Type of device emulation.",
      "enum": [
        "desktop",
        "mobile",
        "tablet"
      ]
    },
    "error_on_404": {
      "type": "boolean",
      "description": "Return error on 404 HTTP status on the target page (false by default)."
    },
    "error_on_redirect": {
      "type": "boolean",
      "description": "Return error on redirect on the target page (false by default)."
    },
    "js_script": {
      "type": "string",
      "description": "Custom JavaScript code to execute on the target page."
    },
    "return_script_result": {
      "type": "boolean",
      "description": "Return result of the custom JavaScript code (js_script parameter) execution on the target page (false by default, page HTML will be returned)."
    },
    "format": {
      "type": "string",
      "description": "Format of the response (text by default). \"json\" will return a JSON object with the response, \"text\" will return a plain text/HTML response.",
      "enum": [
        "json",
        "text"
      ]
    }
  },
  "required": [
    "PCID",
    "url"
  ]
}

---

webscraping_ai_get_question

Get an answer to a question about a given web page

Parameters:

Parameter	Type	Required	Default	Description
url	string	Yes	—	URL of the target page.
question	string	No	—	Question or instructions to ask the LLM model about the target page.
headers	object	No	—	HTTP headers to pass to the target page. Can be specified either via a nested query parameter (…&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (…&headers={“One”: “value1”, “Another”: “value2”}).
timeout	integer	No	—	Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000).
js	boolean	No	—	Execute on-page JavaScript using a headless browser (true by default).
js_timeout	integer	No	—	Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page.
wait_for	string	No	—	CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout.
proxy	string	No	—	Type of proxy. Use residential if your site restricts traffic from datacenters, or stealth for the most heavily protected sites with advanced anti-bot detection (datacenter by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details.
country	string	No	—	Country of the proxy to use (US by default).
custom_proxy	string	No	—	Your own proxy URL to use instead of our built-in proxy pool in “http://user:password@host:port” format (<a target=“_blank” href=“https://webscraping.ai/proxies/smartproxy”&gt;Smartproxy&lt;/a> for example).
device	string	No	—	Type of device emulation.
error_on_404	boolean	No	—	Return error on 404 HTTP status on the target page (false by default).
error_on_redirect	boolean	No	—	Return error on redirect on the target page (false by default).
js_script	string	No	—	Custom JavaScript code to execute on the target page.
format	string	No	—	Format of the response (text by default). “json” will return a JSON object with the response, “text” will return a plain text/HTML response.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "url": {
      "type": "string",
      "description": "URL of the target page."
    },
    "question": {
      "type": "string",
      "description": "Question or instructions to ask the LLM model about the target page."
    },
    "headers": {
      "type": "object",
      "description": "HTTP headers to pass to the target page. Can be specified either via a nested query parameter (...&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (...&headers={\"One\": \"value1\", \"Another\": \"value2\"})."
    },
    "timeout": {
      "type": "integer",
      "description": "Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000)."
    },
    "js": {
      "type": "boolean",
      "description": "Execute on-page JavaScript using a headless browser (true by default)."
    },
    "js_timeout": {
      "type": "integer",
      "description": "Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page."
    },
    "wait_for": {
      "type": "string",
      "description": "CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout."
    },
    "proxy": {
      "type": "string",
      "description": "Type of proxy. Use `residential` if your site restricts traffic from datacenters, or `stealth` for the most heavily protected sites with advanced anti-bot detection (`datacenter` by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details.",
      "enum": [
        "datacenter",
        "residential",
        "stealth"
      ]
    },
    "country": {
      "type": "string",
      "description": "Country of the proxy to use (US by default).",
      "enum": [
        "us",
        "gb",
        "de",
        "it",
        "fr",
        "ca",
        "es",
        "ru",
        "jp",
        "kr",
        "in",
        "hk",
        "tr"
      ]
    },
    "custom_proxy": {
      "type": "string",
      "description": "Your own proxy URL to use instead of our built-in proxy pool in \"http://user:password@host:port\" format (<a target=\"_blank\" href=\"https://webscraping.ai/proxies/smartproxy\">Smartproxy</a> for example)."
    },
    "device": {
      "type": "string",
      "description": "Type of device emulation.",
      "enum": [
        "desktop",
        "mobile",
        "tablet"
      ]
    },
    "error_on_404": {
      "type": "boolean",
      "description": "Return error on 404 HTTP status on the target page (false by default)."
    },
    "error_on_redirect": {
      "type": "boolean",
      "description": "Return error on redirect on the target page (false by default)."
    },
    "js_script": {
      "type": "string",
      "description": "Custom JavaScript code to execute on the target page."
    },
    "format": {
      "type": "string",
      "description": "Format of the response (text by default). \"json\" will return a JSON object with the response, \"text\" will return a plain text/HTML response.",
      "enum": [
        "json",
        "text"
      ]
    }
  },
  "required": [
    "PCID",
    "url"
  ]
}

