Tools
Scrape web API
Cost: 1 credit (non-proxy)
Cost: 2 credits (proxy)
Cost: 2 credits (proxy)
POST
/
scrape
/
web
cURL
curl --request POST \
--url https://api.workfloo.ws/v0/scrape/web \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"url": "https://workfloows.com",
"proxy": {
"enabled": false
},
"output": {
"html": false,
"markdown": false,
"links": false
}
}
'import requests
url = "https://api.workfloo.ws/v0/scrape/web"
payload = {
"url": "https://workfloows.com",
"proxy": { "enabled": False },
"output": {
"html": False,
"markdown": False,
"links": False
}
}
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({
url: 'https://workfloows.com',
proxy: {enabled: false},
output: {html: false, markdown: false, links: false}
})
};
fetch('https://api.workfloo.ws/v0/scrape/web', 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.workfloo.ws/v0/scrape/web",
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://workfloows.com',
'proxy' => [
'enabled' => false
],
'output' => [
'html' => false,
'markdown' => false,
'links' => false
]
]),
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://api.workfloo.ws/v0/scrape/web"
payload := strings.NewReader("{\n \"url\": \"https://workfloows.com\",\n \"proxy\": {\n \"enabled\": false\n },\n \"output\": {\n \"html\": false,\n \"markdown\": false,\n \"links\": false\n }\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://api.workfloo.ws/v0/scrape/web")
.header("x-api-key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"https://workfloows.com\",\n \"proxy\": {\n \"enabled\": false\n },\n \"output\": {\n \"html\": false,\n \"markdown\": false,\n \"links\": false\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.workfloo.ws/v0/scrape/web")
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 \"url\": \"https://workfloows.com\",\n \"proxy\": {\n \"enabled\": false\n },\n \"output\": {\n \"html\": false,\n \"markdown\": false,\n \"links\": false\n }\n}"
response = http.request(request)
puts response.read_body{
"response": {
"success": true,
"proxy_used": false
},
"results": {
"text": "Page content..."
}
}Scrapes textual content from a given public website URL.
Allows optional proxying and multiple output formats: HTML, Markdown, or link extraction.
Requires a valid API key.
Non-proxy scrape
When proxying is not enabled, scraping is performed using standard data center IPs. Some websites may block such traffic. If proxy is disabled, theresponse includes:
"response": {
"success": true,
"proxy_used": false
}
Proxy scrape
When proxying is enabled, the scraper follows these steps:- Attempts a regular (non-proxy) scrape.
- If access is blocked, it retries using a proxy.
- If a CAPTCHA is detected, it attempts to solve it.
- The final result is returned to the client.
response includes additional diagnostic information:
"response": {
"success": true,
"proxy_used": true,
"bot_detected": true,
"captcha_detected": true,
"captcha_solved": true
}
Authorizations
Body
application/json
Was this page helpful?
⌘I
Cost: 1 credit (non-proxy)
Cost: 2 credits (proxy)
Cost: 2 credits (proxy)
cURL
curl --request POST \
--url https://api.workfloo.ws/v0/scrape/web \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"url": "https://workfloows.com",
"proxy": {
"enabled": false
},
"output": {
"html": false,
"markdown": false,
"links": false
}
}
'import requests
url = "https://api.workfloo.ws/v0/scrape/web"
payload = {
"url": "https://workfloows.com",
"proxy": { "enabled": False },
"output": {
"html": False,
"markdown": False,
"links": False
}
}
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({
url: 'https://workfloows.com',
proxy: {enabled: false},
output: {html: false, markdown: false, links: false}
})
};
fetch('https://api.workfloo.ws/v0/scrape/web', 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.workfloo.ws/v0/scrape/web",
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://workfloows.com',
'proxy' => [
'enabled' => false
],
'output' => [
'html' => false,
'markdown' => false,
'links' => false
]
]),
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://api.workfloo.ws/v0/scrape/web"
payload := strings.NewReader("{\n \"url\": \"https://workfloows.com\",\n \"proxy\": {\n \"enabled\": false\n },\n \"output\": {\n \"html\": false,\n \"markdown\": false,\n \"links\": false\n }\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://api.workfloo.ws/v0/scrape/web")
.header("x-api-key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"https://workfloows.com\",\n \"proxy\": {\n \"enabled\": false\n },\n \"output\": {\n \"html\": false,\n \"markdown\": false,\n \"links\": false\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.workfloo.ws/v0/scrape/web")
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 \"url\": \"https://workfloows.com\",\n \"proxy\": {\n \"enabled\": false\n },\n \"output\": {\n \"html\": false,\n \"markdown\": false,\n \"links\": false\n }\n}"
response = http.request(request)
puts response.read_body{
"response": {
"success": true,
"proxy_used": false
},
"results": {
"text": "Page content..."
}
}