Create an extract run
curl --request POST \
--url https://bulkgrid.com/api/v1/extract \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"type": "extract",
"urls": [
"<string>"
],
"query": "<string>",
"schema": {},
"maxRetries": 3
}
'import requests
url = "https://bulkgrid.com/api/v1/extract"
payload = {
"type": "extract",
"urls": ["<string>"],
"query": "<string>",
"schema": {},
"maxRetries": 3
}
headers = {
"x-api-key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
type: 'extract',
urls: ['<string>'],
query: '<string>',
schema: {},
maxRetries: 3
})
};
fetch('https://bulkgrid.com/api/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://bulkgrid.com/api/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([
'type' => 'extract',
'urls' => [
'<string>'
],
'query' => '<string>',
'schema' => [
],
'maxRetries' => 3
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-api-key: <api-key>"
],
]);
$response = curl_exec($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://bulkgrid.com/api/v1/extract"
payload := strings.NewReader("{\n \"type\": \"extract\",\n \"urls\": [\n \"<string>\"\n ],\n \"query\": \"<string>\",\n \"schema\": {},\n \"maxRetries\": 3\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-api-key", "<api-key>")
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://bulkgrid.com/api/v1/extract")
.header("x-api-key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"type\": \"extract\",\n \"urls\": [\n \"<string>\"\n ],\n \"query\": \"<string>\",\n \"schema\": {},\n \"maxRetries\": 3\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://bulkgrid.com/api/v1/extract")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"type\": \"extract\",\n \"urls\": [\n \"<string>\"\n ],\n \"query\": \"<string>\",\n \"schema\": {},\n \"maxRetries\": 3\n}"
response = http.request(request)
puts response.read_body{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"completed_at": "<string>",
"config": null,
"created_at": "<string>",
"credential_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"done": 0,
"error_code": "<string>",
"error_count": 0,
"error_details": null,
"extraction_query": "<string>",
"extraction_schema": null,
"failed": 0,
"in_progress": 0,
"inline_credentials": null,
"indexing_completed_at": "<string>",
"indexing_started_at": "<string>",
"indexing_time_ms": 0,
"last_error": "<string>",
"last_error_at": "<string>",
"last_heartbeat": "<string>",
"max_retries": 0,
"message_ids": [
"<string>"
],
"metadata": null,
"needs_dispatch": true,
"priority": 0,
"processing_time_ms": 0,
"query": "<string>",
"queued": 0,
"requested_by_user_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"retry_count": 0,
"started_at": "<string>",
"status": "pending",
"workspace_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"type": "crawl",
"updated_at": "<string>",
"urls": [
"<string>"
],
"indexed_pages": 0,
"indexing_done": 0,
"indexing_failed": 0,
"indexing_failed_pages": 0,
"indexing_in_progress": 0,
"indexing_queued": 0,
"deletion_requested_at": "<string>"
}{
"error": "<string>",
"details": "<unknown>"
}{
"error": "<string>",
"details": "<unknown>"
}{
"error": "<string>",
"details": "<unknown>"
}{
"error": "<string>",
"details": "<unknown>"
}{
"error": "<string>",
"details": "<unknown>"
}{
"error": "<string>",
"details": "<unknown>"
}Runs
Create an extract run
Required permission: extract:write.
