Examples - Company Search API
Examples
We've provided code samples in Python, cURL, Ruby, Go and JavaScript. If you aren't comfortable working in any of these languages, feel free to use this handy tool to convert code from cURL to the language of your choice.
Heads Up! Credit Usage
Company Search API calls cost the number of total search results returned.
If you are making a search that could have a large number of results, make sure to use the
sizeparameter to set the maximum number of results and cap your credit usage.
See a Bug? Want To See a Specific Example?
Feel free to use the
Suggest Editsbutton in the top right-hand corner of this page to point out any bugs or to request any specific code examples for this API that you'd like to see here.
Basic Usage
"I want to make a query and save the results to a file."
import json
# See https://github.com/peopledatalabs/peopledatalabs-python
from peopledatalabs import PDLPY
# Create a client, specifying your API key
CLIENT = PDLPY(
api_key="YOUR API KEY",
)
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"term": {"website": "google.com"}}
]
}
}
}
# Create a parameters JSON object
PARAMS = {
'query': ES_QUERY,
'size': 10,
'pretty': True
}
# Pass the parameters object to the Company Search API
response = CLIENT.company.search(**PARAMS).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
print("Error:", response)
import json
# See https://github.com/peopledatalabs/peopledatalabs-python
from peopledatalabs import PDLPY
# Create a client, specifying your API key
CLIENT = PDLPY(
api_key="YOUR API KEY",
)
# Create an SQL query
SQL_QUERY = \
"""
SELECT * FROM company
WHERE website='google.com';
"""
# Create a parameters JSON object
PARAMS = {
'sql': SQL_QUERY,
'size': 10,
'pretty': True
}
# Pass the parameters object to the Company Search API
response = CLIENT.company.search(**PARAMS).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
print("Error:", response)
# Elasticsearch
curl -X GET 'https://api.peopledatalabs.com/v5/company/search' \
-H 'X-Api-Key: xxxx' \
--data-raw '{
"size": 10,
"query": {
"bool": {
"must": [
{"term": {"website": "google.com"}}
]
}
}
}'
# SQL
curl -X GET \
'https://api.peopledatalabs.com/v5/company/search' \
-H 'X-Api-Key: xxxx' \
--data-raw '{
"size": 10,
"sql": "SELECT * FROM company WHERE website='\''google.com'\'';"
}'
// See https://github.com/peopledatalabs/peopledatalabs-js
import PDLJS from 'peopledatalabs';
import fs from 'fs';
// Create a client, specifying your API key
const PDLJSClient = new PDLJS({ apiKey: "YOUR API KEY" });
// Create an Elasticsearch query
const esQuery = {
query: {
bool: {
must:[
{"term": {"website": "google.com"}}
]
}
}
}
// Create a parameters JSON object
const params = {
searchQuery: esQuery,
size: 10,
pretty: true
}
// Pass the parameters object to the Company Search API
PDLJSClient.company.search.elastic(params).then((data) => {
// Write out all profiles found to file
fs.writeFile("my_pdl_search.jsonl", Buffer.from(JSON.stringify(data.data)), (err) => {
if (err) throw err;
});
console.log(`Successfully grabbed ${data.data.length} records from PDL.`);
console.log(`${data["total"]} total PDL records exist matching this query.`)
}).catch((error) => {
console.log("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
console.log(error);
});
// See https://github.com/peopledatalabs/peopledatalabs-js
import PDLJS from 'peopledatalabs';
import fs from 'fs';
// Create a client, specifying your API key
const PDLJSClient = new PDLJS({ apiKey: "YOUR API KEY" });
// Create an SQL query
const sqlQuery = `SELECT * FROM company
WHERE website='google.com';`;
// Create a parameters JSON object
const params = {
searchQuery: sqlQuery,
size: 10,
pretty: true
}
// Pass the parameters object to the Company Search API
PDLJSClient.company.search.sql(params).then((data) => {
// Write out all profiles found to file
fs.writeFile("my_pdl_search.jsonl", Buffer.from(JSON.stringify(data.data)), (err) => {
if (err) throw err;
});
console.log(`Successfully grabbed ${data.data.length} records from PDL.`);
console.log(`${data["total"]} total PDL records exist matching this query.`)
}).catch((error) => {
console.log("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
console.log(error);
});
require 'json'
# See https://github.com/peopledatalabs/peopledatalabs-ruby
require 'peopledatalabs'
# Set your API key
Peopledatalabs.api_key = 'YOUR API KEY'
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"term": {"website": "google.com"}},
]
}
}
}
# Pass parameters to the Company Search API
response = Peopledatalabs::Search.company(searchType: 'elastic', query: ES_QUERY, size: 10, pretty: true)
# Check for successful response
if response['status'] == 200
data = response['data']
# Write out each profile found to file
File.open("my_pdl_search.jsonl", "w") do |out|
data.each { |record| out.write(JSON.dump(record) + "\n") }
end
puts "Successfully grabbed #{data.length()} records from PDL."
puts "#{response['total']} total PDL records exist matching this query."
else
puts "NOTE: The carrier pigeons lost motivation in flight. See error and try again."
puts "Error: #{response}"
end
require 'json'
# See https://github.com/peopledatalabs/peopledatalabs-ruby
require 'peopledatalabs'
# Set your API key
Peopledatalabs.api_key = 'YOUR API KEY'
# Create an SQL query
SQL_QUERY = \
"""
SELECT * FROM company
WHERE website='google.com';
"""
# Pass parameters to the Company Search API
response = Peopledatalabs::Search.company(searchType: 'sql', query: SQL_QUERY, size: 10, pretty: true)
# Check for successful response
if response['status'] == 200
data = response['data']
# Write out each profile found to file
File.open("my_pdl_search.jsonl", "w") do |out|
data.each { |record| out.write(JSON.dump(record) + "\n") }
end
puts "Successfully grabbed #{data.length()} records from PDL."
puts "#{response['total']} total PDL records exist matching this query."
else
puts "NOTE: The carrier pigeons lost motivation in flight. See error and try again."
puts "Error: #{response}"
end
package main
import(
"fmt"
"os"
"encoding/json"
"context"
)
// See https://github.com/peopledatalabs/peopledatalabs-go
import (
pdl "github.com/peopledatalabs/peopledatalabs-go"
pdlmodel "github.com/peopledatalabs/peopledatalabs-go/model"
)
func main() {
// Set your API key
apiKey := "YOUR API KEY"
// Set API key as environmental variable
// apiKey := os.Getenv("API_KEY")
// Create a client, specifying your API key
client := pdl.New(apiKey)
// Create an Elasticsearch query
elasticSearchQuery := map[string]interface{} {
"query": map[string]interface{} {
"bool": map[string]interface{} {
"must": []map[string]interface{} {
{"term": map[string]interface{}{"website": "google.com"}},
},
},
},
}
// Create a parameters JSON object
params := pdlmodel.SearchParams {
BaseParams: pdlmodel.BaseParams {
Size: 10,
Pretty: true,
},
SearchBaseParams: pdlmodel.SearchBaseParams {
Query: elasticSearchQuery,
},
}
// Pass the parameters object to the Company Search API
response, err := client.Company.Search(context.Background(), params)
// Check for successful response
if err == nil {
data := response.Data
// Create file
out, outErr := os.Create("my_pdl_search.jsonl")
defer out.Close()
if (outErr == nil) {
for i := range data {
// Convert each profile found to JSON
record, jsonErr := json.Marshal(data[i])
// Write out each profile to file
if (jsonErr == nil) {
out.WriteString(string(record) + "\n")
}
}
out.Sync()
}
fmt.Printf("Successfully grabbed %d records from PDL.\n", len(data))
fmt.Printf("%d total PDL records exist matching this query.\n", response.Total)
} else {
fmt.Println("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
fmt.Println("Error:", err)
}
}
package main
import(
"fmt"
"os"
"encoding/json"
"context"
)
// See https://github.com/peopledatalabs/peopledatalabs-go
import (
pdl "github.com/peopledatalabs/peopledatalabs-go"
pdlmodel "github.com/peopledatalabs/peopledatalabs-go/model"
)
func main() {
// Set your API key
apiKey := "YOUR API KEY"
// Set API key as environmental variable
// apiKey := os.Getenv("API_KEY")
// Create a client, specifying your API key
client := pdl.New(apiKey)
// Create an SQL query
sqlQuery := "SELECT * FROM company" +
" WHERE website='google.com';"
// Create a parameters JSON object
params := pdlmodel.SearchParams {
BaseParams: pdlmodel.BaseParams {
Size: 10,
Pretty: true,
},
SearchBaseParams: pdlmodel.SearchBaseParams {
SQL: sqlQuery,
},
}
// Pass the parameters object to the Company Search API
response, err := client.Company.Search(context.Background(), params)
// Check for successful response
if err == nil {
data := response.Data
// Create file
out, outErr := os.Create("my_pdl_search.jsonl")
defer out.Close()
if (outErr == nil) {
for i := range data {
// Convert each profile found to JSON
record, jsonErr := json.Marshal(data[i])
// Write out each profile to file
if (jsonErr == nil) {
out.WriteString(string(record) + "\n")
}
}
out.Sync()
}
fmt.Printf("Successfully grabbed %d records from PDL.\n", len(data))
fmt.Printf("%d total PDL records exist matching this query.\n", response.Total)
} else {
fmt.Println("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
fmt.Println("Error:", err)
}
}
import requests, json
# Set your API key
API_KEY = "YOUR API KEY"
# Set the Company Search API URL
PDL_URL = "https://api.peopledatalabs.com/v5/company/search"
# Set headers
HEADERS = {
'Content-Type': "application/json",
'X-api-key': API_KEY
}
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"term": {"website": "google.com"}}
]
}
}
}
# Create a parameters JSON object
PARAMS = {
'query': json.dumps(ES_QUERY),
'size': 10,
'pretty': True
}
# Pass the parameters object to the Company Search API
response = requests.get(
PDL_URL,
headers=HEADERS,
params=PARAMS
).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
print("Error:", response)
import requests, json
# Set your API key
API_KEY = "YOUR API KEY"
# Set the Company Search API URL
PDL_URL = "https://api.peopledatalabs.com/v5/company/search"
# Set headers
HEADERS = {
'Content-Type': "application/json",
'X-api-key': API_KEY
}
# Create an SQL query
SQL_QUERY = \
"""
SELECT * FROM company
WHERE website='google.com';
"""
# Create a parameters JSON object
PARAMS = {
'sql': SQL_QUERY,
'size': 10,
'pretty': True
}
# Pass the parameters object to the Company Search API
response = requests.get(
PDL_URL,
headers=HEADERS,
params=PARAMS
).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
print("error:", response)
Using POST Requests
"I would like to use POST requests to query instead of GET requests so that I can make queries with a lot of parameters."
