curl --request POST \
--url https://api.croma.run/global/extract/markdown/v1 \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"url": "https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304"
}
'import requests
url = "https://api.croma.run/global/extract/markdown/v1"
payload = { "url": "https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304" }
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({url: 'https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304'})
};
fetch('https://api.croma.run/global/extract/markdown/v1', 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.croma.run/global/extract/markdown/v1",
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([
'url' => 'https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304'
]),
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.croma.run/global/extract/markdown/v1"
payload := strings.NewReader("{\n \"url\": \"https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304\"\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.croma.run/global/extract/markdown/v1")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.croma.run/global/extract/markdown/v1")
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 \"url\": \"https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304\"\n}"
response = http.request(request)
puts response.read_body{
"data": {
"url": "<string>",
"markdown": "<string>",
"metadata": {
"title": "<string>",
"description": "<string>",
"author": "<string>",
"site_name": "<string>",
"published_at": "<string>",
"modified_at": "<string>",
"image": "<string>",
"keywords": [
"<string>"
],
"page_count": 123
}
}
}{
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"details": {}
}
}{
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"details": {}
}
}{
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"details": {}
}
}{
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"details": {}
}
}{
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"details": {}
}
}{
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"details": {}
}
}Turn any public web page into clean Markdown. scope keeps either the article body or the whole page, and include_metadata adds the page’s title, author and dates. Handles pages that render themselves in the browser at effort: max.
curl --request POST \
--url https://api.croma.run/global/extract/markdown/v1 \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"url": "https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304"
}
'import requests
url = "https://api.croma.run/global/extract/markdown/v1"
payload = { "url": "https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304" }
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({url: 'https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304'})
};
fetch('https://api.croma.run/global/extract/markdown/v1', 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.croma.run/global/extract/markdown/v1",
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([
'url' => 'https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304'
]),
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.croma.run/global/extract/markdown/v1"
payload := strings.NewReader("{\n \"url\": \"https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304\"\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.croma.run/global/extract/markdown/v1")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.croma.run/global/extract/markdown/v1")
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 \"url\": \"https://www.funcionpublica.gov.co/eva/gestornormativo/norma.php?i=304\"\n}"
response = http.request(request)
puts response.read_body{
"data": {
"url": "<string>",
"markdown": "<string>",
"metadata": {
"title": "<string>",
"description": "<string>",
"author": "<string>",
"site_name": "<string>",
"published_at": "<string>",
"modified_at": "<string>",
"image": "<string>",
"keywords": [
"<string>"
],
"page_count": 123
}
}
}{
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"details": {}
}
}{
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"details": {}
}
}{
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"details": {}
}
}{
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"details": {}
}
}{
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"details": {}
}
}{
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"details": {}
}
}Authorizations
Use Authorization: Bearer YOUR_API_KEY
Body
Public http or https URL of the page to read. Loopback and private addresses are not accepted.
2000main keeps the article body and drops navigation and boilerplate; full keeps the whole page.
main, full Effort to spend on the page: min is fastest, standard is the balanced default, max handles pages that render themselves in the browser.
min, standard, max Optional ISO 3166-1 alpha-2 country code (e.g. CO) for pages that serve different content by country. Omit for the default route.
^([A-Za-z]{2})?$Include the page's title, author, dates and other metadata in the response.
Response
Successful response
Show child attributes
Show child attributes