Extrae datos estructurados de páginas web con LLMs
curl --request POST \
--url https://api.firecrawl.dev/v2/extract \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"urls": [
"<string>"
],
"enableWebSearch": false,
"ignoreInvalidURLs": true,
"ignoreSitemap": false,
"includeSubdomains": true,
"prompt": "<string>",
"schema": {},
"scrapeOptions": {
"actions": [
{
"milliseconds": 2,
"type": "wait"
}
],
"blockAds": true,
"excludeTags": [
"<string>"
],
"formats": [
"markdown"
],
"headers": {},
"includeTags": [
"<string>"
],
"location": {
"country": "US",
"languages": [
"en-US"
]
},
"lockdown": false,
"maxAge": 172800000,
"minAge": 123,
"mobile": false,
"onlyCleanContent": false,
"onlyMainContent": true,
"parsers": [
"pdf"
],
"proxy": "auto",
"redactPII": false,
"removeBase64Images": true,
"skipTlsVerification": true,
"storeInCache": true,
"threatProtection": {
"blacklist": [
"<string>"
],
"blockedTlds": [
"<string>"
],
"riskScoreThreshold": 75,
"whitelist": [
"<string>"
]
},
"timeout": 60000,
"waitFor": 0
},
"showSources": false,
"threatProtection": {
"blacklist": [
"<string>"
],
"blockedTlds": [
"<string>"
],
"riskScoreThreshold": 75,
"whitelist": [
"<string>"
]
}
}
'import requests
url = "https://api.firecrawl.dev/v2/extract"
payload = {
"urls": ["<string>"],
"enableWebSearch": False,
"ignoreInvalidURLs": True,
"ignoreSitemap": False,
"includeSubdomains": True,
"prompt": "<string>",
"schema": {},
"scrapeOptions": {
"actions": [
{
"milliseconds": 2,
"type": "wait"
}
],
"blockAds": True,
"excludeTags": ["<string>"],
"formats": ["markdown"],
"headers": {},
"includeTags": ["<string>"],
"location": {
"country": "US",
"languages": ["en-US"]
},
"lockdown": False,
"maxAge": 172800000,
"minAge": 123,
"mobile": False,
"onlyCleanContent": False,
"onlyMainContent": True,
"parsers": ["pdf"],
"proxy": "auto",
"redactPII": False,
"removeBase64Images": True,
"skipTlsVerification": True,
"storeInCache": True,
"threatProtection": {
"blacklist": ["<string>"],
"blockedTlds": ["<string>"],
"riskScoreThreshold": 75,
"whitelist": ["<string>"]
},
"timeout": 60000,
"waitFor": 0
},
"showSources": False,
"threatProtection": {
"blacklist": ["<string>"],
"blockedTlds": ["<string>"],
"riskScoreThreshold": 75,
"whitelist": ["<string>"]
}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
urls: ['<string>'],
enableWebSearch: false,
ignoreInvalidURLs: true,
ignoreSitemap: false,
includeSubdomains: true,
prompt: '<string>',
schema: {},
scrapeOptions: {
actions: [{milliseconds: 2, type: 'wait'}],
blockAds: true,
excludeTags: ['<string>'],
formats: ['markdown'],
headers: {},
includeTags: ['<string>'],
location: {country: 'US', languages: ['en-US']},
lockdown: false,
maxAge: 172800000,
minAge: 123,
mobile: false,
onlyCleanContent: false,
onlyMainContent: true,
parsers: ['pdf'],
proxy: 'auto',
redactPII: false,
removeBase64Images: true,
skipTlsVerification: true,
storeInCache: true,
threatProtection: {
blacklist: ['<string>'],
blockedTlds: ['<string>'],
riskScoreThreshold: 75,
whitelist: ['<string>']
},
timeout: 60000,
waitFor: 0
},
showSources: false,
threatProtection: {
blacklist: ['<string>'],
blockedTlds: ['<string>'],
riskScoreThreshold: 75,
whitelist: ['<string>']
}
})
};
fetch('https://api.firecrawl.dev/v2/extract', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.firecrawl.dev/v2/extract",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'urls' => [
'<string>'
],
'enableWebSearch' => false,
'ignoreInvalidURLs' => true,
'ignoreSitemap' => false,
'includeSubdomains' => true,
'prompt' => '<string>',
'schema' => [
],
'scrapeOptions' => [
'actions' => [
[
'milliseconds' => 2,
'type' => 'wait'
]
],
'blockAds' => true,
'excludeTags' => [
'<string>'
],
'formats' => [
'markdown'
],
'headers' => [
],
'includeTags' => [
'<string>'
],
'location' => [
'country' => 'US',
'languages' => [
'en-US'
]
],
'lockdown' => false,
'maxAge' => 172800000,
'minAge' => 123,
'mobile' => false,
'onlyCleanContent' => false,
'onlyMainContent' => true,
'parsers' => [
'pdf'
],
'proxy' => 'auto',
'redactPII' => false,
'removeBase64Images' => true,
'skipTlsVerification' => true,
'storeInCache' => true,
'threatProtection' => [
'blacklist' => [
'<string>'
],
'blockedTlds' => [
'<string>'
],
'riskScoreThreshold' => 75,
'whitelist' => [
'<string>'
]
],
'timeout' => 60000,
'waitFor' => 0
],
'showSources' => false,
'threatProtection' => [
'blacklist' => [
'<string>'
],
'blockedTlds' => [
'<string>'