Difference Between GET and POST Requests
See this article for a comparison of the differences between GET and POST requests. The biggest difference is that POST requests don't have any limit on the amount of data that you can pass in a request.
import requests, json
# Set your API key
API_KEY = "YOUR API KEY"
# Set the Company Search API URL
PDL_URL = "https://api.peopledatalabs.com/v5/company/search"
# Set headers
HEADERS = {
'Content-Type': "application/json",
'X-api-key': API_KEY
}
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"term": {"website": "google.com"}},
]
}
}
}
# Create a parameters JSON object
PARAMS = {
'query': ES_QUERY, # This is a different syntax than when using GET requests
'size': 10,
'pretty': True
}
# Pass the parameters object to the Person Search API using POST method
response = requests.post( # Using POST method
PDL_URL,
headers=HEADERS,
json=PARAMS # Pass the data directly as a JSON object
# data=json.dumps(PARAMS) # This is an alternative way of passing data using a string
).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
print("Error:", response)
import requests, json
# Set your API key
API_KEY = # YOUR API KEY
# Set the Company Search API URL
PDL_URL = "https://api.peopledatalabs.com/v5/company/search"
# Set headers
HEADERS = {
'Content-Type': "application/json",
'X-api-key': API_KEY
}
# Create an SQL query
SQL_QUERY = \
"""
SELECT * FROM company
WHERE website='google.com';
"""
# Create a parameters JSON object
PARAMS = {
'sql': SQL_QUERY,
'size': 10,
'pretty': True
}
# Pass the parameters object to the Person Search API using POST method
response = requests.post( # Using POST method
PDL_URL,
headers=HEADERS,
json=PARAMS # Pass the data directly as a JSON object
# data=json.dumps(PARAMS) # This is an alternative way of passing data using a string
).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
print("Error:", response)
# Elasticsearch
curl -X POST 'https://api.peopledatalabs.com/v5/company/search' \
-H 'X-Api-Key: xxxx' \
--data-raw '{
"size": 10,
"query": {
"bool": {
"must": [
{"term": {"website": "google.com"}}
]
}
}
}'
# SQL
curl -X POST \
'https://api.peopledatalabs.com/v5/company/search' \
-H 'X-Api-Key: xxxx' \
--data-raw '{
"size": 10,
"sql": "SELECT * FROM company WHERE website='\''google.com'\'';"
}'
Company Search by Tags
"I want to find US-based companies tagged as 'big data' in the financial services industry."
import json
# See https://github.com/peopledatalabs/peopledatalabs-python
from peopledatalabs import PDLPY
# Create a client, specifying your API key
CLIENT = PDLPY(
api_key="YOUR API KEY",
)
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"term": {"tags": "big data"}},
{"term": {"industry": "financial services"}},
{"term": {"location.country": "united states"}}
]
}
}
}
# Create a parameters JSON object
PARAMS = {
'query': ES_QUERY,
'size': 10,
'pretty': True
}
# Pass the parameters object to the Company Search API
response = CLIENT.company.search(**PARAMS).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
print("Error:", response)
import json
# See https://github.com/peopledatalabs/peopledatalabs-python
from peopledatalabs import PDLPY
# Create a client, specifying your API key
CLIENT = PDLPY(
api_key="YOUR API KEY",
)
# Create an SQL query
SQL_QUERY = \
"""
SELECT * FROM company
WHERE tags='big data'
AND industry='financial services'
AND location.country='united states';
"""
# Create a parameters JSON object
PARAMS = {
'sql': SQL_QUERY,
'size': 10,
'pretty': True
}
# Pass the parameters object to the Company Search API
response = CLIENT.company.search(**PARAMS).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
print("Error:", response)
// See https://github.com/peopledatalabs/peopledatalabs-js
import PDLJS from 'peopledatalabs';
import fs from 'fs';
// Create a client, specifying your API key
const PDLJSClient = new PDLJS({ apiKey: "YOUR API KEY" });
// Create an Elasticsearch query
const esQuery = {
query: {
bool: {
must:[
{"term": {"tags": "big data"}},
{"term": {"industry": "financial services"}},
{"term": {"location.country": "united states"}}
]
}
}
}
// Create a parameters JSON object
const params = {
searchQuery: esQuery,
size: 10,
pretty: true
}
// Pass the parameters object to the Company Search API
PDLJSClient.company.search.elastic(params).then((data) => {
// Write out all profiles found to file
fs.writeFile("my_pdl_search.jsonl", Buffer.from(JSON.stringify(data.data)), (err) => {
if (err) throw err;
});
console.log(`Successfully grabbed ${data.data.length} records from PDL.`);
console.log(`${data["total"]} total PDL records exist matching this query.`)
}).catch((error) => {
console.log("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
console.log(error);
});
// See https://github.com/peopledatalabs/peopledatalabs-js
import PDLJS from 'peopledatalabs';
import fs from 'fs';
// Create a client, specifying your API key
const PDLJSClient = new PDLJS({ apiKey: "YOUR API KEY" });
// Create an SQL query
const sqlQuery = `SELECT * FROM company
WHERE tags='big data'
AND industry='financial services'
AND location.country='united states';`;
// Create a parameters JSON object
const params = {
searchQuery: sqlQuery,
size: 10,
pretty: true
}
// Pass the parameters object to the Company Search API
PDLJSClient.company.search.sql(params).then((data) => {
// Write out all profiles found to file
fs.writeFile("my_pdl_search.jsonl", Buffer.from(JSON.stringify(data.data)), (err) => {
if (err) throw err;
});
console.log(`Successfully grabbed ${data.data.length} records from PDL.`);
console.log(`${data["total"]} total PDL records exist matching this query.`)
}).catch((error) => {
console.log("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
console.log(error);
});
require 'json'
# See https://github.com/peopledatalabs/peopledatalabs-ruby
require 'peopledatalabs'
# Set your API key
Peopledatalabs.api_key = 'YOUR API KEY'
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"term": {"tags": "big data"}},
{"term": {"industry": "financial services"}},
{"term": {"location.country": "united states"}}
]
}
}
}
# Pass parameters to the Company Search API
response = Peopledatalabs::Search.company(searchType: 'elastic', query: ES_QUERY, size: 10, pretty: true)
# Check for successful response
if response['status'] == 200
data = response['data']
# Write out each profile found to file
File.open("my_pdl_search.jsonl", "w") do |out|
data.each { |record| out.write(JSON.dump(record) + "\n") }
end
puts "Successfully grabbed #{data.length()} records from PDL."
puts "#{response['total']} total PDL records exist matching this query."
else
puts "NOTE: The carrier pigeons lost motivation in flight. See error and try again."
puts "Error: #{response}"
end
require 'json'
# See https://github.com/peopledatalabs/peopledatalabs-ruby
require 'peopledatalabs'
# Set your API key
Peopledatalabs.api_key = 'YOUR API KEY'
# Create an SQL query
SQL_QUERY = \
"""
SELECT * FROM company
WHERE tags='big data'
AND industry='financial services'
AND location.country='united states';
"""
# Pass parameters to the Company Search API
response = Peopledatalabs::Search.company(searchType: 'sql', query: SQL_QUERY, size: 10, pretty: true)
# Check for successful response
if response['status'] == 200
data = response['data']
# Write out each profile found to file
File.open("my_pdl_search.jsonl", "w") do |out|
data.each { |record| out.write(JSON.dump(record) + "\n") }
end
puts "Successfully grabbed #{data.length()} records from PDL."
puts "#{response['total']} total PDL records exist matching this query."
else
puts "NOTE: The carrier pigeons lost motivation in flight. See error and try again."
puts "Error: #{response}"
end
package main
import(
"fmt"
"os"
"encoding/json"
"context"
)
// See https://github.com/peopledatalabs/peopledatalabs-go
import (
pdl "github.com/peopledatalabs/peopledatalabs-go"
pdlmodel "github.com/peopledatalabs/peopledatalabs-go/model"
)
func main() {
// Set your API key
apiKey := "YOUR API KEY"
// Set API key as environmental variable
// apiKey := os.Getenv("API_KEY")
// Create a client, specifying your API key
client := pdl.New(apiKey)
// Create an Elasticsearch query
elasticSearchQuery := map[string]interface{} {
"query": map[string]interface{} {
"bool": map[string]interface{} {
"must": []map[string]interface{} {
{"term": map[string]interface{}{"tags": "big data"}},
{"term": map[string]interface{}{"industry": "financial services"}},
{"term": map[string]interface{}{"location.country": "united states"}},
},
},
},
}
// Create a parameters JSON object
params := pdlmodel.SearchParams {
BaseParams: pdlmodel.BaseParams {
Size: 10,
Pretty: true,
},
SearchBaseParams: pdlmodel.SearchBaseParams {
Query: elasticSearchQuery,
},
}
// Pass the parameters object to the Company Search API
response, err := client.Company.Search(context.Background(), params)
// Check for successful response
if err == nil {
data := response.Data
// Create file
out, outErr := os.Create("my_pdl_search.jsonl")
defer out.Close()
if (outErr == nil) {
for i := range data {
// Convert each profile found to JSON
record, jsonErr := json.Marshal(data[i])
// Write out each profile to file
if (jsonErr == nil) {
out.WriteString(string(record) + "\n")
}
}
out.Sync()
}
fmt.Printf("Successfully grabbed %d records from PDL.\n", len(data))
fmt.Printf("%d total PDL records exist matching this query.\n", response.Total)
} else {
fmt.Println("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
fmt.Println("Error:", err)
}
}
package main
import(
"fmt"
"os"
"encoding/json"
"context"
)
// See https://github.com/peopledatalabs/peopledatalabs-go
import (
pdl "github.com/peopledatalabs/peopledatalabs-go"
pdlmodel "github.com/peopledatalabs/peopledatalabs-go/model"
)
func main() {
// Set your API key
apiKey := "YOUR API KEY"
// Set API key as environmental variable
// apiKey := os.Getenv("API_KEY")
// Create a client, specifying your API key
client := pdl.New(apiKey)
// Create an SQL query
sqlQuery := "SELECT * FROM company" +
" WHERE tags='big data'" +
" AND industry='financial services'" +
" AND location.country='united states';"
// Create a parameters JSON object
params := pdlmodel.SearchParams {
BaseParams: pdlmodel.BaseParams {
Size: 10,
Pretty: true,
},
SearchBaseParams: pdlmodel.SearchBaseParams {
SQL: sqlQuery,
},
}
// Pass the parameters object to the Company Search API
response, err := client.Company.Search(context.Background(), params)
// Check for successful response
if err == nil {
data := response.Data
// Create file
out, outErr := os.Create("my_pdl_search.jsonl")
defer out.Close()
if (outErr == nil) {
for i := range data {
// Convert each profile found to JSON
record, jsonErr := json.Marshal(data[i])
// Write out each profile to file
if (jsonErr == nil) {
out.WriteString(string(record) + "\n")
}
}
out.Sync()
}
fmt.Printf("Successfully grabbed %d records from PDL.\n", len(data))
fmt.Printf("%d total PDL records exist matching this query.\n", response.Total)
} else {
fmt.Println("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
fmt.Println("Error:", err)
}
}
import requests, json
# Set your API key
API_KEY = "YOUR API KEY"
# Set the Company Search API URL
PDL_URL = "https://api.peopledatalabs.com/v5/company/search"
# Set headers
HEADERS = {
'Content-Type': "application/json",
'X-api-key': API_KEY
}
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"term": {"tags": "big data"}},
{"term": {"industry": "financial services"}},
{"term": {"location.country": "united states"}}
]
}
}
}
# Create a parameters JSON object
PARAMS = {
'query': json.dumps(ES_QUERY),
'size': 10,
'pretty': True
}
# Pass the parameters object to the Company Search API
response = requests.get(
PDL_URL,
headers=HEADERS,
params=PARAMS
).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
print("Error:", response)
import requests, json
# Set your API key
API_KEY = "YOUR API KEY"
# Set the Company Search API URL
PDL_URL = "https://api.peopledatalabs.com/v5/company/search"
# Set headers
HEADERS = {
'Content-Type': "application/json",
'X-api-key': API_KEY
}
# Create an SQL query
SQL_QUERY = \
"""
SELECT * FROM company
WHERE tags='big data'
AND industry='financial services'
AND location.country='united states';
"""
# Create a parameters JSON object
PARAMS = {
'sql': SQL_QUERY,
'size': 10,
'pretty': True
}
# Pass the parameters object to the Company Search API
response = requests.get(
PDL_URL,
headers=HEADERS,
params=PARAMS
).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
print("Error:", response)
Sales and Marketing
"I want to find companies offering account-based marketing services in the United States."
