Extraire des données structurées depuis des pages à l’aide de LLM
curl --request POST \
--url https://api.firecrawl.dev/v1/extract \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"urls": [
"<string>"
],
"enableWebSearch": false,
"ignoreInvalidURLs": false,
"ignoreSitemap": false,
"includeSubdomains": true,
"prompt": "<string>",
"schema": {},
"scrapeOptions": {
"actions": [
{
"type": "wait",
"milliseconds": 2,
"selector": "#my-element"
}
],
"blockAds": true,
"excludeTags": [
"<string>"
],
"headers": {},
"includeTags": [
"<string>"
],
"jsonOptions": {
"prompt": "<string>",
"schema": {},
"systemPrompt": "<string>"
},
"location": {
"country": "US",
"languages": [
"en-US"
]
},
"maxAge": 0,
"mobile": false,
"onlyMainContent": true,
"parsePDF": true,
"removeBase64Images": true,
"skipTlsVerification": false,
"storeInCache": true,
"threatProtection": {
"blacklist": [
"<string>"
],
"blockedTlds": [
"<string>"
],
"riskScoreThreshold": 75,
"whitelist": [
"<string>"
]
},
"timeout": 30000,
"waitFor": 0,
"changeTrackingOptions": {
"modes": [],
"prompt": "<string>",
"schema": {},
"tag": null
},
"formats": [
"markdown"
]
},
"showSources": false,
"threatProtection": {
"blacklist": [
"<string>"
],
"blockedTlds": [
"<string>"
],
"riskScoreThreshold": 75,
"whitelist": [
"<string>"
]
}
}
'import requests
url = "https://api.firecrawl.dev/v1/extract"
payload = {
"urls": ["<string>"],
"enableWebSearch": False,
"ignoreInvalidURLs": False,
"ignoreSitemap": False,
"includeSubdomains": True,
"prompt": "<string>",
"schema": {},
"scrapeOptions": {
"actions": [
{
"type": "wait",
"milliseconds": 2,
"selector": "#my-element"
}
],
"blockAds": True,
"excludeTags": ["<string>"],
"headers": {},
"includeTags": ["<string>"],
"jsonOptions": {
"prompt": "<string>",
"schema": {},
"systemPrompt": "<string>"
},
"location": {
"country": "US",
"languages": ["en-US"]
},
"maxAge": 0,
"mobile": False,
"onlyMainContent": True,
"parsePDF": True,
"removeBase64Images": True,
"skipTlsVerification": False,
"storeInCache": True,
"threatProtection": {
"blacklist": ["<string>"],
"blockedTlds": ["<string>"],
"riskScoreThreshold": 75,
"whitelist": ["<string>"]
},
"timeout": 30000,
"waitFor": 0,
"changeTrackingOptions": {
"modes": [],
"prompt": "<string>",
"schema": {},
"tag": None
},
"formats": ["markdown"]
},
"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: false,
ignoreSitemap: false,
includeSubdomains: true,
prompt: '<string>',
schema: {},
scrapeOptions: {
actions: [{type: 'wait', milliseconds: 2, selector: '#my-element'}],
blockAds: true,
excludeTags: ['<string>'],
headers: {},
includeTags: ['<string>'],
jsonOptions: {prompt: '<string>', schema: {}, systemPrompt: '<string>'},
location: {country: 'US', languages: ['en-US']},
maxAge: 0,
mobile: false,
onlyMainContent: true,
parsePDF: true,
removeBase64Images: true,
skipTlsVerification: false,
storeInCache: true,
threatProtection: {
blacklist: ['<string>'],
blockedTlds: ['<string>'],
riskScoreThreshold: 75,
whitelist: ['<string>']
},
timeout: 30000,
waitFor: 0,
changeTrackingOptions: {modes: [], prompt: '<string>', schema: {}, tag: null},
formats: ['markdown']
},
showSources: false,
threatProtection: {
blacklist: ['<string>'],
blockedTlds: ['<string>'],
riskScoreThreshold: 75,
whitelist: ['<string>']
}
})
};
fetch('https://api.firecrawl.dev/v1/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/v1/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' => false,
'ignoreSitemap' => false,
'includeSubdomains' => true,
'prompt' => '<string>',
'schema' => [
],
'scrapeOptions' => [
'actions' => [
[
'type' => 'wait',
'milliseconds' => 2,
'selector' => '#my-element'
]
],
'blockAds' => true,
'excludeTags' => [
'<string>'
],
'headers' => [
],
'includeTags' => [
'<string>'
],
'jsonOptions' => [
'prompt' => '<string>',
'schema' => [
],
'systemPrompt' => '<string>'