---

webscraping_ai_get_selected

HTML of a selected page area by URL and CSS selector

Parameters:

Parameter	Type	Required	Default	Description
selector	string	No	—	CSS selector (null by default, returns whole page HTML)
url	string	Yes	—	URL of the target page.
headers	object	No	—	HTTP headers to pass to the target page. Can be specified either via a nested query parameter (…&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (…&headers={“One”: “value1”, “Another”: “value2”}).
timeout	integer	No	—	Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000).
js	boolean	No	—	Execute on-page JavaScript using a headless browser (true by default).
js_timeout	integer	No	—	Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page.
wait_for	string	No	—	CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout.
proxy	string	No	—	Type of proxy. Use residential if your site restricts traffic from datacenters, or stealth for the most heavily protected sites with advanced anti-bot detection (datacenter by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details.
country	string	No	—	Country of the proxy to use (US by default).
custom_proxy	string	No	—	Your own proxy URL to use instead of our built-in proxy pool in “http://user:password@host:port” format (<a target=“_blank” href=“https://webscraping.ai/proxies/smartproxy”&gt;Smartproxy&lt;/a> for example).
device	string	No	—	Type of device emulation.
error_on_404	boolean	No	—	Return error on 404 HTTP status on the target page (false by default).
error_on_redirect	boolean	No	—	Return error on redirect on the target page (false by default).
js_script	string	No	—	Custom JavaScript code to execute on the target page.
format	string	No	—	Format of the response (text by default). “json” will return a JSON object with the response, “text” will return a plain text/HTML response.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "selector": {
      "type": "string",
      "description": "CSS selector (null by default, returns whole page HTML)"
    },
    "url": {
      "type": "string",
      "description": "URL of the target page."
    },
    "headers": {
      "type": "object",
      "description": "HTTP headers to pass to the target page. Can be specified either via a nested query parameter (...&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (...&headers={\"One\": \"value1\", \"Another\": \"value2\"})."
    },
    "timeout": {
      "type": "integer",
      "description": "Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000)."
    },
    "js": {
      "type": "boolean",
      "description": "Execute on-page JavaScript using a headless browser (true by default)."
    },
    "js_timeout": {
      "type": "integer",
      "description": "Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page."
    },
    "wait_for": {
      "type": "string",
      "description": "CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout."
    },
    "proxy": {
      "type": "string",
      "description": "Type of proxy. Use `residential` if your site restricts traffic from datacenters, or `stealth` for the most heavily protected sites with advanced anti-bot detection (`datacenter` by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details.",
      "enum": [
        "datacenter",
        "residential",
        "stealth"
      ]
    },
    "country": {
      "type": "string",
      "description": "Country of the proxy to use (US by default).",
      "enum": [
        "us",
        "gb",
        "de",
        "it",
        "fr",
        "ca",
        "es",
        "ru",
        "jp",
        "kr",
        "in",
        "hk",
        "tr"
      ]
    },
    "custom_proxy": {
      "type": "string",
      "description": "Your own proxy URL to use instead of our built-in proxy pool in \"http://user:password@host:port\" format (<a target=\"_blank\" href=\"https://webscraping.ai/proxies/smartproxy\">Smartproxy</a> for example)."
    },
    "device": {
      "type": "string",
      "description": "Type of device emulation.",
      "enum": [
        "desktop",
        "mobile",
        "tablet"
      ]
    },
    "error_on_404": {
      "type": "boolean",
      "description": "Return error on 404 HTTP status on the target page (false by default)."
    },
    "error_on_redirect": {
      "type": "boolean",
      "description": "Return error on redirect on the target page (false by default)."
    },
    "js_script": {
      "type": "string",
      "description": "Custom JavaScript code to execute on the target page."
    },
    "format": {
      "type": "string",
      "description": "Format of the response (text by default). \"json\" will return a JSON object with the response, \"text\" will return a plain text/HTML response.",
      "enum": [
        "json",
        "text"
      ]
    }
  },
  "required": [
    "PCID",
    "url"
  ]
}