import json
# See https://github.com/peopledatalabs/peopledatalabs-python
from peopledatalabs import PDLPY
# Create a client, specifying your API key
CLIENT = PDLPY(
api_key="YOUR API KEY",
)
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"match": {"summary": "account based marketing"}},
{"term": {"location.country" : "united states"}}
]
}
}
}
# Create a parameters JSON object
PARAMS = {
'query': ES_QUERY,
'size': 100
}
# Pass the parameters object to the Company Search API
response = CLIENT.company.search(**PARAMS).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The eager beaver was not so eager. See error and try again.")
print("error:", response)
// See https://github.com/peopledatalabs/peopledatalabs-js
import PDLJS from 'peopledatalabs';
import fs from 'fs';
// Create a client, specifying your API key
const PDLJSClient = new PDLJS({ apiKey: "YOUR API KEY" });
// Create an Elasticsearch query
const esQuery = {
query: {
bool: {
must:[
{"match": {"summary": "account based marketing"}},
{"term": {"location.country" : "united states"}}
]
}
}
}
// Create a parameters JSON object
const params = {
searchQuery: esQuery,
size: 100,
}
// Pass the parameters object to the Company Search API
PDLJSClient.company.search.elastic(params).then((data) => {
// Write out all profiles found to file
fs.writeFile("my_pdl_search.jsonl", Buffer.from(JSON.stringify(data.data)), (err) => {
if (err) throw err;
});
console.log(`Successfully grabbed ${data.data.length} records from PDL.`);
console.log(`${data["total"]} total PDL records exist matching this query.`)
}).catch((error) => {
console.log("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
console.log(error);
});
require 'json'
# See https://github.com/peopledatalabs/peopledatalabs-ruby
require 'peopledatalabs'
# Set your API key
Peopledatalabs.api_key = 'YOUR API KEY'
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"match": {"summary": "account based marketing"}},
{"term": {"location.country": "united states"}}
]
}
}
}
# Pass parameters to the Company Search API
response = Peopledatalabs::Search.company(searchType: 'elastic', query: ES_QUERY, size: 100, pretty: true)
# Check for successful response
if response['status'] == 200
data = response['data']
# Write out each profile found to file
File.open("my_pdl_search.jsonl", "w") do |out|
data.each { |record| out.write(JSON.dump(record) + "\n") }
end
puts "Successfully grabbed #{data.length()} records from PDL."
puts "#{response['total']} total PDL records exist matching this query."
else
puts "NOTE: The carrier pigeons lost motivation in flight. See error and try again."
puts "Error: #{response}"
end
package main
import(
"fmt"
"os"
"encoding/json"
"context"
)
// See https://github.com/peopledatalabs/peopledatalabs-go
import (
pdl "github.com/peopledatalabs/peopledatalabs-go"
pdlmodel "github.com/peopledatalabs/peopledatalabs-go/model"
)
func main() {
// Set your API key
apiKey := "YOUR API KEY"
// Set API key as environmental variable
// apiKey := os.Getenv("API_KEY")
// Create a client, specifying your API key
client := pdl.New(apiKey)
// Create an Elasticsearch query
elasticSearchQuery := map[string]interface{} {
"query": map[string]interface{} {
"bool": map[string]interface{} {
"must": []map[string]interface{} {
{"match": map[string]interface{}{"summary": "account based marketing"}},
{"term": map[string]interface{}{"location.country": "united states"}},
},
},
},
}
// Create a parameters JSON object
params := pdlmodel.SearchParams {
BaseParams: pdlmodel.BaseParams {
Size: 10,
},
SearchBaseParams: pdlmodel.SearchBaseParams {
Query: elasticSearchQuery,
},
}
// Pass the parameters object to the Company Search API
response, err := client.Company.Search(context.Background(), params)
// Check for successful response
if err == nil {
data := response.Data
// Create file
out, outErr := os.Create("my_pdl_search.jsonl")
defer out.Close()
if (outErr == nil) {
for i := range data {
// Convert each profile found to JSON
record, jsonErr := json.Marshal(data[i])
// Write out each profile to file
if (jsonErr == nil) {
out.WriteString(string(record) + "\n")
}
}
out.Sync()
}
fmt.Printf("Successfully grabbed %d records from PDL.\n", len(data))
fmt.Printf("%d total PDL records exist matching this query.\n", response.Total)
} else {
fmt.Println("NOTE: The eager beaver was not so eager. See error and try again.")
fmt.Println("Error:", err)
}
}
import requests, json
# Set your API key
API_KEY = "YOUR API KEY"
# Set the Company Search API URL
PDL_URL = "https://api.peopledatalabs.com/v5/company/search"
# Set headers
HEADERS = {
'Content-Type': "application/json",
'X-api-key': API_KEY
}
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"match": {"summary": "account based marketing"}},
{"term": {"location.country" : "united states"}}
]
}
}
}
# Create a parameters JSON object
PARAMS = {
'query': json.dumps(ES_QUERY),
'size': 100
}
# Pass the parameters object to the Company Search API
response = requests.get(
PDL_URL,
headers=HEADERS,
params=PARAMS
).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The eager beaver was not so eager. See error and try again.")
print("error:", response)
Investment Research
"I want to find 100 small biotech companies headquartered in the San Francisco area with under 50 employees ."
import json
# See https://github.com/peopledatalabs/peopledatalabs-python
from peopledatalabs import PDLPY
# Create a client, specifying your API key
CLIENT = PDLPY(
api_key="YOUR API KEY",
)
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
# for enumerated possible values of industry
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
# for enumerated possible values of company sizes
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"terms": {"size": ["1-10", "11-50"]}},
{"term": {"industry" : "biotechnology"}},
{"term": {"location.locality": "san francisco"}}
]
}
}
}
# Create a parameters JSON object
PARAMS = {
"query": ES_QUERY,
"size": 100
}
# Pass the parameters object to the Company Search API
response = CLIENT.company.search(**PARAMS).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The eager beaver was not so eager. See error and try again.")
print("error:", response)
import json
# See https://github.com/peopledatalabs/peopledatalabs-python
from peopledatalabs import PDLPY
# Create a client, specifying your API key
CLIENT = PDLPY(
api_key="YOUR API KEY",
)
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
# for enumerated possible values of industry
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
# for enumerated possible values of company sizes
# Create an SQL query
SQL_QUERY = \
f"""
SELECT * FROM company
WHERE size IN ('1-10', '11-50')
AND industry = 'biotechnology'
AND location.locality='san francisco';
"""
# Create a parameters JSON object
PARAMS = {
'sql': SQL_QUERY,
'size': 100
}
# Pass the parameters object to the Company Search API
response = CLIENT.company.search(**PARAMS).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The eager beaver was not so eager. See error and try again.")
print("error:", response)
// See https://github.com/peopledatalabs/peopledatalabs-js
import PDLJS from 'peopledatalabs';
import fs from 'fs';
// Create a client, specifying your API key
const PDLJSClient = new PDLJS({ apiKey: "YOUR API KEY" });
// Create an Elasticsearch query
const esQuery = {
query: {
bool: {
must:[
{"terms": {"size": ["1-10", "11-50"]}},
{"term": {"industry" : "biotechnology"}},
{"term": {"location.locality": "san francisco"}}
]
}
}
}
// Create a parameters JSON object
const params = {
searchQuery: esQuery,
size: 100,
}
// Pass the parameters object to the Company Search API
PDLJSClient.company.search.elastic(params).then((data) => {
// Write out all profiles found to file
fs.writeFile("my_pdl_search.jsonl", Buffer.from(JSON.stringify(data.data)), (err) => {
if (err) throw err;
});
console.log(`Successfully grabbed ${data.data.length} records from PDL.`);
console.log(`${data["total"]} total PDL records exist matching this query.`)
}).catch((error) => {
console.log("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
console.log(error);
});
// See https://github.com/peopledatalabs/peopledatalabs-js
import PDLJS from 'peopledatalabs';
import fs from 'fs';
// Create a client, specifying your API key
const PDLJSClient = new PDLJS({ apiKey: "YOUR API KEY" });
// Create an SQL query
const sqlQuery = `SELECT * FROM company
WHERE size IN ('1-10', '11-50')
AND industry = 'biotechnology'
AND location.locality='san francisco';`;
// Create a parameters JSON object
const params = {
searchQuery: sqlQuery,
size: 100
}
// Pass the parameters object to the Company Search API
PDLJSClient.company.search.sql(params).then((data) => {
// Write out all profiles found to file
fs.writeFile("my_pdl_search.jsonl", Buffer.from(JSON.stringify(data.data)), (err) => {
if (err) throw err;
});
console.log(`Successfully grabbed ${data.data.length} records from PDL.`);
console.log(`${data["total"]} total PDL records exist matching this query.`)
}).catch((error) => {
console.log("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
console.log(error);
});
require 'json'
# See https://github.com/peopledatalabs/peopledatalabs-ruby
require 'peopledatalabs'
# Set your API key
Peopledatalabs.api_key = 'YOUR API KEY'
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
# for enumerated possible values of industry
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
# for enumerated possible values of company sizes
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"terms": {"size": ["1-10", "11-50"]}},
{"term": {"industry": "biotechnology"}},
{"term": {"location.locality": "san francisco"}}
]
}
}
}
# Pass parameters to the Company Search API
response = Peopledatalabs::Search.company(searchType: 'elastic', query: ES_QUERY, size: 100, pretty: true)
# Check for successful response
if response['status'] == 200
data = response['data']
# Write out each profile found to file
File.open("my_pdl_search.jsonl", "w") do |out|
data.each { |record| out.write(JSON.dump(record) + "\n") }
end
puts "Successfully grabbed #{data.length()} records from PDL."
puts "#{response['total']} total PDL records exist matching this query."
else
puts "NOTE: The carrier pigeons lost motivation in flight. See error and try again."
puts "Error: #{response}"
end
require 'json'
# See https://github.com/peopledatalabs/peopledatalabs-ruby
require 'peopledatalabs'
# Set your API key
Peopledatalabs.api_key = 'YOUR API KEY'
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
# for enumerated possible values of industry
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
# for enumerated possible values of company sizes
# Create an SQL query
SQL_QUERY = \
"""
SELECT * FROM company
WHERE size IN ('1-10', '11-50')
AND industry = 'biotechnology'
AND location.locality='san francisco';
"""
# Pass parameters to the Company Search API
response = Peopledatalabs::Search.company(searchType: 'sql', query: SQL_QUERY, size: 100, pretty: true)
# Check for successful response
if response['status'] == 200
data = response['data']
# Write out each profile found to file
File.open("my_pdl_search.jsonl", "w") do |out|
data.each { |record| out.write(JSON.dump(record) + "\n") }
end
puts "Successfully grabbed #{data.length()} records from PDL."