],
'location' => [
'country' => 'US',
'languages' => [
'en-US'
]
],
'maxAge' => 0,
'mobile' => false,
'onlyMainContent' => true,
'parsePDF' => true,
'removeBase64Images' => true,
'skipTlsVerification' => false,
'storeInCache' => true,
'threatProtection' => [
'blacklist' => [
'<string>'
],
'blockedTlds' => [
'<string>'
],
'riskScoreThreshold' => 75,
'whitelist' => [
'<string>'
]
],
'timeout' => 30000,
'waitFor' => 0,
'changeTrackingOptions' => [
'modes' => [
],
'prompt' => '<string>',
'schema' => [
],
'tag' => null
],
'formats' => [
'markdown'
]
],
'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/v1/extract"
payload := strings.NewReader("{\n \"urls\": [\n \"<string>\"\n ],\n \"enableWebSearch\": false,\n \"ignoreInvalidURLs\": false,\n \"ignoreSitemap\": false,\n \"includeSubdomains\": true,\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"scrapeOptions\": {\n \"actions\": [\n {\n \"type\": \"wait\",\n \"milliseconds\": 2,\n \"selector\": \"#my-element\"\n }\n ],\n \"blockAds\": true,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"jsonOptions\": {\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"systemPrompt\": \"<string>\"\n },\n \"location\": {\n \"country\": \"US\",\n \"languages\": [\n \"en-US\"\n ]\n },\n \"maxAge\": 0,\n \"mobile\": false,\n \"onlyMainContent\": true,\n \"parsePDF\": true,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": false,\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\": 30000,\n \"waitFor\": 0,\n \"changeTrackingOptions\": {\n \"modes\": [],\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"tag\": null\n },\n \"formats\": [\n \"markdown\"\n ]\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/v1/extract")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"urls\": [\n \"<string>\"\n ],\n \"enableWebSearch\": false,\n \"ignoreInvalidURLs\": false,\n \"ignoreSitemap\": false,\n \"includeSubdomains\": true,\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"scrapeOptions\": {\n \"actions\": [\n {\n \"type\": \"wait\",\n \"milliseconds\": 2,\n \"selector\": \"#my-element\"\n }\n ],\n \"blockAds\": true,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"jsonOptions\": {\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"systemPrompt\": \"<string>\"\n },\n \"location\": {\n \"country\": \"US\",\n \"languages\": [\n \"en-US\"\n ]\n },\n \"maxAge\": 0,\n \"mobile\": false,\n \"onlyMainContent\": true,\n \"parsePDF\": true,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": false,\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\": 30000,\n \"waitFor\": 0,\n \"changeTrackingOptions\": {\n \"modes\": [],\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"tag\": null\n },\n \"formats\": [\n \"markdown\"\n ]\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/v1/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\": false,\n \"ignoreSitemap\": false,\n \"includeSubdomains\": true,\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"scrapeOptions\": {\n \"actions\": [\n {\n \"type\": \"wait\",\n \"milliseconds\": 2,\n \"selector\": \"#my-element\"\n }\n ],\n \"blockAds\": true,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"jsonOptions\": {\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"systemPrompt\": \"<string>\"\n },\n \"location\": {\n \"country\": \"US\",\n \"languages\": [\n \"en-US\"\n ]\n },\n \"maxAge\": 0,\n \"mobile\": false,\n \"onlyMainContent\": true,\n \"parsePDF\": true,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": false,\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\": 30000,\n \"waitFor\": 0,\n \"changeTrackingOptions\": {\n \"modes\": [],\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"tag\": null\n },\n \"formats\": [\n \"markdown\"\n ]\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."
