Ahrefs Research

Ahrefs SEO Research

Overview

The Ahrefs API provides programmatic access to Ahrefs SEO data. The official Python SDK (ahrefs-python) provides typed request and response models for all endpoints, auto-generated from the OpenAPI spec.

Key capabilities:

• Site Explorer - Backlinks, organic keywords, domain rating, traffic, referring domains
• Keywords Explorer - Keyword research, volumes, difficulty, related terms
• Rank Tracker - SERP monitoring, competitor tracking
• Site Audit - Technical SEO issues, page content, page explorer
• Brand Radar - AI brand mentions, share of voice, impressions
• SERP Overview - Search result analysis
• Batch Analysis - Bulk domain/URL metrics via POST

Installation

pip3 install git+https://github.com/ahrefs/ahrefs-python.git

Requires Python 3.11+. Dependencies: httpx, pydantic.

API Method Discovery

The SDK has 52 methods across 7 API sections. The built-in search tool is the fastest way to find the right method -- it returns matching method signatures, parameters, and return types directly, so there's no need to scan through a large reference.

Python (preferred when already in a Python context):

from ahrefs.search import search_api_methods

# Returns formatted text with method signatures, parameters, and return types
print(search_api_methods("domain rating"))

# Filter by API section and limit results
print(search_api_methods("backlinks", section="site-explorer", limit=3))

CLI (preferred when exploring from the terminal):

# Ensure python3 points to the interpreter where ahrefs-python is installed:
#   which python3
#   python3 -c "import ahrefs"
python3 -m ahrefs.api_search "domain rating"
python3 -m ahrefs.api_search "backlinks" --section site-explorer --limit 3
python3 -m ahrefs.api_search "batch" --json
python3 -m ahrefs.api_search --sections  # list all API sections

IMPORTANT RULES

• ALWAYS use the ahrefs-python SDK. DO NOT make raw httpx/requests calls to the Ahrefs API.
• ALWAYS pass dates as strings in YYYY-MM-DD format (e.g. "2025-01-15").
• ALWAYS use select on list endpoints to request only the columns you need. List endpoints return all columns by default, which wastes API units and increases response size.
• USE context managers (with / async with) for client lifecycle management.
• NEVER hardcode API keys in source code. Use the AHREFS_API_KEY environment variable or your preferred secrets mechanism.
• The client handles retries (429, 5xx, connection errors) automatically. DO NOT implement your own retry logic on top of the SDK.

Quick Start

import os
from ahrefs import AhrefsClient

with AhrefsClient(api_key=os.environ["AHREFS_API_KEY"]) as client:
    data = client.site_explorer_domain_rating(target="ahrefs.com", date="2025-01-15")
    print(data.domain_rating)  # 91.0
    print(data.ahrefs_rank)    # 3

SDK Patterns

Client Setup

import os
import ahrefs

with ahrefs.AhrefsClient(
    api_key=os.environ["AHREFS_API_KEY"],  # or any secrets source
    base_url="...",          # override API base URL (default: https://api.ahrefs.com/v3)
    timeout=30.0,            # request timeout in seconds (default: 60)
    max_retries=3,           # retries on transient errors (default: 2)
) as client:
    ...

Async client:

import os
from ahrefs import AsyncAhrefsClient

async with AsyncAhrefsClient(api_key=os.environ["AHREFS_API_KEY"]) as client:
    data = await client.site_explorer_domain_rating(target="ahrefs.com", date="2025-01-15")

For parallel calls, use asyncio.gather:

import asyncio

async with AsyncAhrefsClient(api_key=os.environ["AHREFS_API_KEY"]) as client:
    dr_ahrefs, dr_moz = await asyncio.gather(
        client.site_explorer_domain_rating(target="ahrefs.com", date="2025-01-15"),
        client.site_explorer_domain_rating(target="moz.com", date="2025-01-15"),
    )

Calling Methods

Two calling styles -- both are equivalent:

# Keyword arguments (recommended)
data = client.site_explorer_domain_rating(target="ahrefs.com", date="2025-01-15")

# Request objects (full type safety)
from ahrefs.types import SiteExplorerDomainRatingRequest
request = SiteExplorerDomainRatingRequest(target="ahrefs.com", date="2025-01-15")
data = client.site_explorer_domain_rating(request)

Method names follow {api_section}_{endpoint}, e.g. site_explorer_organic_keywords, keywords_explorer_overview.

Responses

Methods return typed Data objects directly.

