# CV & Resume Parser (VerbatimCV) (`verbatimcv/verbatimcv-cv-parser`) Actor

Parse CVs and resumes (PDF or DOCX links) into versioned JSON: candidate, experience, skills and preferences, each preference with the exact quote it came from. Hidden prompt injection removed.

- **URL**: https://apify.com/verbatimcv/verbatimcv-cv-parser.md
- **Developed by:** [Thomas Waye](https://apify.com/verbatimcv) (community)
- **Features:** Limited permissions
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-usage

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## CV & Resume Parser (VerbatimCV)

Turn CV and resume links (PDF or DOCX) into clean, versioned JSON that an AI agent or automation can
act on. Built on the [VerbatimCV API](https://verbatimcv.com).

### What you get for each CV

- **Candidate and contact details**: name, email, phone in E.164, location normalised next to the raw text.
- **Experience and education** with dates parsed by code. A year-only date stays a year; ambiguous day/month order is flagged.
- **Preferences with quotes**: work arrangement (remote, hybrid, onsite), engagement type, availability and notice period, compensation, timezone, working hours, relocation and right to work. Each is `stated`, `inferred` or `absent`, with a confidence and the **exact quote from the CV**.
- **Skills, certifications and spoken languages**, plus total months of experience and seniority, each with the method used.
- **Safety**: hidden white text and prompt injection aimed at AI screeners are removed before extraction and reported. Age, date of birth, gender, photos, marital status and nationality are never returned.
- **`agent_guidance.confirm_before_acting`**: the fields worth checking with a person before acting.

Nothing is invented: if the CV doesn't say something, the value is `null`.

### How to use it

1. Get a free VerbatimCV API key at https://api.verbatimcv.com/account?ref=apify (50 parses a month, no card).
2. Paste the key into **VerbatimCV API key** and add one or more public `https://` links to CVs.
3. Run. Each CV becomes one dataset item; export as JSON, CSV or Excel, or connect the dataset to your ATS, Airtable, Zapier or Make.

Try it with the prefilled sample CV (a fictional candidate).

### Output

Each item is the [VerbatimCV ParseResult](https://verbatimcv.com/docs/schema) plus `input_url`. If a
CV can't be parsed, the item has `input_url` and `error` (`code` and `message`), for example
`UNSUPPORTED_FORMAT` or `URL_FETCH_FAILED`; see [error codes](https://verbatimcv.com/docs/parse#errors).

```json
"work_arrangement": {
  "value": ["remote"],
  "source": "stated",
  "confidence": 0.95,
  "evidence": "Remote only"
}
```

### Limits

- PDF and DOCX only, up to 10 MB and 20 pages. Scans are OCR'd.
- Links must be public `https://` URLs.
- Most CVs take 5–10 seconds. The free plan allows 5 parses a minute; the Actor waits when it hits the limit.

### Privacy

VerbatimCV does not store CVs or results. Extraction uses Anthropic's API, which deletes API data
within 30 days and does not train on it.

# Actor input Schema

## `cvUrls` (type: `array`):

Public https:// links to CVs or resumes (PDF or DOCX, up to 10 MB and 20 pages). One result per link.

## `apiKey` (type: `string`):

Your key (starts with vcv\_). Get one free, 50 parses a month with no card, at https://api.verbatimcv.com/account?ref=apify

## Actor input object example

```json
{
  "cvUrls": [
    "https://verbatimcv.com/samples/sample-cv-remote-contractor.pdf"
  ]
}
```

# Actor output Schema

## `overview` (type: `string`):

One row per CV link: candidate, preferences with their verbatim quotes, experience and seniority, what to confirm before acting, and any error.

## `results` (type: `string`):

The complete VerbatimCV ParseResult for each CV link, plus input_url and error. Schema: https://verbatimcv.com/docs/schema

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "cvUrls": [
        "https://verbatimcv.com/samples/sample-cv-remote-contractor.pdf"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("verbatimcv/verbatimcv-cv-parser").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "cvUrls": ["https://verbatimcv.com/samples/sample-cv-remote-contractor.pdf"] }

# Run the Actor and wait for it to finish
run = client.actor("verbatimcv/verbatimcv-cv-parser").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "cvUrls": [
    "https://verbatimcv.com/samples/sample-cv-remote-contractor.pdf"
  ]
}' |
apify call verbatimcv/verbatimcv-cv-parser --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,verbatimcv/verbatimcv-cv-parser"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/Oh0K2FwbXjTb9Vgqk/builds/3ifZABVE9JXb3rr2Q/openapi.json