puts "#{response['total']} total PDL records exist matching this query."
else
puts "NOTE: The carrier pigeons lost motivation in flight. See error and try again."
puts "Error: #{response}"
end
package main
import(
"fmt"
"os"
"encoding/json"
"context"
)
// See https://github.com/peopledatalabs/peopledatalabs-go
import (
pdl "github.com/peopledatalabs/peopledatalabs-go"
pdlmodel "github.com/peopledatalabs/peopledatalabs-go/model"
)
func main() {
// Set your API key
apiKey := "YOUR API KEY"
// Set API key as environmental variable
// apiKey := os.Getenv("API_KEY")
// Create a client, specifying your API key
client := pdl.New(apiKey)
// https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
// for enumerated possible values of industry
// https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
// for enumerated possible values of company sizes
// Create an Elasticsearch query
elasticSearchQuery := map[string]interface{} {
"query": map[string]interface{} {
"bool": map[string]interface{} {
"must": []map[string]interface{} {
{"terms": map[string]interface{}{"size": []string{"1-10", "11-50"}}},
{"term": map[string]interface{}{"industry": "biotechnology"}},
{"term": map[string]interface{}{"location.locality": "san francisco"}},
},
},
},
}
// Create a parameters JSON object
params := pdlmodel.SearchParams {
BaseParams: pdlmodel.BaseParams {
Size: 100,
},
SearchBaseParams: pdlmodel.SearchBaseParams {
Query: elasticSearchQuery,
},
}
// Pass the parameters object to the Company Search API
response, err := client.Company.Search(context.Background(), params)
// Check for successful response
if err == nil {
data := response.Data
// Create file
out, outErr := os.Create("my_pdl_search.jsonl")
defer out.Close()
if (outErr == nil) {
for i := range data {
// Convert each profile found to JSON
record, jsonErr := json.Marshal(data[i])
// Write out each profile to file
if (jsonErr == nil) {
out.WriteString(string(record) + "\n")
}
}
out.Sync()
}
fmt.Printf("Successfully grabbed %d records from pdl.\n", len(data))
fmt.Printf("%d total PDL records exist matching this query.\n", response.Total)
} else {
fmt.Println("NOTE: The eager beaver was not so eager. See error and try again.")
fmt.Println("Error:", err)
}
}
package main
import(
"fmt"
"os"
"encoding/json"
"context"
)
// See https://github.com/peopledatalabs/peopledatalabs-go
import (
pdl "github.com/peopledatalabs/peopledatalabs-go"
pdlmodel "github.com/peopledatalabs/peopledatalabs-go/model"
)
func main() {
// Set your API key
apiKey := "YOUR API KEY"
// Set API key as environmental variable
// apiKey := os.Getenv("API_KEY")
// Create a client, specifying your API key
client := pdl.New(apiKey)
// https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
// for enumerated possible values of industry
// https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
// for enumerated possible values of company sizes
// Create an SQL query
sqlQuery := "SELECT * FROM company" +
" WHERE size IN ('1-10', '11-50')" +
" AND industry = 'biotechnology'" +
" AND location.locality='san francisco';"
// Create a parameters JSON object
params := pdlmodel.SearchParams {
BaseParams: pdlmodel.BaseParams {
Size: 100,
Pretty: true,
},
SearchBaseParams: pdlmodel.SearchBaseParams {
SQL: sqlQuery,
},
}
// Pass the parameters object to the Company Search API
response, err := client.Company.Search(context.Background(), params)
// Check for successful response
if err == nil {
data := response.Data
// Create file
out, outErr := os.Create("my_pdl_search.jsonl")
defer out.Close()
if (outErr == nil) {
for i := range data {
// Convert each profile found to JSON
record, jsonErr := json.Marshal(data[i])
// Write out each profile to file
if (jsonErr == nil) {
out.WriteString(string(record) + "\n")
}
}
out.Sync()
}
fmt.Printf("Successfully grabbed %d records from PDL.\n", len(data))
fmt.Printf("%d total PDL records exist matching this query.\n", response.Total)
} else {
fmt.Println("NOTE: The eager beaver was not so eager. See error and try again.")
fmt.Println("Error:", err)
}
}
import requests, json
# Set your API key
API_KEY = "YOUR API KEY"
# Set the Company Search API URL
PDL_URL = "https://api.peopledatalabs.com/v5/company/search"
# Set headers
HEADERS = {
"Content-Type": "application/json",
"X-api-key": API_KEY
}
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
# for enumerated possible values of industry
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
# for enumerated possible values of company sizes
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"terms": {"size": ["1-10", "11-50"]}},
{"term": {"industry" : "biotechnology"}},
{"term": {"location.locality": "san francisco"}}
]
}
}
}
# Create a parameters JSON object
PARAMS = {
"query": json.dumps(ES_QUERY),
"size": 100
}
# Pass the parameters object to the Company Search API
response = requests.get(
PDL_URL,
headers=HEADERS,
params=PARAMS
).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(response['data'])} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The eager beaver was not so eager. See error and try again.")
print("error:", response)
import requests, json
# Set your API key
API_KEY = "YOUR API KEY"
# Set the Company Search API URL
PDL_URL = "https://api.peopledatalabs.com/v5/company/search"
# Set headers
HEADERS = {
"Content-Type": "application/json",
"X-api-key": API_KEY
}
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
# for enumerated possible values of industry
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
# for enumerated possible values of company sizes
# Create an SQL query
SQL_QUERY = \
f"""
SELECT * FROM company
WHERE size IN ('1-10', '11-50')
AND industry = 'biotechnology'
AND location.locality='san francisco';
"""
# Create a parameters JSON object
PARAMS = {
'sql': SQL_QUERY,
'size': 100
}
# Pass the parameters object to the Company Search API
response = requests.get(
PDL_URL,
headers=HEADERS,
params=PARAMS
).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(response['data'])} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The eager beaver was not so eager. See error and try again.")
print("error:", response)
Bulk Retrieval
"I want to find all automotive companies in the Detroit area and save them to a CSV file."
High Credit Usage Code Below
The code example below illustrates retrieving all the company profiles in a metro area and is meant primarily for demonstrating the use of the
scroll_tokenparameter when requesting large amounts of records. As a result, this code is mostly illustrative in meaning. It further can expend a lot of credits and doesn't have any error handling. TheMAX_NUM_RECORDS_LIMITparameter in the example sets the maximum number of profiles that you will retrieve (and the maximum number of credits that you will expend), so please set that accordingly when testing this example.
import json, time, csv
# See https://github.com/peopledatalabs/peopledatalabs-python
from peopledatalabs import PDLPY
# Create a client, specifying your API key
CLIENT = PDLPY(
api_key="YOUR API KEY",
)
# Limit the number of records to pull (to prevent accidentally using
# more credits than expected when testing out this code).
MAX_NUM_RECORDS_LIMIT = 150 # The maximum number of records to retrieve
USE_MAX_NUM_RECORDS_LIMIT = True # Set to False to pull all available records
# Create an Elasticsearch query
ES_QUERY = {
'query': {
'bool': {
'must': [
{'term': {'industry': "automotive"}},
{'term': {'location.metro': "detroit, michigan"}}
]
}
}
}
# Create a parameters JSON object
PARAMS = {
'query': ES_QUERY,
'size': 100,
'pretty': True
}
# Pull all results in multiple batches
batch = 1
# Store all records retreived in an array
all_records = []
# Time the process
start_time = time.time()
found_all_records = False
continue_scrolling = True
# While still scrolling through data and still records to be found
while continue_scrolling and not found_all_records:
# Check if we reached the maximum number of records we want
if USE_MAX_NUM_RECORDS_LIMIT:
num_records_to_request = MAX_NUM_RECORDS_LIMIT - len(all_records)
# Adjust size parameter
PARAMS['size'] = max(0, min(100, num_records_to_request))
# Check if MAX_NUM_RECORDS_LIMIT reached
if num_records_to_request == 0:
print(f"Stopping - reached maximum number of records to pull "
f"[MAX_NUM_RECORDS_LIMIT = {MAX_NUM_RECORDS_LIMIT}].")
break
# Pass the parameters object to the Company Search API
response = CLIENT.company.search(**PARAMS).json()
# Check for successful response
if response['status'] == 200:
# Add records retrieved to the records array
all_records.extend(response['data'])
print(f"Retrieved {len(response['data'])} records in batch {batch} "
f"- {response['total'] - len(all_records)} records remaining.")
else:
print(f"Error retrieving some records:\n\t"
f"[{response['status']} - {response['error']['type']}] "
f"{response['error']['message']}")
# Get scroll_token from response if exists and store it in parameters object
if 'scroll_token' in response:
PARAMS['scroll_token'] = response['scroll_token']
else:
continue_scrolling = False
print(f"Unable to continue scrolling.")
batch += 1
found_all_records = (len(all_records) == response['total'])
time.sleep(6) # avoid hitting rate limit thresholds
# Calculate time required to process batches
end_time = time.time()
runtime = end_time - start_time
print(f"Successfully recovered {len(all_records)} profiles in "
f"{batch} batches [{round(runtime, 2)} seconds].")
# Save profiles to CSV (utility function)
def save_profiles_to_csv(profiles, filename, fields=[], delim=','):
# Define header fields
if fields == [] and len(profiles) > 0:
fields = profiles[0].keys()
# Write CSV file
with open(filename, 'w') as csvfile:
writer = csv.writer(csvfile, delimiter=delim)
# Write header
writer.writerow(fields)
# Write body
count = 0
for profile in profiles:
writer.writerow([ profile[field] for field in fields ])
count += 1
print(f"Wrote {count} lines to: '{filename}'.")
# Use utility function to save all records retrieved to CSV
csv_header_fields = ['name', 'website', "linkedin_url",
'size', 'tags']
csv_filename = "all_company_profiles.csv"
save_profiles_to_csv(all_records, csv_filename, csv_header_fields)
import json, time, csv
# See https://github.com/peopledatalabs/peopledatalabs-python
from peopledatalabs import PDLPY
# Create a client, specifying your API key
CLIENT = PDLPY(
api_key="YOUR API KEY",
)
# Limit the number of records to pull (to prevent accidentally using
# more credits than expected when testing out this code).
MAX_NUM_RECORDS_LIMIT = 150 # The maximum number of records to retrieve
USE_MAX_NUM_RECORDS_LIMIT = True # Set to False to pull all available records
# Create an SQL query
SQL_QUERY = \
f"""
SELECT * FROM company
WHERE industry = 'automotive'
AND location.metro='detroit, michigan';
"""
# Create a parameters JSON object
PARAMS = {
'sql': SQL_QUERY,
'size': 100,
'pretty': True
}
# Pull all results in multiple batches
batch = 1
# Store all records retreived in an array
all_records = []
# Time the process
start_time = time.time()
found_all_records = False
continue_scrolling = True
# While still scrolling through data and still records to be found
while continue_scrolling and not found_all_records:
# Check if we reached the maximum number of records we want
if USE_MAX_NUM_RECORDS_LIMIT:
num_records_to_request = MAX_NUM_RECORDS_LIMIT - len(all_records)
# Adjust size parameter
PARAMS['size'] = max(0, min(100, num_records_to_request))
# Check if MAX_NUM_RECORDS_LIMIT reached
if num_records_to_request == 0:
print(f"Stopping - reached maximum number of records to pull "
f"[MAX_NUM_RECORDS_LIMIT = {MAX_NUM_RECORDS_LIMIT}].")
break
# Pass the parameters object to the Company Search API
response = CLIENT.company.search(**PARAMS).json()
# Check for successful response
if response['status'] == 200:
# Add records retrieved to the records array
all_records.extend(response['data'])
print(f"Retrieved {len(response['data'])} records in batch {batch} "
f"- {response['total'] - len(all_records)} records remaining.")
else:
print(f"Error retrieving some records:\n\t"
f"[{response['status']} - {response['error']['type']}] "
f"{response['error']['message']}")
# Get scroll_token from response if exists and store it in parameters object
if 'scroll_token' in response:
PARAMS['scroll_token'] = response['scroll_token']
else:
continue_scrolling = False
print(f"Unable to continue scrolling.")
batch += 1
found_all_records = (len(all_records) == response['total'])
time.sleep(6) # avoid hitting rate limit thresholds
# Calculate time required to process batches
end_time = time.time()
runtime = end_time - start_time
print(f"Successfully recovered {len(all_records)} profiles in "
f"{batch} batches [{round(runtime, 2)} seconds].")