---

webscraping_ai_get_selected_multiple

HTML of multiple page areas by URL and CSS selectors

Parameters:

Parameter	Type	Required	Default	Description
selectors	string[]	No	—	Multiple CSS selectors (null by default, returns whole page HTML)
url	string	Yes	—	URL of the target page.
headers	object	No	—	HTTP headers to pass to the target page. Can be specified either via a nested query parameter (…&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (…&headers={“One”: “value1”, “Another”: “value2”}).
timeout	integer	No	—	Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000).
js	boolean	No	—	Execute on-page JavaScript using a headless browser (true by default).
js_timeout	integer	No	—	Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page.
wait_for	string	No	—	CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout.
proxy	string	No	—	Type of proxy. Use residential if your site restricts traffic from datacenters, or stealth for the most heavily protected sites with advanced anti-bot detection (datacenter by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details.
country	string	No	—	Country of the proxy to use (US by default).
custom_proxy	string	No	—	Your own proxy URL to use instead of our built-in proxy pool in “http://user:password@host:port” format (<a target=“_blank” href=“https://webscraping.ai/proxies/smartproxy”&gt;Smartproxy&lt;/a> for example).
device	string	No	—	Type of device emulation.
error_on_404	boolean	No	—	Return error on 404 HTTP status on the target page (false by default).
error_on_redirect	boolean	No	—	Return error on redirect on the target page (false by default).
js_script	string	No	—	Custom JavaScript code to execute on the target page.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "selectors": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Multiple CSS selectors (null by default, returns whole page HTML)"
    },
    "url": {
      "type": "string",
      "description": "URL of the target page."
    },
    "headers": {
      "type": "object",
      "description": "HTTP headers to pass to the target page. Can be specified either via a nested query parameter (...&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (...&headers={\"One\": \"value1\", \"Another\": \"value2\"})."
    },
    "timeout": {
      "type": "integer",
      "description": "Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000)."
    },
    "js": {
      "type": "boolean",
      "description": "Execute on-page JavaScript using a headless browser (true by default)."
    },
    "js_timeout": {
      "type": "integer",
      "description": "Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page."
    },
    "wait_for": {
      "type": "string",
      "description": "CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout."
    },
    "proxy": {
      "type": "string",
      "description": "Type of proxy. Use `residential` if your site restricts traffic from datacenters, or `stealth` for the most heavily protected sites with advanced anti-bot detection (`datacenter` by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details.",
      "enum": [
        "datacenter",
        "residential",
        "stealth"
      ]
    },
    "country": {
      "type": "string",
      "description": "Country of the proxy to use (US by default).",
      "enum": [
        "us",
        "gb",
        "de",
        "it",
        "fr",
        "ca",
        "es",
        "ru",
        "jp",
        "kr",
        "in",
        "hk",
        "tr"
      ]
    },
    "custom_proxy": {
      "type": "string",
      "description": "Your own proxy URL to use instead of our built-in proxy pool in \"http://user:password@host:port\" format (<a target=\"_blank\" href=\"https://webscraping.ai/proxies/smartproxy\">Smartproxy</a> for example)."
    },
    "device": {
      "type": "string",
      "description": "Type of device emulation.",
      "enum": [
        "desktop",
        "mobile",
        "tablet"
      ]
    },
    "error_on_404": {
      "type": "boolean",
      "description": "Return error on 404 HTTP status on the target page (false by default)."
    },
    "error_on_redirect": {
      "type": "boolean",
      "description": "Return error on redirect on the target page (false by default)."
    },
    "js_script": {
      "type": "string",
      "description": "Custom JavaScript code to execute on the target page."
    }
  },
  "required": [
    "PCID",
    "url"
  ]
}

