Movatterモバイル変換


[0]ホーム

URL:


Skip to main content
OurBuilding Ambient Agents with LangGraph course is now available on LangChain Academy!
Open In ColabOpen on GitHub

DataForSEO

DataForSeo provides comprehensive SEO and digital marketing data solutions via API.

TheDataForSeo API retrievesSERP from the most popular search engines likeGoogle,Bing,Yahoo. It also allows to >get SERPs from different search engine types likeMaps,News,Events, etc.

This notebook demonstrates how to use theDataForSeo API to obtain search engine results.

%pip install--upgrade--quiet langchain-community
from langchain_community.utilities.dataforseo_api_searchimport DataForSeoAPIWrapper
API Reference:DataForSeoAPIWrapper

Setting up the API credentials

You can obtain your API credentials by registering on theDataForSeo website.

import os

os.environ["DATAFORSEO_LOGIN"]="your_api_access_username"
os.environ["DATAFORSEO_PASSWORD"]="your_api_access_password"

wrapper= DataForSeoAPIWrapper()

The run method will return the first result snippet from one of the following elements: answer_box, knowledge_graph, featured_snippet, shopping, organic.

wrapper.run("Weather in Los Angeles")

The Difference Betweenrun andresults

run andresults are two methods provided by theDataForSeoAPIWrapper class.

Therun method executes the search and returns the first result snippet from the answer box, knowledge graph, featured snippet, shopping, or organic results. These elements are sorted by priority from highest to lowest.

Theresults method returns a JSON response configured according to the parameters set in the wrapper. This allows for more flexibility in terms of what data you want to return from the API.

Getting Results as JSON

You can customize the result types and fields you want to return in the JSON response. You can also set a maximum count for the number of top results to return.

json_wrapper= DataForSeoAPIWrapper(
json_result_types=["organic","knowledge_graph","answer_box"],
json_result_fields=["type","title","description","text"],
top_count=3,
)
json_wrapper.results("Bill Gates")

Customizing Location and Language

You can specify the location and language of your search results by passing additional parameters to the API wrapper.

customized_wrapper= DataForSeoAPIWrapper(
top_count=10,
json_result_types=["organic","local_pack"],
json_result_fields=["title","description","type"],
params={"location_name":"Germany","language_code":"en"},
)
customized_wrapper.results("coffee near me")

Customizing the Search Engine

You can also specify the search engine you want to use.

customized_wrapper= DataForSeoAPIWrapper(
top_count=10,
json_result_types=["organic","local_pack"],
json_result_fields=["title","description","type"],
params={"location_name":"Germany","language_code":"en","se_name":"bing"},
)
customized_wrapper.results("coffee near me")

Customizing the Search Type

The API wrapper also allows you to specify the type of search you want to perform. For example, you can perform a maps search.

maps_search= DataForSeoAPIWrapper(
top_count=10,
json_result_fields=["title","value","address","rating","type"],
params={
"location_coordinate":"52.512,13.36,12z",
"language_code":"en",
"se_type":"maps",
},
)
maps_search.results("coffee near me")

Integration with Langchain Agents

You can use theTool class from thelangchain.agents module to integrate theDataForSeoAPIWrapper with a langchain agent. TheTool class encapsulates a function that the agent can call.

from langchain_core.toolsimport Tool

search= DataForSeoAPIWrapper(
top_count=3,
json_result_types=["organic"],
json_result_fields=["title","description","type"],
)
tool= Tool(
name="google-search-answer",
description="My new answer tool",
func=search.run,
)
json_tool= Tool(
name="google-search-json",
description="My new json tool",
func=search.results,
)
API Reference:Tool

Related


[8]ページ先頭

©2009-2025 Movatter.jp