}Points de terminaison d’extraction
Extraction
POST
/
extract
Extraire des données structurées depuis des pages à l’aide de LLM
curl --request POST \
--url https://api.firecrawl.dev/v1/extract \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"urls": [
"<string>"
],
"enableWebSearch": false,
"ignoreInvalidURLs": false,
"ignoreSitemap": false,
"includeSubdomains": true,
"prompt": "<string>",
"schema": {},
"scrapeOptions": {
"actions": [
{
"type": "wait",
"milliseconds": 2,
"selector": "#my-element"
}
],
"blockAds": true,
"excludeTags": [
"<string>"
],
"headers": {},
"includeTags": [
"<string>"
],
"jsonOptions": {
"prompt": "<string>",
"schema": {},
"systemPrompt": "<string>"
},
"location": {
"country": "US",
"languages": [
"en-US"
]
},
"maxAge": 0,
"mobile": false,
"onlyMainContent": true,
"parsePDF": true,
"removeBase64Images": true,
"skipTlsVerification": false,
"storeInCache": true,
"threatProtection": {
"blacklist": [
"<string>"
],
"blockedTlds": [
"<string>"
],
"riskScoreThreshold": 75,
"whitelist": [
"<string>"
]
},
"timeout": 30000,
"waitFor": 0,
"changeTrackingOptions": {
"modes": [],
"prompt": "<string>",
"schema": {},
"tag": null
},
"formats": [
"markdown"
]
},
"showSources": false,
"threatProtection": {
"blacklist": [
"<string>"
],
"blockedTlds": [
"<string>"
],
"riskScoreThreshold": 75,
"whitelist": [
"<string>"
]
}
}
'import requests
url = "https://api.firecrawl.dev/v1/extract"
payload = {
"urls": ["<string>"],
"enableWebSearch": False,
"ignoreInvalidURLs": False,
"ignoreSitemap": False,
"includeSubdomains": True,
"prompt": "<string>",
"schema": {},
"scrapeOptions": {
"actions": [
{
"type": "wait",
"milliseconds": 2,
"selector": "#my-element"
}
],
"blockAds": True,
"excludeTags": ["<string>"],
"headers": {},
"includeTags": ["<string>"],
"jsonOptions": {
"prompt": "<string>",
"schema": {},
"systemPrompt": "<string>"
},
"location": {
"country": "US",
"languages": ["en-US"]
},
"maxAge": 0,
"mobile": False,
"onlyMainContent": True,
"parsePDF": True,
"removeBase64Images": True,
"skipTlsVerification": False,
"storeInCache": True,
"threatProtection": {
"blacklist": ["<string>"],
"blockedTlds": ["<string>"],
"riskScoreThreshold": 75,
"whitelist": ["<string>"]
},
"timeout": 30000,
"waitFor": 0,
"changeTrackingOptions": {
"modes": [],
"prompt": "<string>",
"schema": {},
"tag": None
},
"formats": ["markdown"]
},
"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: false,
ignoreSitemap: false,
includeSubdomains: true,
prompt: '<string>',
schema: {},
scrapeOptions: {
actions: [{type: 'wait', milliseconds: 2, selector: '#my-element'}],
blockAds: true,
excludeTags: ['<string>'],
headers: {},
includeTags: ['<string>'],
jsonOptions: {prompt: '<string>', schema: {}, systemPrompt: '<string>'},
location: {country: 'US', languages: ['en-US']},
maxAge: 0,
mobile: false,
onlyMainContent: true,
parsePDF: true,
removeBase64Images: true,
skipTlsVerification: false,
storeInCache: true,
threatProtection: {
blacklist: ['<string>'],
blockedTlds: ['<string>'],
riskScoreThreshold: 75,
whitelist: ['<string>']
},
timeout: 30000,
waitFor: 0,
changeTrackingOptions: {modes: [], prompt: '<string>', schema: {}, tag: null},
formats: ['markdown']
},
showSources: false,
threatProtection: {
blacklist: ['<string>'],
blockedTlds: ['<string>'],
riskScoreThreshold: 75,
whitelist: ['<string>']
}
})
};
fetch('https://api.firecrawl.dev/v1/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/v1/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' => false,
'ignoreSitemap' => false,
'includeSubdomains' => true,
'prompt' => '<string>',
'schema' => [
],
'scrapeOptions' => [
'actions' => [
[
'type' => 'wait',
'milliseconds' => 2,
'selector' => '#my-element'
]
],
'blockAds' => true,
'excludeTags' => [
'<string>'
],
'headers' => [
],
'includeTags' => [
'<string>'
],
'jsonOptions' => [
'prompt' => '<string>',
'schema' => [
],
'systemPrompt' => '<string>'
],
'location' => [
'country' => 'US',
'languages' => [
'en-US'
]
],
'maxAge' => 0,
'mobile' => false,
'onlyMainContent' => true,
'parsePDF' => true,
'removeBase64Images' => true,
'skipTlsVerification' => false,
'storeInCache' => true,
'threatProtection' => [
'blacklist' => [
'<string>'
],
'blockedTlds' => [
'<string>'
],
'riskScoreThreshold' => 75,
'whitelist' => [
'<string>'
]
],
'timeout' => 30000,
'waitFor' => 0,
'changeTrackingOptions' => [
'modes' => [
],
'prompt' => '<string>',
'schema' => [
],
'tag' => null
],
'formats' => [
'markdown'
]
],
'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/v1/extract"