# Save profiles to CSV (utility function)
def save_profiles_to_csv(profiles, filename, fields=[], delim=','):
# Define header fields
if fields == [] and len(profiles) > 0:
fields = profiles[0].keys()
# Write CSV file
with open(filename, 'w') as csvfile:
writer = csv.writer(csvfile, delimiter=delim)
# Write header
writer.writerow(fields)
# Write body
count = 0
for profile in profiles:
writer.writerow([ profile[field] for field in fields ])
count += 1
print(f"Wrote {count} lines to: '{filename}'.")
# Use utility function to save all records retrieved to CSV
csv_header_fields = ['name', 'website', "linkedin_url",
'size', 'tags']
csv_filename = "all_company_profiles.csv"
save_profiles_to_csv(all_records, csv_filename, csv_header_fields)
// See https://github.com/peopledatalabs/peopledatalabs-js
import PDLJS from 'peopledatalabs';
// See https://www.npmjs.com/package/csv-writer
import * as csvwriter from 'csv-writer';
// Create a client, specifying your API key
const PDLJSClient = new PDLJS({ apiKey: "YOUR API KEY" });
// Limit the number of records to pull (to prevent accidentally using
// more credits than expected when testing out this code).
const maxNumRecordsLimit = 150; // The maximum number of records to retrieve
const useMaxNumRecordsLimit = true; // Set to false to pull all available records
// Create an Elasticsearch query
const esQuery = {
query: {
bool: {
must:[
{'term': {'industry': "automotive"}},
{'term': {'location.metro': "detroit, michigan"}}
]
}
}
}
// Create a parameters JSON object
var params = {
searchQuery: esQuery,
size: 100,
scroll_token: null,
pretty: true
}
// Pull all results in multiple batches
var batch = 1;
// Store all records retreived in an array
var allRecords = [];
// Time the process
var startTime = Date.now();
var foundAllRecords = false;
var continueScrolling = true;
var numRetrieved = 0;
// Queue parameter objects in order to iterate through batches
var paramQueue = [];
// The current scroll_token
var scrollToken = null;
var numRecordsToRequest = 100;
while (numRecordsToRequest > 0) {
// Check if we reached the maximum number of records we want
if (useMaxNumRecordsLimit) {
numRecordsToRequest = maxNumRecordsLimit - numRetrieved;
// Adjust size parameter
params.size = Math.max(0, Math.min(100, numRecordsToRequest));
numRetrieved += params.size;
// Add batch to the parameter queue
if (params.size > 0) {
paramQueue.push(JSON.parse(JSON.stringify(params)));
}
} else {
break;
}
}
// Run initial batch
runBatch();
// Retrieve records associated with a batch
function runBatch() {
// Get the parameters for the current batch
let currParams = useMaxNumRecordsLimit ? paramQueue[batch-1] : params;
// Set the scroll_token from the previous batch
currParams.scroll_token = scrollToken;
batch++;
// Pass the current parameters object to the Company Search API
PDLJSClient.company.search.elastic(currParams).then((data) => {
// Add records retrieved to the records array
Array.prototype.push.apply(allRecords, data.data);
// Store the scroll_token if exists
if (data['scroll_token']) {
scrollToken = data['scroll_token'];
} else {
continueScrolling = false;
console.log("Unable to continue scrolling.");
}
foundAllRecords = (allRecords.length == data['total']);
console.log(`Retrieved ${data.data.length} records in batch ${(batch-1)}` +
` - ${(data['total'] - allRecords.length)} records remaining.`);
// Run next batch recursively, if any
if (!foundAllRecords && (batch <= paramQueue.length || !useMaxNumRecordsLimit)) {
runBatch();
} else {
console.log(`Stopping - reached maximum number of records to pull [maxNumRecordsLimit = ` +
`${maxNumRecordsLimit}].`);
// Calculate time required to process batches
let endTime = Date.now();
let runTime = endTime - startTime;
console.log (`Successfully recovered ${allRecords.length} profiles in ` +
`${(batch-1)} batches [${Math.round(runTime/1000)} seconds].`);
// Set CSV fields
let csvHeaderFields = [
{id: "work_email", title: "work_email"},
{id: "full_name", title: "full_name"},
{id: "linkedin_url", title: "linkedin_url"},
{id: "size", title: "size"},
{id: "tags", title: "tags"}
];
let csvFilename = "all_company_profiles.csv";
// Write records array to CSV file
saveProfilesToCSV(allRecords, csvFilename, csvHeaderFields);
}
}).catch((error) => {
console.log(error);
});
}
// Write CSV file using csv-writer (https://www.npmjs.com/package/csv-writer)
// $ npm i -s csv-writer
function saveProfilesToCSV(profiles, filename, fields) {
// Create CSV file
const createCsvWriter = csvwriter.createObjectCsvWriter;
const csvWriter = createCsvWriter({
path: filename,
header: fields
});
let data = [];
// Iterate through records array
for (let i = 0; i < profiles.length; i++) {
let record = profiles[i];
data[i] = {};
// Store requested fields
for (let field in fields) {
data[i][fields[field].id] = record[fields[field].id];
}
}
// Write data to CSV file
csvWriter
.writeRecords(data)
.then(()=> console.log('The CSV file was written successfully.'));
}
// See https://github.com/peopledatalabs/peopledatalabs-js
import PDLJS from 'peopledatalabs';
// See https://www.npmjs.com/package/csv-writer
import * as csvwriter from 'csv-writer';
// Create a client, specifying your API key
const PDLJSClient = new PDLJS({ apiKey: "YOUR API KEY" });
// Limit the number of records to pull (to prevent accidentally using
// more credits than expected when testing out this code).
const maxNumRecordsLimit = 150; // The maximum number of records to retrieve
const useMaxNumRecordsLimit = true; // Set to false to pull all available records
// Create an SQL query
const sqlQuery = `SELECT * FROM company
WHERE industry = 'automotive'
AND location.metro='detroit, michigan';`;
// Create a parameters JSON object
var params = {
searchQuery: sqlQuery,
size: 100,
scroll_token: null,
pretty: true
}
// Pull all results in multiple batches
var batch = 1;
// Store all records retreived in an array
var allRecords = [];
// Time the process
var startTime = Date.now();
var foundAllRecords = false;
var continueScrolling = true;
var numRetrieved = 0;
// Queue parameter objects in order to iterate through batches
var paramQueue = [];
// The current scroll_token
var scrollToken = null;
var numRecordsToRequest = 100;
while (numRecordsToRequest > 0) {
// Check if we reached the maximum number of records we want
if (useMaxNumRecordsLimit) {
numRecordsToRequest = maxNumRecordsLimit - numRetrieved;
// Adjust size parameter
params.size = Math.max(0, Math.min(100, numRecordsToRequest));
numRetrieved += params.size;
// Add batch to the parameter queue
if (params.size > 0) {
paramQueue.push(JSON.parse(JSON.stringify(params)));
}
} else {
break;
}
}
// Run initial batch
runBatch();
// Retrieve records associated with a batch
function runBatch() {
// Get the parameters for the current batch
let currParams = useMaxNumRecordsLimit ? paramQueue[batch-1] : params;
// Set the scroll_token from the previous batch
currParams.scroll_token = scrollToken;
batch++;
// Pass the current parameters object to the Company Search API
PDLJSClient.company.search.sql(currParams).then((data) => {
// Add records retrieved to the records array
Array.prototype.push.apply(allRecords, data.data);
// Store the scroll_token if exists
if (data['scroll_token']) {
scrollToken = data['scroll_token'];
} else {
continueScrolling = false;
console.log("Unable to continue scrolling.");
}
foundAllRecords = (allRecords.length == data['total']);
console.log(`Retrieved ${data.data.length} records in batch ${(batch-1)}` +
` - ${(data['total'] - allRecords.length)} records remaining.`);
// Run next batch recursively, if any
if (!foundAllRecords && (batch <= paramQueue.length || !useMaxNumRecordsLimit)) {
runBatch();
} else {
console.log(`Stopping - reached maximum number of records to pull [maxNumRecordsLimit = ` +
`${maxNumRecordsLimit}].`);
// Calculate time required to process batches
let endTime = Date.now();
let runTime = endTime - startTime;
console.log (`Successfully recovered ${allRecords.length} profiles in ` +
`${(batch-1)} batches [${Math.round(runTime/1000)} seconds].`);
// Set CSV fields
let csvHeaderFields = [
{id: "work_email", title: "work_email"},
{id: "full_name", title: "full_name"},
{id: "linkedin_url", title: "linkedin_url"},
{id: "size", title: "size"},
{id: "tags", title: "tags"}
];
let csvFilename = "all_company_profiles.csv";
// Write records array to CSV file
saveProfilesToCSV(allRecords, csvFilename, csvHeaderFields);
}
}).catch((error) => {
console.log(error);
});
}
// Write CSV file using csv-writer (https://www.npmjs.com/package/csv-writer)
// $ npm i -s csv-writer
function saveProfilesToCSV(profiles, filename, fields) {
// Create CSV file
const createCsvWriter = csvwriter.createObjectCsvWriter;
const csvWriter = createCsvWriter({
path: filename,
header: fields
});
let data = [];
for (let i = 0; i < profiles.length; i++) {
let record = profiles[i];
data[i] = {};
// Store requested fields
for (let field in fields) {
data[i][fields[field].id] = record[fields[field].id];
}
}
// Write data to CSV file
csvWriter
.writeRecords(data)
.then(()=> console.log('The CSV file was written successfully.'));
}
require 'json'
require 'csv'
# See https://github.com/peopledatalabs/peopledatalabs-ruby
require 'peopledatalabs'
# Set your API key
Peopledatalabs.api_key = 'YOUR API KEY'
# Limit the number of records to pull (to prevent accidentally using
# more credits than expected when testing out this code).
MAX_NUM_RECORDS_LIMIT = 150 # The maximum number of records to retrieve
USE_MAX_NUM_RECORDS_LIMIT = true # Set to false to pull all available records
# Create an Elasticsearch query
ES_QUERY = {
'query': {
'bool': {
'must': [
{'term': {'industry': "automotive"}},
{'term': {'location.metro': "detroit, michigan"}}
]
}
}
}
# Pull all results in multiple batches
batch = 1
# Store all records retreived in an array
all_records = []
# Time the process
start_time = Time.now
found_all_records = false
continue_scrolling = true
scroll_token = {}
# While still scrolling through data and still records to be found
while continue_scrolling && !found_all_records do
# Check if we reached the maximum number of records we want
if USE_MAX_NUM_RECORDS_LIMIT
num_records_to_request = MAX_NUM_RECORDS_LIMIT - all_records.length()
# Adjust size parameter
size = [0, [100, num_records_to_request].min].max
# Check if MAX_NUM_RECORDS_LIMIT reached
if num_records_to_request == 0
puts "Stopping - reached maximum number of records to pull "
puts "[MAX_NUM_RECORDS_LIMIT = #{MAX_NUM_RECORDS_LIMIT}]."