POST
/
api
/
v1
/
extract
Create an extract run
curl --request POST \
--url https://bulkgrid.com/api/v1/extract \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"type": "extract",
"urls": [
"<string>"
],
"query": "<string>",
"schema": {},
"maxRetries": 3
}
'import requests
url = "https://bulkgrid.com/api/v1/extract"
payload = {
"type": "extract",
"urls": ["<string>"],
"query": "<string>",
"schema": {},
"maxRetries": 3
}
headers = {
"x-api-key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
type: 'extract',
urls: ['<string>'],
query: '<string>',
schema: {},
maxRetries: 3
})
};
fetch('https://bulkgrid.com/api/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://bulkgrid.com/api/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([
'type' => 'extract',
'urls' => [
'<string>'
],
'query' => '<string>',
'schema' => [
],
'maxRetries' => 3
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-api-key: <api-key>"
],
]);
$response = curl_exec($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://bulkgrid.com/api/v1/extract"
payload := strings.NewReader("{\n \"type\": \"extract\",\n \"urls\": [\n \"<string>\"\n ],\n \"query\": \"<string>\",\n \"schema\": {},\n \"maxRetries\": 3\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-api-key", "<api-key>")
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://bulkgrid.com/api/v1/extract")
.header("x-api-key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"type\": \"extract\",\n \"urls\": [\n \"<string>\"\n ],\n \"query\": \"<string>\",\n \"schema\": {},\n \"maxRetries\": 3\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://bulkgrid.com/api/v1/extract")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"type\": \"extract\",\n \"urls\": [\n \"<string>\"\n ],\n \"query\": \"<string>\",\n \"schema\": {},\n \"maxRetries\": 3\n}"
response = http.request(request)
puts response.read_body{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"completed_at": "<string>",
"config": null,
"created_at": "<string>",
"credential_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"done": 0,
"error_code": "<string>",
"error_count": 0,
"error_details": null,
"extraction_query": "<string>",
"extraction_schema": null,
"failed": 0,
"in_progress": 0,
"inline_credentials": null,
"indexing_completed_at": "<string>",
"indexing_started_at": "<string>",
"indexing_time_ms": 0,
"last_error": "<string>",
"last_error_at": "<string>",
"last_heartbeat": "<string>",
"max_retries": 0,
"message_ids": [
"<string>"
],
"metadata": null,
"needs_dispatch": true,
"priority": 0,
"processing_time_ms": 0,
"query": "<string>",
"queued": 0,
"requested_by_user_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"retry_count": 0,
"started_at": "<string>",
"status": "pending",
"workspace_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"type": "crawl",
"updated_at": "<string>",
"urls": [
"<string>"
],
"indexed_pages": 0,
"indexing_done": 0,
"indexing_failed": 0,
"indexing_failed_pages": 0,
"indexing_in_progress": 0,
"indexing_queued": 0,
"deletion_requested_at": "<string>"
}{
"error": "<string>",
"details": "<unknown>"
}{
"error": "<string>",
"details": "<unknown>"
}{
"error": "<string>",
"details": "<unknown>"
}{
"error": "<string>",
"details": "<unknown>"
}{
"error": "<string>",
"details": "<unknown>"
}{
"error": "<string>",
"details": "<unknown>"
}Authorizations
apiKeyAuthbearerAuth
Bulkgrid API key
Body
application/json
Available options:
extract List of URLs to extract data from
Minimum array length:
1Extraction query used to guide the extraction
Minimum string length:
1JSON schema defining the structure of data to extract
Show child attributes
Show child attributes
Maximum retry attempts for each URL
Required range:
1 <= x <= 5Response
Successful response
Pattern:
^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$Available options:
null Pattern:
^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$Required range:
-9007199254740991 <= x <= 9007199254740991Required range:
-9007199254740991 <= x <= 9007199254740991Available options:
null Available options:
null Required range:
-9007199254740991 <= x <= 9007199254740991Required range:
-9007199254740991 <= x <= 9007199254740991Available options:
null Required range:
-9007199254740991 <= x <= 9007199254740991Required range:
-9007199254740991 <= x <= 9007199254740991Available options:
null Required range:
-9007199254740991 <= x <= 9007199254740991Required range:
-9007199254740991 <= x <= 9007199254740991Required range:
-9007199254740991 <= x <= 9007199254740991Pattern:
^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$Required range:
-9007199254740991 <= x <= 9007199254740991Available options:
pending, processing, completed, failed, cancelled Pattern:
^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$Available options:
crawl, deep_crawl, extract, source_sync Required range:
-9007199254740991 <= x <= 9007199254740991Required range:
-9007199254740991 <= x <= 9007199254740991Required range:
-9007199254740991 <= x <= 9007199254740991Required range:
-9007199254740991 <= x <= 9007199254740991Required range:
-9007199254740991 <= x <= 9007199254740991Required range:
-9007199254740991 <= x <= 9007199254740991