],
'riskScoreThreshold' => 75,
'whitelist' => [
'<string>'
]
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.firecrawl.dev/v2/extract"
payload := strings.NewReader("{\n \"urls\": [\n \"<string>\"\n ],\n \"enableWebSearch\": false,\n \"ignoreInvalidURLs\": true,\n \"ignoreSitemap\": false,\n \"includeSubdomains\": true,\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"scrapeOptions\": {\n \"actions\": [\n {\n \"milliseconds\": 2,\n \"type\": \"wait\"\n }\n ],\n \"blockAds\": true,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"formats\": [\n \"markdown\"\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"location\": {\n \"country\": \"US\",\n \"languages\": [\n \"en-US\"\n ]\n },\n \"lockdown\": false,\n \"maxAge\": 172800000,\n \"minAge\": 123,\n \"mobile\": false,\n \"onlyCleanContent\": false,\n \"onlyMainContent\": true,\n \"parsers\": [\n \"pdf\"\n ],\n \"proxy\": \"auto\",\n \"redactPII\": false,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": true,\n \"storeInCache\": true,\n \"threatProtection\": {\n \"blacklist\": [\n \"<string>\"\n ],\n \"blockedTlds\": [\n \"<string>\"\n ],\n \"riskScoreThreshold\": 75,\n \"whitelist\": [\n \"<string>\"\n ]\n },\n \"timeout\": 60000,\n \"waitFor\": 0\n },\n \"showSources\": false,\n \"threatProtection\": {\n \"blacklist\": [\n \"<string>\"\n ],\n \"blockedTlds\": [\n \"<string>\"\n ],\n \"riskScoreThreshold\": 75,\n \"whitelist\": [\n \"<string>\"\n ]\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.firecrawl.dev/v2/extract")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"urls\": [\n \"<string>\"\n ],\n \"enableWebSearch\": false,\n \"ignoreInvalidURLs\": true,\n \"ignoreSitemap\": false,\n \"includeSubdomains\": true,\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"scrapeOptions\": {\n \"actions\": [\n {\n \"milliseconds\": 2,\n \"type\": \"wait\"\n }\n ],\n \"blockAds\": true,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"formats\": [\n \"markdown\"\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"location\": {\n \"country\": \"US\",\n \"languages\": [\n \"en-US\"\n ]\n },\n \"lockdown\": false,\n \"maxAge\": 172800000,\n \"minAge\": 123,\n \"mobile\": false,\n \"onlyCleanContent\": false,\n \"onlyMainContent\": true,\n \"parsers\": [\n \"pdf\"\n ],\n \"proxy\": \"auto\",\n \"redactPII\": false,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": true,\n \"storeInCache\": true,\n \"threatProtection\": {\n \"blacklist\": [\n \"<string>\"\n ],\n \"blockedTlds\": [\n \"<string>\"\n ],\n \"riskScoreThreshold\": 75,\n \"whitelist\": [\n \"<string>\"\n ]\n },\n \"timeout\": 60000,\n \"waitFor\": 0\n },\n \"showSources\": false,\n \"threatProtection\": {\n \"blacklist\": [\n \"<string>\"\n ],\n \"blockedTlds\": [\n \"<string>\"\n ],\n \"riskScoreThreshold\": 75,\n \"whitelist\": [\n \"<string>\"\n ]\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.firecrawl.dev/v2/extract")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"urls\": [\n \"<string>\"\n ],\n \"enableWebSearch\": false,\n \"ignoreInvalidURLs\": true,\n \"ignoreSitemap\": false,\n \"includeSubdomains\": true,\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"scrapeOptions\": {\n \"actions\": [\n {\n \"milliseconds\": 2,\n \"type\": \"wait\"\n }\n ],\n \"blockAds\": true,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"formats\": [\n \"markdown\"\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"location\": {\n \"country\": \"US\",\n \"languages\": [\n \"en-US\"\n ]\n },\n \"lockdown\": false,\n \"maxAge\": 172800000,\n \"minAge\": 123,\n \"mobile\": false,\n \"onlyCleanContent\": false,\n \"onlyMainContent\": true,\n \"parsers\": [\n \"pdf\"\n ],\n \"proxy\": \"auto\",\n \"redactPII\": false,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": true,\n \"storeInCache\": true,\n \"threatProtection\": {\n \"blacklist\": [\n \"<string>\"\n ],\n \"blockedTlds\": [\n \"<string>\"\n ],\n \"riskScoreThreshold\": 75,\n \"whitelist\": [\n \"<string>\"\n ]\n },\n \"timeout\": 60000,\n \"waitFor\": 0\n },\n \"showSources\": false,\n \"threatProtection\": {\n \"blacklist\": [\n \"<string>\"\n ],\n \"blockedTlds\": [\n \"<string>\"\n ],\n \"riskScoreThreshold\": 75,\n \"whitelist\": [\n \"<string>\"\n ]\n }\n}"
response = http.request(request)
puts response.read_body{
"id": "<string>",
"invalidURLs": [
"<string>"
],
"success": true
}{
"error": "Invalid input data."