Scalar endpoints return a single data object (or None):

data = client.site_explorer_domain_rating(target="ahrefs.com", date="2025-01-15")
print(data.domain_rating)

List endpoints return a list of data objects. There is no pagination -- set limit to the number of results you need. Use select to request only the columns you need:

items = client.site_explorer_organic_keywords(
    target="ahrefs.com",
    date="2025-01-15",
    select="keyword,volume,best_position",
    order_by="volume:desc",
    limit=10,
)
for item in items:
    print(item.keyword, item.volume, item.best_position)

Error Handling

import ahrefs

try:
    data = client.site_explorer_domain_rating(target="example.com", date="2025-01-15")
except ahrefs.AuthenticationError:    # 401
    ...
except ahrefs.RateLimitError as e:    # 429 -- e.retry_after has the delay
    ...
except ahrefs.NotFoundError:          # 404
    ...
except ahrefs.APIError as e:          # other 4xx/5xx -- e.status_code, e.response_body
    ...
except ahrefs.APIConnectionError:     # network / timeout
    ...

All exceptions inherit from ahrefs.AhrefsError.

Common Parameters

Most list endpoints share these parameters:

Parameters typed as enums in the API reference (CountryEnum, VolumeModeEnum, etc.) accept plain strings -- pass country="us" not CountryEnum("us").

The where parameter takes a JSON string. Use json.dumps() to build it:

import json
where = json.dumps({"field": "volume", "is": ["gte", 1000]})
items = client.site_explorer_organic_keywords(
    target="ahrefs.com", date="2025-01-15",
    select="keyword,volume", where=where,
)

For full filter syntax (boolean combinators, operators, nested fields), see references/filter-syntax.md.

API Methods

Use search_api_methods("query") or python3 -m ahrefs.api_search "query" to find methods by keyword. Search covers all 52 methods across 7 API sections and returns complete signatures, parameters, and response fields.

Filter syntax

Some API endpoints accept a where parameter, which applies a filter to the result set.

The following sections give some examples of filter usage and a full syntax reference.

Examples

For more real world examples, try applying some filters to a report on ahrefs.com using our visual interface, and then press the API {} button to view the where parameter of the generated API v3 query.

Field "foo" equals 3:

{ "field": "foo", "is": ["eq", 3] }

For fields of type object, use dot notation to refer to nested fields. Field "bar", nested under field "foo", equals 3:

{ "field": "foo.bar", "is": ["eq", 3] }

The integer field "foo" equals 3 and the integer field "bar" is less than 10:

{
    "and": [
        { "field": "foo", "is": ["eq", 3] },
        { "field": "bar", "is": ["lt", 10] }
    ]
}

Either the uppercased value of the string field "foo" equals "AHREFS", or all string elements in the array field "bar" have the prefix "Ahrefs" and suffix "seo".

{
  "or": [
    {
      "field": "foo",
      "modifier": "uppercase",
      "is": ["eq", "AHREFS"]
    },
    {
      "field": "bar",
      "list_is": {
        "and": [
          ["prefix", "Ahrefs"],
          ["suffix", "seo"],
        ]
      }
    }
  ]
}

Language reference

The filter syntax is described by the following grammar, expressed in BNF-style notation.

A term enclosed in angle brackets < and > denotes a symbol. A symbol followed by a + denotes a non-empty array containing the symbol. A ? preceding an object field indicates that the field is optional.

The two terminal symbols are defined as follows:

• <field_alias> A filter field alias. See the particular endpoint's documentation for the list of valid aliases. Note that the select and where parameters may accept different aliases.
• <value> A JSON value. It should match the type of the field (or of the field's modifier, if one is present).

Permitted patterns in regex filter expressions differs by tool.

• Keywords Explorer: Only * as a wildcard operator.
• Site Explorer: RE2 syntax.

<bool_filter> ::= { "and" : <bool_filter>+ }
              |   { "or" : <bool_filter>+ }
              |   { "not" : <bool_filter> }
              |   <expr>

<expr> ::= {
             "field" : <field_alias>,
             ? "is": <condition>,
             ? "list_is": <list_condition>
           }

<condition> ::= [ "eq", <value> ]
            |   [ "neq", <value> ]
            |   [ "gt", <value> ]
            |   [ "gte", <value> ]
            |   [ "lt", <value> ]
            |   [ "lte", <value> ]
            |   [ "substring", <value> ]
            |   [ "isubstring", <value> ]
            |   [ "phrase_match", <value> ]
            |   [ "iphrase_match", <value> ]
            |   [ "prefix", <value> ]
            |   [ "suffix", <value> ]
            |   [ "regex", <value> ]
            |   "empty"
            |   "is_null"

<condition_bool_filter> ::= { "and" : <condition_bool_filter>+ }
                        |   { "or" : <condition_bool_filter>+ }
                        |   { "not" : <condition_bool_filter> }
                        |   <condition>

<list_condition> ::= { "any" : <condition_bool_filter> }
                 |   { "all" : <condition_bool_filter> }