break
end
end
# Pass parameters to the Company Search API
response = Peopledatalabs::Search.company(searchType: 'elastic', query: ES_QUERY, size: size, scroll_token: scroll_token, pretty: true)
# Check for successful response
if response['status'] == 200
# Add records retrieved to the records array
all_records += response['data']
puts "Retrieved #{response['data'].length()} records in batch #{batch} "
puts "- #{response['total'] - all_records.length()} records remaining."
else
puts "Error retrieving some records:\n\t"
puts "[#{response['status']} - #{response['error']['type']}] "
puts response['error']['message']
end
# Get scroll_token from response if exists and store it
if response.key?('scroll_token')
scroll_token = response['scroll_token']
else
continue_scrolling = false
puts "Unable to continue scrolling."
end
batch += 1
found_all_records = (all_records.length() == response['total'])
sleep(6) # avoid hitting rate limit thresholds
end
# Calculate time required to process batches
end_time = Time.now
runtime = end_time - start_time
puts "Successfully recovered #{all_records.length()} profiles in "
puts "#{batch} batches [#{runtime.round(2)} seconds]."
# Save profiles to CSV (utility function)
def save_profiles_to_csv(profiles, filename, fields=[], delim=',')
# Define header fields
if fields == [] && profiles.length() > 0
fields = profiles[0].keys
end
count = 0
# Write CSV file
CSV.open(filename, 'w') do |writer|
# Write header
writer << fields
# Write body
profiles.each do |profile|
record = []
fields.each do |field|
record << profile[field]
count += 1
end
writer << record
end
end
puts "Wrote #{count} lines to: '#{filename}'."
end
# Use utility function to save profiles to CSV
csv_header_fields = ['name', 'website', 'linkedin_url',
'size', 'tags']
csv_filename = "all_company_profiles.csv"
save_profiles_to_csv(all_records, csv_filename, csv_header_fields)
require 'json'
require 'csv'
# See https://github.com/peopledatalabs/peopledatalabs-ruby
require 'peopledatalabs'
# Set your API key
Peopledatalabs.api_key = 'YOUR API KEY'
# Limit the number of records to pull (to prevent accidentally using
# more credits than expected when testing out this code).
MAX_NUM_RECORDS_LIMIT = 150 # The maximum number of records to retrieve
USE_MAX_NUM_RECORDS_LIMIT = true # Set to false to pull all available records
# Create an SQL query
SQL_QUERY = \
"""
SELECT * FROM company
WHERE industry = 'automotive'
AND location.metro='detroit, michigan';
"""
# Pull all results in multiple batches
batch = 1
# Store all records retreived in an array
all_records = []
# Time the process
start_time = Time.now
found_all_records = false
continue_scrolling = true
scroll_token = {}
# While still scrolling through data and still records to be found
while continue_scrolling && !found_all_records do
# Check if we reached the maximum number of records we want
if USE_MAX_NUM_RECORDS_LIMIT
num_records_to_request = MAX_NUM_RECORDS_LIMIT - all_records.length()
# Adjust size parameter
size = [0, [100, num_records_to_request].min].max
# Check if MAX_NUM_RECORDS_LIMIT reached
if num_records_to_request == 0
puts "Stopping - reached maximum number of records to pull "
puts "[MAX_NUM_RECORDS_LIMIT = #{MAX_NUM_RECORDS_LIMIT}]."
break
end
end
# Pass parameters to the Company Search API
response = Peopledatalabs::Search.company(searchType: 'sql', query: SQL_QUERY, size: size, scroll_token: scroll_token, pretty: true)
# Check for successful response
if response['status'] == 200
# Add records retrieved to the records array
all_records += response['data']
puts "Retrieved #{response['data'].length()} records in batch #{batch} "
puts "- #{response['total'] - all_records.length()} records remaining."
else
puts "Error retrieving some records:\n\t"
puts "[#{response['status']} - #{response['error']['type']}] "
puts response['error']['message']
end
# Get scroll_token from response if exists and store it
if response.key?('scroll_token')
scroll_token = response['scroll_token']
else
continue_scrolling = false
puts "Unable to continue scrolling."
end
batch += 1
found_all_records = (all_records.length() == response['total'])
sleep(6) # avoid hitting rate limit thresholds
end
# Calculate time required to process batches
end_time = Time.now
runtime = end_time - start_time
puts "Successfully recovered #{all_records.length()} profiles in "
puts "#{batch} batches [#{runtime.round(2)} seconds]."
# Save profiles to CSV (utility function)
def save_profiles_to_csv(profiles, filename, fields=[], delim=',')
# Define header fields
if fields == [] && profiles.length() > 0
fields = profiles[0].keys
end
count = 0
# Write CSV file
CSV.open(filename, 'w') do |writer|
# Write header
writer << fields
# Write body
profiles.each do |profile|
record = []
fields.each do |field|
record << profile[field]
count += 1
end
writer << record
end
end
puts "Wrote #{count} lines to: '#{filename}'."
end
# Use utility function to save profiles to CSV
csv_header_fields = ['name', 'website', 'linkedin_url',
'size', 'tags']
csv_filename = "all_company_profiles.csv"
save_profiles_to_csv(all_records, csv_filename, csv_header_fields)
package main
import (
"fmt"
"time"
"os"
"math"
"reflect"
"encoding/json"
"encoding/csv"
"context"
)
// See https://github.com/peopledatalabs/peopledatalabs-go
import (
pdl "github.com/peopledatalabs/peopledatalabs-go"
pdlmodel "github.com/peopledatalabs/peopledatalabs-go/model"
)
func main() {
// Set your API key
apiKey := "YOUR API KEY"
// Set API key as environmental variable
// apiKey := os.Getenv("API_KEY")
// Create a client, specifying your API key
client := pdl.New(apiKey)
// Limit the number of records to pull (to prevent accidentally using
// more credits than expected when testing out this code).
const maxNumRecordsLimit = 150 // The maximum number of records to retrieve
const useMaxNumRecordsLimit = true // Set to False to pull all available records
// Create an Elasticsearch query
elasticSearchQuery := map[string]interface{} {
"query": map[string]interface{} {
"bool": map[string]interface{} {
"must": []map[string]interface{} {
{"term": map[string]interface{}{"industry": "automotive"}},
{"term": map[string]interface{}{"location.metro": "detroit, michigan"}},
},
},
},
}
// Create a parameters JSON object
p := pdlmodel.SearchParams {
BaseParams: pdlmodel.BaseParams {
Size: 50,
Pretty: true,
},
SearchBaseParams: pdlmodel.SearchBaseParams {
Query: elasticSearchQuery,
},
}
// Pull all results in multiple batches
batch := 1
// Store all records retreived in an array
var allRecords []pdlmodel.Company
// Time the process
startTime := time.Now()
foundAllRecords := false
continueScrolling := true
var numRecordsToRequest int
// While still scrolling through data and still records to be found
for continueScrolling && !foundAllRecords {
// Check if we reached the maximum number of records we want
if useMaxNumRecordsLimit {
numRecordsToRequest = maxNumRecordsLimit - len(allRecords)
// Adjust size parameter
p.BaseParams.Size = (int) (math.Max(0.0, math.Min(50.0, (float64) (numRecordsToRequest))))
// Check if MAX_NUM_RECORDS_LIMIT reached
if numRecordsToRequest == 0 {
fmt.Printf("Stopping - reached maximum number of records to pull " +
"[MAX_NUM_RECORDS_LIMIT = %d].\n", maxNumRecordsLimit)
break
}
}
// Pass the parameters object to the Company Search API
response, err := client.Company.Search(context.Background(), p)
// Check for successful response
if err == nil {
fmt.Printf("Retrieved %d records in batch %d - %d records remaining.\n",
len(response.Data), batch, response.Total - len(allRecords))
} else {
fmt.Println("Error retrieving some records:\n\t",
err)
}
// Convert response to JSON
var data map[string]interface{}
jsonResponse, jsonErr := json.Marshal(response)
if jsonErr == nil {
json.Unmarshal(jsonResponse, &data)
// Get scroll_token from response if exists and store it in parameters object
if scrollToken, ok := data["scroll_token"]; ok {
p.SearchBaseParams.ScrollToken = fmt.Sprintf("%v", scrollToken)
} else {
continueScrolling = false
fmt.Println("Unable to continue scrolling.")
}
// Add records retrieved to the records array
allRecords = append(allRecords, response.Data...)
}
batch++
foundAllRecords = (len(allRecords) == response.Total)
time.Sleep(6 * time.Second) // avoid hitting rate limit thresholds
}
// Calculate time required to process batches
endTime := time.Now()
runtime := endTime.Sub(startTime).Seconds()
fmt.Printf("Successfully recovered %d profiles in %d batches [%d seconds].\n",
len(allRecords), batch, (int) (math.Round((float64) (runtime))))
// Use utility function to save profiles to CSV
csvHeaderFields := []string{"name", "website", "linkedin_url",
"size", "tags"}
csvFilename := "all_company_profiles.csv"
saveProfilesToCsv(allRecords, csvFilename, csvHeaderFields, ",")
}
// Save profiles to CSV (utility function)
func saveProfilesToCsv(profiles []pdlmodel.Company, filename string, fields []string, delim string) {
// Define header fields
if fields == nil && len(profiles) > 0 {
e := reflect.ValueOf(&(profiles[0])).Elem()
for i := 0; i < e.NumField(); i++ {
fields = append(fields, e.Type().Field(i).Name)
}
}
// Write CSV file
csvFile, err := os.Create(filename)
if err == nil {
csvwriter := csv.NewWriter(csvFile)
defer csvwriter.Flush()
// Write header
csvwriter.Write(fields)
// Write body
count := 0
for i := range profiles {
var data map[string]interface{}
jsonResponse, jsonErr := json.Marshal(profiles[i])
if jsonErr == nil {
json.Unmarshal(jsonResponse, &data)
var record []string
for j := range fields {
record = append(record, fmt.Sprintf("%v", data[fields[j]]))
}
csvwriter.Write(record)
count++
}
}
fmt.Printf("Wrote %d lines to: %s.\n", count, filename)
}
}
package main
import (
"fmt"
"time"
"os"
"math"
"reflect"
"encoding/json"
"encoding/csv"
"context"
)
// See https://github.com/peopledatalabs/peopledatalabs-go
import (
pdl "github.com/peopledatalabs/peopledatalabs-go"
pdlmodel "github.com/peopledatalabs/peopledatalabs-go/model"
)
func main() {
// Set your API key
apiKey := "YOUR API KEY"
// Set API key as environmental variable
// apiKey := os.Getenv("API_KEY")
// Create a client, specifying your API key
client := pdl.New(apiKey)
// Limit the number of records to pull (to prevent accidentally using
// more credits than expected when testing out this code).