}{
"error": "An unexpected error occurred on the server."
}Endpoints de extracción
Extraer
POST
/
extract
Extrae datos estructurados de páginas web con LLMs
curl --request POST \
--url https://api.firecrawl.dev/v2/extract \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"urls": [
"<string>"
],
"enableWebSearch": false,
"ignoreInvalidURLs": true,
"ignoreSitemap": false,
"includeSubdomains": true,
"prompt": "<string>",
"schema": {},
"scrapeOptions": {
"actions": [
{
"milliseconds": 2,
"type": "wait"
}
],
"blockAds": true,
"excludeTags": [
"<string>"
],
"formats": [
"markdown"
],
"headers": {},
"includeTags": [
"<string>"
],
"location": {
"country": "US",
"languages": [
"en-US"
]
},
"lockdown": false,
"maxAge": 172800000,
"minAge": 123,
"mobile": false,
"onlyCleanContent": false,
"onlyMainContent": true,
"parsers": [
"pdf"
],
"proxy": "auto",
"redactPII": false,
"removeBase64Images": true,
"skipTlsVerification": true,
"storeInCache": true,
"threatProtection": {
"blacklist": [
"<string>"
],
"blockedTlds": [
"<string>"
],
"riskScoreThreshold": 75,
"whitelist": [
"<string>"
]
},
"timeout": 60000,
"waitFor": 0
},
"showSources": false,
"threatProtection": {
"blacklist": [
"<string>"
],
"blockedTlds": [
"<string>"
],
"riskScoreThreshold": 75,
"whitelist": [
"<string>"
]
}
}
'import requests
url = "https://api.firecrawl.dev/v2/extract"
payload = {
"urls": ["<string>"],
"enableWebSearch": False,
"ignoreInvalidURLs": True,
"ignoreSitemap": False,
"includeSubdomains": True,
"prompt": "<string>",
"schema": {},
"scrapeOptions": {
"actions": [
{
"milliseconds": 2,
"type": "wait"
}
],
"blockAds": True,
"excludeTags": ["<string>"],
"formats": ["markdown"],
"headers": {},
"includeTags": ["<string>"],
"location": {
"country": "US",
"languages": ["en-US"]
},
"lockdown": False,
"maxAge": 172800000,
"minAge": 123,
"mobile": False,
"onlyCleanContent": False,
"onlyMainContent": True,
"parsers": ["pdf"],
"proxy": "auto",
"redactPII": False,
"removeBase64Images": True,
"skipTlsVerification": True,
"storeInCache": True,
"threatProtection": {
"blacklist": ["<string>"],
"blockedTlds": ["<string>"],
"riskScoreThreshold": 75,
"whitelist": ["<string>"]
},
"timeout": 60000,
"waitFor": 0
},
"showSources": False,
"threatProtection": {
"blacklist": ["<string>"],
"blockedTlds": ["<string>"],
"riskScoreThreshold": 75,
"whitelist": ["<string>"]
}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
urls: ['<string>'],
enableWebSearch: false,
ignoreInvalidURLs: true,
ignoreSitemap: false,
includeSubdomains: true,
prompt: '<string>',
schema: {},
scrapeOptions: {
actions: [{milliseconds: 2, type: 'wait'}],
blockAds: true,
excludeTags: ['<string>'],
formats: ['markdown'],
headers: {},
includeTags: ['<string>'],
location: {country: 'US', languages: ['en-US']},
lockdown: false,
maxAge: 172800000,
minAge: 123,
mobile: false,
onlyCleanContent: false,
onlyMainContent: true,
parsers: ['pdf'],
proxy: 'auto',
redactPII: false,
removeBase64Images: true,
skipTlsVerification: true,
storeInCache: true,
threatProtection: {
blacklist: ['<string>'],
blockedTlds: ['<string>'],
riskScoreThreshold: 75,
whitelist: ['<string>']
},
timeout: 60000,
waitFor: 0
},
showSources: false,
threatProtection: {
blacklist: ['<string>'],
blockedTlds: ['<string>'],
riskScoreThreshold: 75,
whitelist: ['<string>']
}
})
};
fetch('https://api.firecrawl.dev/v2/extract', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.firecrawl.dev/v2/extract",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'urls' => [
'<string>'
],
'enableWebSearch' => false,
'ignoreInvalidURLs' => true,
'ignoreSitemap' => false,
'includeSubdomains' => true,