payload := strings.NewReader("{\n \"urls\": [\n \"<string>\"\n ],\n \"enableWebSearch\": false,\n \"ignoreInvalidURLs\": false,\n \"ignoreSitemap\": false,\n \"includeSubdomains\": true,\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"scrapeOptions\": {\n \"actions\": [\n {\n \"type\": \"wait\",\n \"milliseconds\": 2,\n \"selector\": \"#my-element\"\n }\n ],\n \"blockAds\": true,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"jsonOptions\": {\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"systemPrompt\": \"<string>\"\n },\n \"location\": {\n \"country\": \"US\",\n \"languages\": [\n \"en-US\"\n ]\n },\n \"maxAge\": 0,\n \"mobile\": false,\n \"onlyMainContent\": true,\n \"parsePDF\": true,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": false,\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\": 30000,\n \"waitFor\": 0,\n \"changeTrackingOptions\": {\n \"modes\": [],\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"tag\": null\n },\n \"formats\": [\n \"markdown\"\n ]\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/v1/extract")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"urls\": [\n \"<string>\"\n ],\n \"enableWebSearch\": false,\n \"ignoreInvalidURLs\": false,\n \"ignoreSitemap\": false,\n \"includeSubdomains\": true,\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"scrapeOptions\": {\n \"actions\": [\n {\n \"type\": \"wait\",\n \"milliseconds\": 2,\n \"selector\": \"#my-element\"\n }\n ],\n \"blockAds\": true,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"jsonOptions\": {\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"systemPrompt\": \"<string>\"\n },\n \"location\": {\n \"country\": \"US\",\n \"languages\": [\n \"en-US\"\n ]\n },\n \"maxAge\": 0,\n \"mobile\": false,\n \"onlyMainContent\": true,\n \"parsePDF\": true,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": false,\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\": 30000,\n \"waitFor\": 0,\n \"changeTrackingOptions\": {\n \"modes\": [],\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"tag\": null\n },\n \"formats\": [\n \"markdown\"\n ]\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/v1/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\": false,\n \"ignoreSitemap\": false,\n \"includeSubdomains\": true,\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"scrapeOptions\": {\n \"actions\": [\n {\n \"type\": \"wait\",\n \"milliseconds\": 2,\n \"selector\": \"#my-element\"\n }\n ],\n \"blockAds\": true,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"jsonOptions\": {\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"systemPrompt\": \"<string>\"\n },\n \"location\": {\n \"country\": \"US\",\n \"languages\": [\n \"en-US\"\n ]\n },\n \"maxAge\": 0,\n \"mobile\": false,\n \"onlyMainContent\": true,\n \"parsePDF\": true,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": false,\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\": 30000,\n \"waitFor\": 0,\n \"changeTrackingOptions\": {\n \"modes\": [],\n \"prompt\": \"<string>\",\n \"schema\": {},\n \"tag\": null\n },\n \"formats\": [\n \"markdown\"\n ]\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."
}Remarque : Une nouvelle version v2 de cette API est désormais disponible, avec des fonctionnalités améliorées et de meilleures performances.
Autorisations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Corps
application/json
Les URL à partir desquelles extraire les données. Les URL doivent utiliser le format glob.
Lorsque la valeur est définie sur true, l’extraction utilisera la recherche sur le Web pour trouver des données supplémentaires
Si des URL non valides sont spécifiées dans le tableau urls, elles seront ignorées. Au lieu de faire échouer toute la requête, une extraction sera effectuée à partir des URL valides restantes, et les URL non valides seront renvoyées dans le champ invalidURLs de la réponse.
Lorsque cette option est à true, les fichiers sitemap.xml sont ignorés lors de l’analyse du site web
Si activé, les sous-domaines des URL fournies seront également explorés
Prompt guidant le processus d’extraction
Schéma qui définit la structure des données extraites. Doit être conforme à la spécification JSON Schema.
Show child attributes
Show child attributes
Lorsque cette option est définie sur true, les sources utilisées pour extraire les données seront incluses dans la réponse sous la clé sources.
Dérogation par requête à la Protection contre les menaces. Les champs que vous fournissez remplacent les champs correspondants de la politique de votre organisation pour cette requête uniquement ; les champs omis conservent leurs valeurs définies au niveau de l’organisation. La Protection contre les menaces doit être activée pour votre équipe (fonctionnalité Enterprise) — sinon, la requête est rejetée avec un code 403. Si votre organisation a désactivé les dérogations par requête, toute requête incluant cet objet est rejetée avec un code 403. Si la Protection contre les menaces est imposée pour votre équipe, mode ne peut pas être défini sur off.
Show child attributes
Show child attributes
Réponse
Extraction réussie
⌘I