const maxNumRecordsLimit = 150 // The maximum number of records to retrieve
const useMaxNumRecordsLimit = true // Set to False to pull all available records
// Create an SQL query
sqlQuery := "SELECT * FROM company" +
" WHERE industry = 'automotive'" +
" AND location.metro='detroit, michigan';"
// Create a parameters JSON object
p := pdlmodel.SearchParams {
BaseParams: pdlmodel.BaseParams {
Size: 50,
Pretty: true,
},
SearchBaseParams: pdlmodel.SearchBaseParams {
SQL: sqlQuery,
},
}
// Pull all results in multiple batches
batch := 1
// Store all records retreived in an array
var allRecords []pdlmodel.Company
// Time the process
startTime := time.Now()
foundAllRecords := false
continueScrolling := true
var numRecordsToRequest int
// While still scrolling through data and still records to be found
for continueScrolling && !foundAllRecords {
// Check if we reached the maximum number of records we want
if useMaxNumRecordsLimit {
numRecordsToRequest = maxNumRecordsLimit - len(allRecords)
// Adjust size parameter
p.BaseParams.Size = (int) (math.Max(0.0, math.Min(50.0, (float64) (numRecordsToRequest))))
// Check if MAX_NUM_RECORDS_LIMIT reached
if numRecordsToRequest == 0 {
fmt.Printf("Stopping - reached maximum number of records to pull " +
"[MAX_NUM_RECORDS_LIMIT = %d].\n", maxNumRecordsLimit)
break
}
}
// Pass the parameters object to the Company Search API
response, err := client.Company.Search(context.Background(), p)
// Check for successful response
if err == nil {
fmt.Printf("Retrieved %d records in batch %d - %d records remaining.\n",
len(response.Data), batch, response.Total - len(allRecords))
} else {
fmt.Println("Error retrieving some records:\n\t",
err)
}
// Convert response to JSON
var data map[string]interface{}
jsonResponse, jsonErr := json.Marshal(response)
if jsonErr == nil {
json.Unmarshal(jsonResponse, &data)
// Get scroll_token from response if exists and store it in parameters object
if scrollToken, ok := data["scroll_token"]; ok {
p.SearchBaseParams.ScrollToken = fmt.Sprintf("%v", scrollToken)
} else {
continueScrolling = false
fmt.Println("Unable to continue scrolling.")
}
// Add records retrieved to the records array
allRecords = append(allRecords, response.Data...)
}
batch++
foundAllRecords = (len(allRecords) == response.Total)
time.Sleep(6 * time.Second) // avoid hitting rate limit thresholds
}
// Calculate time required to process batches
endTime := time.Now()
runtime := endTime.Sub(startTime).Seconds()
fmt.Printf("Successfully recovered %d profiles in %d batches [%d seconds].\n",
len(allRecords), batch, (int) (math.Round((float64) (runtime))))
// Use utility function to save profiles to CSV
csvHeaderFields := []string{"name", "website", "linkedin_url",
"size", "tags"}
csvFilename := "all_company_profiles.csv"
saveProfilesToCsv(allRecords, csvFilename, csvHeaderFields, ",")
}
// Save profiles to CSV (utility function)
func saveProfilesToCsv(profiles []pdlmodel.Company, filename string, fields []string, delim string) {
// Define header fields
if fields == nil && len(profiles) > 0 {
e := reflect.ValueOf(&(profiles[0])).Elem()
for i := 0; i < e.NumField(); i++ {
fields = append(fields, e.Type().Field(i).Name)
}
}
// Write CSV file
csvFile, err := os.Create(filename)
if err == nil {
csvwriter := csv.NewWriter(csvFile)
defer csvwriter.Flush()
// Write header
csvwriter.Write(fields)
// Write body
count := 0
for i := range profiles {
var data map[string]interface{}
jsonResponse, jsonErr := json.Marshal(profiles[i])
if jsonErr == nil {
json.Unmarshal(jsonResponse, &data)
var record []string
for j := range fields {
record = append(record, fmt.Sprintf("%v", data[fields[j]]))
}
csvwriter.Write(record)
count++
}
}
fmt.Printf("Wrote %d lines to: %s.\n", count, filename)
}
}
import requests, json, time, csv
# Set your API key
API_KEY = "YOUR API KEY"
# Limit the number of records to pull (to prevent accidentally using
# more credits than expected when testing out this code).
MAX_NUM_RECORDS_LIMIT = 150 # The maximum number of records to retrieve
USE_MAX_NUM_RECORDS_LIMIT = True # Set to False to pull all available records
# Set the Company Search API URL
PDL_URL = "https://api.peopledatalabs.com/v5/company/search"
# Set headers
HEADERS = {
'Content-Type': "application/json",
'X-api-key': API_KEY
}
# Create an Elasticsearch query
ES_QUERY = {
'query': {
'bool': {
'must': [
{'term': {'industry': "automotive"}},
{'term': {'location.metro': "detroit, michigan"}}
]
}
}
}
# Create a parameters JSON object
PARAMS = {
'query': json.dumps(ES_QUERY),
'size': 100,
'pretty': True
}
# Pull all results in multiple batches
batch = 1
# Store all records retreived in an array
all_records = []
# Time the process
start_time = time.time()
found_all_records = False
continue_scrolling = True
# While still scrolling through data and still records to be found
while continue_scrolling and not found_all_records:
# Check if we reached the maximum number of records we want
if USE_MAX_NUM_RECORDS_LIMIT:
num_records_to_request = MAX_NUM_RECORDS_LIMIT - len(all_records)
# Adjust size parameter
PARAMS['size'] = max(0, min(100, num_records_to_request))
# Check if MAX_NUM_RECORDS_LIMIT reached
if num_records_to_request == 0:
print(f"Stopping - reached maximum number of records to pull "
f"[MAX_NUM_RECORDS_LIMIT = {MAX_NUM_RECORDS_LIMIT}].")
break
# Pass the parameters object to the Company Search API
response = requests.get(
PDL_URL,
headers=HEADERS,
params=PARAMS
).json()
# Check for successful response
if response['status'] == 200:
# Add records retrieved to the records array
all_records.extend(response['data'])
print(f"Retrieved {len(response['data'])} records in batch {batch} "
f"- {response['total'] - len(all_records)} records remaining.")
else:
print(f"Error retrieving some records:\n\t"
f"[{response['status']} - {response['error']['type']}] "
f"{response['error']['message']}")
# Get scroll_token from response if exists and store it in parameters object
if 'scroll_token' in response:
PARAMS['scroll_token'] = response['scroll_token']
else:
continue_scrolling = False
print(f"Unable to continue scrolling.")
batch += 1
found_all_records = (len(all_records) == response['total'])
time.sleep(6) # avoid hitting rate limit thresholds
# Calculate time required to process batches
end_time = time.time()
runtime = end_time - start_time
print(f"Successfully recovered {len(all_records)} profiles in "
f"{batch} batches [{round(runtime, 2)} seconds].")
# Save profiles to CSV (utility function)
def save_profiles_to_csv(profiles, filename, fields=[], delim=','):
# Define header fields
if fields == [] and len(profiles) > 0:
fields = profiles[0].keys()
# Write CSV file
with open(filename, 'w') as csvfile:
writer = csv.writer(csvfile, delimiter=delim)
# Write header
writer.writerow(fields)
# Write body
count = 0
for profile in profiles:
writer.writerow([ profile[field] for field in fields ])
count += 1
print(f"Wrote {count} lines to: '{filename}'.")
# Use utility function to save profiles to CSV
csv_header_fields = ['name', 'website', "linkedin_url",
'size', 'tags']
csv_filename = "all_company_profiles.csv"
save_profiles_to_csv(all_records, csv_filename, csv_header_fields)
import requests, json, time, csv
# Set your API key
API_KEY = "YOUR API KEY"
# Limit the number of records to pull (to prevent accidentally using
# more credits than expected when testing out this code).
MAX_NUM_RECORDS_LIMIT = 150 # The maximum number of records to retrieve
USE_MAX_NUM_RECORDS_LIMIT = True # Set to False to pull all available records
# Set the Company Search API URL
PDL_URL = "https://api.peopledatalabs.com/v5/company/search"
# Set headers
HEADERS = {
'Content-Type': "application/json",
'X-api-key': API_KEY
}
# Create an SQL query
SQL_QUERY = \
f"""
SELECT * FROM company
WHERE industry = 'automotive'
AND location.metro='detroit, michigan';
"""
# Create a parameters JSON object
PARAMS = {
'sql': SQL_QUERY,
'size': 100,
'pretty': True
}
# Pull all results in multiple batches
batch = 1
# Store all records retreived in an array
all_records = []
# Time the process
start_time = time.time()
found_all_records = False
continue_scrolling = True
# While still scrolling through data and still records to be found
while continue_scrolling and not found_all_records:
# Check if we reached the maximum number of records we want
if USE_MAX_NUM_RECORDS_LIMIT:
num_records_to_request = MAX_NUM_RECORDS_LIMIT - len(all_records)
# Adjust size parameter
PARAMS['size'] = max(0, min(100, num_records_to_request))
# Check if MAX_NUM_RECORDS_LIMIT reached
if num_records_to_request == 0:
print(f"Stopping - reached maximum number of records to pull "
f"[MAX_NUM_RECORDS_LIMIT = {MAX_NUM_RECORDS_LIMIT}].")
break
# Pass the parameters object to the Company Search API
response = requests.get(
PDL_URL,
headers=HEADERS,
params=PARAMS
).json()
# Check for successful response
if response['status'] == 200:
# Add records retrieved to the records array
all_records.extend(response['data'])
print(f"Retrieved {len(response['data'])} records in batch {batch} "
f"- {response['total'] - len(all_records)} records remaining.")
else:
print(f"Error retrieving some records:\n\t"
f"[{response['status']} - {response['error']['type']}] "
f"{response['error']['message']}")
# Get scroll_token from response if exists and store it in parameters object
if 'scroll_token' in response:
PARAMS['scroll_token'] = response['scroll_token']
else:
continue_scrolling = False
print(f"Unable to continue scrolling.")
batch += 1
found_all_records = (len(all_records) == response['total'])
time.sleep(6) # avoid hitting rate limit thresholds
# Calculate time required to process batches
end_time = time.time()
runtime = end_time - start_time
print(f"Successfully recovered {len(all_records)} profiles in "
f"{batch} batches [{round(runtime, 2)} seconds].")
# Save profiles to CSV (utility function)
def save_profiles_to_csv(profiles, filename, fields=[], delim=','):
# Define header fields
if fields == [] and len(profiles) > 0:
fields = profiles[0].keys()
# Write CSV file
with open(filename, 'w') as csvfile:
writer = csv.writer(csvfile, delimiter=delim)
# Write header
writer.writerow(fields)
# Write body
count = 0
for profile in profiles:
writer.writerow([ profile[field] for field in fields ])
count += 1
print(f"Wrote {count} lines to: '{filename}'.")