'prompt' => '<string>',
'schema' => [
],
'scrapeOptions' => [
'actions' => [
[
'milliseconds' => 2,
'type' => 'wait'
]
],
'blockAds' => true,
'excludeTags' => [
'<string>'
],
'formats' => [
'markdown'
],
'headers' => [
],
'includeTags' => [
'<string>'
],
'location' => [
'country' => 'US',
'languages' => [
'en-US'
]
],
'lockdown' => false,
'maxAge' => 172800000,
'minAge' => 123,
'mobile' => false,
'onlyCleanContent' => false,
'onlyMainContent' => true,
'parsers' => [
'pdf'
],
'proxy' => 'auto',
'redactPII' => false,
'removeBase64Images' => true,
'skipTlsVerification' => true,
'storeInCache' => true,
'threatProtection' => [
'blacklist' => [
'<string>'
],
'blockedTlds' => [
'<string>'
],
'riskScoreThreshold' => 75,
'whitelist' => [
'<string>'
]
],
'timeout' => 60000,
'waitFor' => 0
],
'showSources' => false,
'threatProtection' => [
'blacklist' => [
'<string>'
],
'blockedTlds' => [
'<string>'
],
'riskScoreThreshold' => 75,
'whitelist' => [
'<string>'
]
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.firecrawl.dev/v2/extract"
payload := strings.NewReader("{\n \"urls\": [\n \"<string>\"\n ],\n \"enableWebSearch\": false,\n \"ignoreInvalidURLs\": true,\n \"ignoreSitemap\": false,\n \"includeSubdomains\": true,\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"scrapeOptions\": {\n \"actions\": [\n {\n \"milliseconds\": 2,\n \"type\": \"wait\"\n }\n ],\n \"blockAds\": true,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"formats\": [\n \"markdown\"\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"location\": {\n \"country\": \"US\",\n \"languages\": [\n \"en-US\"\n ]\n },\n \"lockdown\": false,\n \"maxAge\": 172800000,\n \"minAge\": 123,\n \"mobile\": false,\n \"onlyCleanContent\": false,\n \"onlyMainContent\": true,\n \"parsers\": [\n \"pdf\"\n ],\n \"proxy\": \"auto\",\n \"redactPII\": false,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": true,\n \"storeInCache\": true,\n \"threatProtection\": {\n \"blacklist\": [\n \"<string>\"\n ],\n \"blockedTlds\": [\n \"<string>\"\n ],\n \"riskScoreThreshold\": 75,\n \"whitelist\": [\n \"<string>\"\n ]\n },\n \"timeout\": 60000,\n \"waitFor\": 0\n },\n \"showSources\": false,\n \"threatProtection\": {\n \"blacklist\": [\n \"<string>\"\n ],\n \"blockedTlds\": [\n \"<string>\"\n ],\n \"riskScoreThreshold\": 75,\n \"whitelist\": [\n \"<string>\"\n ]\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.firecrawl.dev/v2/extract")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"urls\": [\n \"<string>\"\n ],\n \"enableWebSearch\": false,\n \"ignoreInvalidURLs\": true,\n \"ignoreSitemap\": false,\n \"includeSubdomains\": true,\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"scrapeOptions\": {\n \"actions\": [\n {\n \"milliseconds\": 2,\n \"type\": \"wait\"\n }\n ],\n \"blockAds\": true,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"formats\": [\n \"markdown\"\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"location\": {\n \"country\": \"US\",\n \"languages\": [\n \"en-US\"\n ]\n },\n \"lockdown\": false,\n \"maxAge\": 172800000,\n \"minAge\": 123,\n \"mobile\": false,\n \"onlyCleanContent\": false,\n \"onlyMainContent\": true,\n \"parsers\": [\n \"pdf\"\n ],\n \"proxy\": \"auto\",\n \"redactPII\": false,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": true,\n \"storeInCache\": true,\n \"threatProtection\": {\n \"blacklist\": [\n \"<string>\"\n ],\n \"blockedTlds\": [\n \"<string>\"\n ],\n \"riskScoreThreshold\": 75,\n \"whitelist\": [\n \"<string>\"\n ]\n },\n \"timeout\": 60000,\n \"waitFor\": 0\n },\n \"showSources\": false,\n \"threatProtection\": {\n \"blacklist\": [\n \"<string>\"\n ],\n \"blockedTlds\": [\n \"<string>\"\n ],\n \"riskScoreThreshold\": 75,\n \"whitelist\": [\n \"<string>\"\n ]\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.firecrawl.dev/v2/extract")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"urls\": [\n \"<string>\"\n ],\n \"enableWebSearch\": false,\n \"ignoreInvalidURLs\": true,\n \"ignoreSitemap\": false,\n \"includeSubdomains\": true,\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"scrapeOptions\": {\n \"actions\": [\n {\n \"milliseconds\": 2,\n \"type\": \"wait\"\n }\n ],\n \"blockAds\": true,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"formats\": [\n \"markdown\"\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"location\": {\n \"country\": \"US\",\n \"languages\": [\n \"en-US\"\n ]\n },\n \"lockdown\": false,\n \"maxAge\": 172800000,\n \"minAge\": 123,\n \"mobile\": false,\n \"onlyCleanContent\": false,\n \"onlyMainContent\": true,\n \"parsers\": [\n \"pdf\"\n ],\n \"proxy\": \"auto\",\n \"redactPII\": false,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": true,\n \"storeInCache\": true,\n \"threatProtection\": {\n \"blacklist\": [\n \"<string>\"\n ],\n \"blockedTlds\": [\n \"<string>\"\n ],\n \"riskScoreThreshold\": 75,\n \"whitelist\": [\n \"<string>\"\n ]\n },\n \"timeout\": 60000,\n \"waitFor\": 0\n },\n \"showSources\": false,\n \"threatProtection\": {\n \"blacklist\": [\n \"<string>\"\n ],\n \"blockedTlds\": [\n \"<string>\"\n ],\n \"riskScoreThreshold\": 75,\n \"whitelist\": [\n \"<string>\"\n ]\n }\n}"
response = http.request(request)
puts response.read_body{
"id": "<string>",
"invalidURLs": [
"<string>"
],
"success": true
}{
"error": "Invalid input data."
}{
"error": "An unexpected error occurred on the server."
}¿Eres un agente de IA que necesita una clave de API de Firecrawl? Consulta firecrawl.dev/agent-onboarding/SKILL.md para ver las instrucciones de incorporación automática.
Autorizaciones
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Cuerpo
application/json
Las URL de las que se extraerán datos. Deben estar en formato glob.
Si es true, la extracción utilizará la búsqueda web para encontrar datos adicionales
Si se especifican URLs no válidas en el array urls, se ignorarán. En lugar de provocar el fallo de toda la solicitud, se realizará una extracción con las URLs válidas restantes, y las URLs no válidas se devolverán en el campo invalidURLs de la respuesta.
Si es true, se ignorarán los archivos sitemap.xml durante el escaneo del sitio web
Si se establece en true, también se escanearán los subdominios de las URL proporcionadas
Prompt para orientar el proceso de extracción
Esquema que define la estructura de los datos extraídos. Debe cumplir con JSON Schema.
Show child attributes
Show child attributes
Cuando se establece en true, las fuentes utilizadas para extraer los datos se incluirán en la respuesta bajo la clave sources.
Anulación por solicitud de Protección contra amenazas. Los campos que proporciones reemplazan los campos correspondientes de la política de tu organización solo para esta solicitud; los campos omitidos conservan sus valores a nivel de organización. Requiere que Protección contra amenazas esté habilitada para tu equipo (función enterprise); de lo contrario, la solicitud se rechaza con un 403. Si tu organización ha deshabilitado las anulaciones por solicitud, cualquier solicitud que incluya este objeto se rechaza con un 403. Si Protección contra amenazas se aplica de forma obligatoria a tu equipo, mode no puede establecerse en off.
Show child attributes
Show child attributes
Respuesta
Extracción exitosa
⌘I