---

webscraping_ai_get_text

Page text by URL

Parameters:

Parameter	Type	Required	Default	Description
text_format	string	No	—	Format of the text response (plain by default). “plain” will return only the page body text. “json” and “xml” will return a json/xml with “title”, “description” and “content” keys.
return_links	boolean	No	—	[Works only with text_format=json] Return links from the page body text (false by default). Useful for building web crawlers.
url	string	Yes	—	URL of the target page.
headers	object	No	—	HTTP headers to pass to the target page. Can be specified either via a nested query parameter (…&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (…&headers={“One”: “value1”, “Another”: “value2”}).
timeout	integer	No	—	Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000).
js	boolean	No	—	Execute on-page JavaScript using a headless browser (true by default).
js_timeout	integer	No	—	Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page.
wait_for	string	No	—	CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout.
proxy	string	No	—	Type of proxy. Use residential if your site restricts traffic from datacenters, or stealth for the most heavily protected sites with advanced anti-bot detection (datacenter by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details.
country	string	No	—	Country of the proxy to use (US by default).
custom_proxy	string	No	—	Your own proxy URL to use instead of our built-in proxy pool in “http://user:password@host:port” format (<a target=“_blank” href=“https://webscraping.ai/proxies/smartproxy”&gt;Smartproxy&lt;/a> for example).
device	string	No	—	Type of device emulation.
error_on_404	boolean	No	—	Return error on 404 HTTP status on the target page (false by default).
error_on_redirect	boolean	No	—	Return error on redirect on the target page (false by default).
js_script	string	No	—	Custom JavaScript code to execute on the target page.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "text_format": {
      "type": "string",
      "description": "Format of the text response (plain by default). \"plain\" will return only the page body text. \"json\" and \"xml\" will return a json/xml with \"title\", \"description\" and \"content\" keys.",
      "enum": [
        "plain",
        "xml",
        "json"
      ]
    },
    "return_links": {
      "type": "boolean",
      "description": "[Works only with text_format=json] Return links from the page body text (false by default). Useful for building web crawlers."
    },
    "url": {
      "type": "string",
      "description": "URL of the target page."
    },
    "headers": {
      "type": "object",
      "description": "HTTP headers to pass to the target page. Can be specified either via a nested query parameter (...&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (...&headers={\"One\": \"value1\", \"Another\": \"value2\"})."
    },
    "timeout": {
      "type": "integer",
      "description": "Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000)."
    },
    "js": {
      "type": "boolean",
      "description": "Execute on-page JavaScript using a headless browser (true by default)."
    },
    "js_timeout": {
      "type": "integer",
      "description": "Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page."
    },
    "wait_for": {
      "type": "string",
      "description": "CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout."
    },
    "proxy": {
      "type": "string",
      "description": "Type of proxy. Use `residential` if your site restricts traffic from datacenters, or `stealth` for the most heavily protected sites with advanced anti-bot detection (`datacenter` by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details.",
      "enum": [
        "datacenter",
        "residential",
        "stealth"
      ]
    },
    "country": {
      "type": "string",
      "description": "Country of the proxy to use (US by default).",
      "enum": [
        "us",
        "gb",
        "de",
        "it",
        "fr",
        "ca",
        "es",
        "ru",
        "jp",
        "kr",
        "in",
        "hk",
        "tr"
      ]
    },
    "custom_proxy": {
      "type": "string",
      "description": "Your own proxy URL to use instead of our built-in proxy pool in \"http://user:password@host:port\" format (<a target=\"_blank\" href=\"https://webscraping.ai/proxies/smartproxy\">Smartproxy</a> for example)."
    },
    "device": {
      "type": "string",
      "description": "Type of device emulation.",
      "enum": [
        "desktop",
        "mobile",
        "tablet"
      ]
    },
    "error_on_404": {
      "type": "boolean",
      "description": "Return error on 404 HTTP status on the target page (false by default)."
    },
    "error_on_redirect": {
      "type": "boolean",
      "description": "Return error on redirect on the target page (false by default)."
    },
    "js_script": {
      "type": "string",
      "description": "Custom JavaScript code to execute on the target page."
    }
  },
  "required": [
    "PCID",
    "url"
  ]
}