# Use utility function to save profiles to CSV
csv_header_fields = ['name', 'website', "linkedin_url",
'size', 'tags']
csv_filename = "all_company_profiles.csv"
save_profiles_to_csv(all_records, csv_filename, csv_header_fields)
Affiliate Lookup
(search by affiliated companies)
"I want to find all companies that are affiliated with Amazon."
import json
# See https://github.com/peopledatalabs/peopledatalabs-python
from peopledatalabs import PDLPY
# Create a client, specifying your API key
CLIENT = PDLPY(
api_key="YOUR API KEY",
)
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
# for enumerated possible values of industry
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
# for enumerated possible values of company sizes
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"term": {"affiliated_profiles": "amazon"}}
]
}
}
}
# Create a parameters JSON object
PARAMS = {
"query": ES_QUERY,
"size": 100
}
# Pass the parameters object to the Company Search API
response = CLIENT.company.search(**PARAMS).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The eager beaver was not so eager. See error and try again.")
print("error:", response)
import json
# See https://github.com/peopledatalabs/peopledatalabs-python
from peopledatalabs import PDLPY
# Create a client, specifying your API key
CLIENT = PDLPY(
api_key="YOUR API KEY",
)
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
# for enumerated possible values of industry
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
# for enumerated possible values of company sizes
# Create an SQL query
SQL_QUERY = \
f"""
SELECT * FROM company
WHERE affiliated_profiles = 'amazon';
"""
# Create a parameters JSON object
PARAMS = {
'sql': SQL_QUERY,
'size': 100
}
# Pass the parameters object to the Company Search API
response = CLIENT.company.search(**PARAMS).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(data)} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The eager beaver was not so eager. See error and try again.")
print("error:", response)
// See https://github.com/peopledatalabs/peopledatalabs-js
import PDLJS from 'peopledatalabs';
import fs from 'fs';
// Create a client, specifying your API key
const PDLJSClient = new PDLJS({ apiKey: "YOUR API KEY" });
// Create an Elasticsearch query
const esQuery = {
query: {
bool: {
must:[
{"term": {"affiliated_profiles": "amazon"}}
]
}
}
}
// Create a parameters JSON object
const params = {
searchQuery: esQuery,
size: 100,
}
// Pass the parameters object to the Company Search API
PDLJSClient.company.search.elastic(params).then((data) => {
// Write out all profiles found to file
fs.writeFile("my_pdl_search.jsonl", Buffer.from(JSON.stringify(data.data)), (err) => {
if (err) throw err;
});
console.log(`Successfully grabbed ${data.data.length} records from PDL.`);
console.log(`${data["total"]} total PDL records exist matching this query.`)
}).catch((error) => {
console.log("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
console.log(error);
});
// See https://github.com/peopledatalabs/peopledatalabs-js
import PDLJS from 'peopledatalabs';
import fs from 'fs';
// Create a client, specifying your API key
const PDLJSClient = new PDLJS({ apiKey: "YOUR API KEY" });
// Create an SQL query
const sqlQuery = `SELECT * FROM company
WHERE affiliated_profiles = 'amazon';`;
// Create a parameters JSON object
const params = {
searchQuery: sqlQuery,
size: 100
}
// Pass the parameters object to the Company Search API
PDLJSClient.company.search.sql(params).then((data) => {
// Write out all profiles found to file
fs.writeFile("my_pdl_search.jsonl", Buffer.from(JSON.stringify(data.data)), (err) => {
if (err) throw err;
});
console.log(`Successfully grabbed ${data.data.length} records from PDL.`);
console.log(`${data["total"]} total PDL records exist matching this query.`)
}).catch((error) => {
console.log("NOTE: The carrier pigeons lost motivation in flight. See error and try again.")
console.log(error);
});
require 'json'
# See https://github.com/peopledatalabs/peopledatalabs-ruby
require 'peopledatalabs'
# Set your API key
Peopledatalabs.api_key = 'YOUR API KEY'
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
# for enumerated possible values of industry
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
# for enumerated possible values of company sizes
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"term": {"affiliated_profiles": "amazon"}}
]
}
}
}
# Pass parameters to the Company Search API
response = Peopledatalabs::Search.company(searchType: 'elastic', query: ES_QUERY, size: 100, pretty: true)
# Check for successful response
if response['status'] == 200
data = response['data']
# Write out each profile found to file
File.open("my_pdl_search.jsonl", "w") do |out|
data.each { |record| out.write(JSON.dump(record) + "\n") }
end
puts "Successfully grabbed #{data.length()} records from PDL."
puts "#{response['total']} total PDL records exist matching this query."
else
puts "NOTE: The carrier pigeons lost motivation in flight. See error and try again."
puts "Error: #{response}"
end
require 'json'
# See https://github.com/peopledatalabs/peopledatalabs-ruby
require 'peopledatalabs'
# Set your API key
Peopledatalabs.api_key = 'YOUR API KEY'
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
# for enumerated possible values of industry
# https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
# for enumerated possible values of company sizes
# Create an SQL query
SQL_QUERY = \
"""
SELECT * FROM company
WHERE affiliated_profiles = 'amazon';
"""
# Pass parameters to the Company Search API
response = Peopledatalabs::Search.company(searchType: 'sql', query: SQL_QUERY, size: 100, pretty: true)
# Check for successful response
if response['status'] == 200
data = response['data']
# Write out each profile found to file
File.open("my_pdl_search.jsonl", "w") do |out|
data.each { |record| out.write(JSON.dump(record) + "\n") }
end
puts "Successfully grabbed #{data.length()} records from PDL."
puts "#{response['total']} total PDL records exist matching this query."
else
puts "NOTE: The carrier pigeons lost motivation in flight. See error and try again."
puts "Error: #{response}"
end
package main
import(
"fmt"
"os"
"encoding/json"
"context"
)
// See https://github.com/peopledatalabs/peopledatalabs-go
import (
pdl "github.com/peopledatalabs/peopledatalabs-go"
pdlmodel "github.com/peopledatalabs/peopledatalabs-go/model"
)
func main() {
// Set your API key
apiKey := "YOUR API KEY"
// Set API key as environmental variable
// apiKey := os.Getenv("API_KEY")
// Create a client, specifying your API key
client := pdl.New(apiKey)
// https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
// for enumerated possible values of industry
// https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
// for enumerated possible values of company sizes
// Create an Elasticsearch query
elasticSearchQuery := map[string]interface{} {
"query": map[string]interface{} {
"bool": map[string]interface{} {
"must": []map[string]interface{} {
{"term": map[string]interface{}{"affiliated_profiles": "amazon"}},
},
},
},
}
// Create a parameters JSON object
params := pdlmodel.SearchParams {
BaseParams: pdlmodel.BaseParams {
Size: 100,
},
SearchBaseParams: pdlmodel.SearchBaseParams {
Query: elasticSearchQuery,
},
}
// Pass the parameters object to the Company Search API
response, err := client.Company.Search(context.Background(), params)
// Check for successful response
if err == nil {
data := response.Data
// Create file
out, outErr := os.Create("my_pdl_search.jsonl")
defer out.Close()
if (outErr == nil) {
for i := range data {
// Convert each profile found to JSON
record, jsonErr := json.Marshal(data[i])
// Write out each profile to file
if (jsonErr == nil) {
out.WriteString(string(record) + "\n")
}
}
out.Sync()
}
fmt.Printf("Successfully grabbed %d records from PDL.\n", len(data))
fmt.Printf("%d total PDL records exist matching this query.\n", response.Total)
} else {
fmt.Println("NOTE: The eager beaver was not so eager. See error and try again.")
fmt.Println("Error:", err)
}
}
package main
import(
"fmt"
"os"
"encoding/json"
"context"
)
// See https://github.com/peopledatalabs/peopledatalabs-go
import (
pdl "github.com/peopledatalabs/peopledatalabs-go"
pdlmodel "github.com/peopledatalabs/peopledatalabs-go/model"
)
func main() {
// Set your API key
apiKey := "YOUR API KEY"
// Set API key as environmental variable
// apiKey := os.Getenv("API_KEY")
// Create a client, specifying your API key
client := pdl.New(apiKey)
// https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/industry.txt
// for enumerated possible values of industry
// https://pdl-prod-schema.s3-us-west-2.amazonaws.com/14.0/enums/job_company_size.txt
// for enumerated possible values of company sizes
// Create an SQL query
sqlQuery := "SELECT * FROM company" +
" WHERE affiliated_profiles = 'amazon';"
// Create a parameters JSON object
params := pdlmodel.SearchParams {
BaseParams: pdlmodel.BaseParams {
Size: 100,
Pretty: true,
},
SearchBaseParams: pdlmodel.SearchBaseParams {
SQL: sqlQuery,
},
}
// Pass the parameters object to the Company Search API
response, err := client.Company.Search(context.Background(), params)
// Check for successful response
if err == nil {
data := response.Data
// Create file
out, outErr := os.Create("my_pdl_search.jsonl")
defer out.Close()
if (outErr == nil) {
for i := range data {
// Convert each profile found to JSON
record, jsonErr := json.Marshal(data[i])
// Write out each profile to file
if (jsonErr == nil) {
out.WriteString(string(record) + "\n")
}
}
out.Sync()
}
fmt.Printf("Successfully grabbed %d records from PDL.\n", len(data))
fmt.Printf("%d total PDL records exist matching this query.\n", response.Total)
} else {
fmt.Println("NOTE: The eager beaver was not so eager. See error and try again.")
fmt.Println("Error:", err)
}
}
import requests, json
# Set your API key
API_KEY = "YOUR API KEY"
# Set the Company Search API URL
PDL_URL = "https://api.peopledatalabs.com/v5/company/search"
# Set headers
HEADERS = {
"Content-Type": "application/json",
"X-api-key": API_KEY
}
# Create an Elasticsearch query
ES_QUERY = {
"query": {
"bool": {
"must": [
{"term": {"affiliated_profiles": "amazon"}}
]
}
}
}
# Create a parameters JSON object
PARAMS = {
"query": json.dumps(ES_QUERY),
"size": 100
}
# Pass the parameters object to the Company Search API
response = requests.get(
PDL_URL,
headers=HEADERS,
params=PARAMS
).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(response['data'])} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The eager beaver was not so eager. See error and try again.")
print("error:", response)
import requests, json
# Set your API key
API_KEY = "YOUR API KEY"
# Set the Company Search API URL
PDL_URL = "https://api.peopledatalabs.com/v5/company/search"
# Set headers
HEADERS = {
"Content-Type": "application/json",
"X-api-key": API_KEY
}
# Create an SQL query
SQL_QUERY = \
f"""
SELECT * FROM company
WHERE affiliated_profiles = 'amazon';
"""
# Create a parameters JSON object
PARAMS = {
'sql': SQL_QUERY,
'size': 100
}
# Pass the parameters object to the Company Search API
response = requests.get(
PDL_URL,
headers=HEADERS,
params=PARAMS
).json()
# Check for successful response
if response["status"] == 200:
data = response['data']
# Write out each profile found to file
with open("my_pdl_search.jsonl", "w") as out:
for record in data:
out.write(json.dumps(record) + "\n")
print(f"Successfully grabbed {len(response['data'])} records from PDL.")
print(f"{response['total']} total PDL records exist matching this query.")
else:
print("NOTE: The eager beaver was not so eager. See error and try again.")
print("error:", response)
Updated 5 months ago