import requests, json
API_KEY = # YOUR API KEY

PDL_URL = "https://api.peopledatalabs.com/v5/company/search"

H = {
  'Content-Type': "application/json",
  'X-api-key': API_KEY
}

ES_QUERY = {
  "query": {
    "bool": {
      "must": [
        {"term": {"website": "google.com"}},
      ]
    }
  }
}

P = {
  'query': json.dumps(ES_QUERY),
  'size': 10,
  'pretty': True
}

response = requests.get(
  PDL_URL,
  headers=H,
  params=P
).json()

if response["status"] == 200:
  data = response['data']
  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

API_KEY = # YOUR API KEY

PDL_URL = "https://api.peopledatalabs.com/v5/company/search"

H = {
  'Content-Type': "application/json",
  'X-api-key': API_KEY
}

SQL_QUERY = \
"""
  SELECT * FROM company
  WHERE website='google.com';
 """

P = {
  'sql': SQL_QUERY,
  'size': 10,
  'pretty': True
}

response = requests.get(
  PDL_URL,
  headers=H,
  params=P
).json()

if response["status"] == 200:
  data = response['data']
  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'\'';"
}'

import requests, json
API_KEY = # YOUR API KEY

PDL_URL = "https://api.peopledatalabs.com/v5/company/search"

H = {
  'Content-Type': "application/json",
  'X-api-key': API_KEY
}

ES_QUERY = {
  "query": {
    "bool": {
      "must": [
        {"term": {"tags": "big data"}},
        {"term": {"industry": "financial services"}},
        {"term": {"location.country": "united states"}}
      ]
    }
  }
}

P = {
  'query': json.dumps(ES_QUERY),
  'size': 10,
  'pretty': True
}

response = requests.get(
  PDL_URL,
  headers=H,
  params=P
).json()

if response["status"] == 200:
  data = response['data']
  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
API_KEY = # YOUR API KEY

PDL_URL = "https://api.peopledatalabs.com/v5/company/search"

H = {
  'Content-Type': "application/json",
  'X-api-key': API_KEY
}

SQL_QUERY = \
"""
  SELECT * FROM company
  WHERE tags='big data'
  AND industry='financial services'
  AND location.country='united states';
 """

P = {
  'sql': SQL_QUERY,
  'size': 10,
  'pretty': True
}


response = requests.get(
  PDL_URL,
  headers=H,
  params=P
).json()

if response["status"] == 200:
  data = response['data']
  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
API_KEY = #YOUR API KEY

PDL_URL = "https://api.peopledatalabs.com/v5/company/search"

H = {
  'Content-Type': "application/json",
  'X-api-key': API_KEY
}

ES_QUERY = {
  "query": {
    "bool": {
      "must": [
        {"match": {"summary": "account based marketing"}},
        {"term": {"location.country" : "united states"}}
      ]
    }
  }
}

P = {
  'query': json.dumps(ES_QUERY),
  'size': 100
}

response = requests.get(
  PDL_URL,
  headers=H,
  params=P
).json()

if response["status"] == 200:
  
  data = response['data']
  
  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 requests, json
API_KEY = #YOUR API KEY

PDL_URL = "https://api.peopledatalabs.com/v5/company/search"

H = {
  'Content-Type': "application/json",
  'X-api-key': API_KEY
}

SQL_QUERY = \
f"""
  SELECT * FROM company
  WHERE MATCH(summary, 'account based marketing')
  AND location.country='united states';
"""

P = {
  'sql': SQL_QUERY,
  'size': 100
}

response = requests.get(
  PDL_URL,
  headers=H,
  params=P
).json()



if response["status"] == 200:
  
  data = response['data']
  
  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 requests, json
API_KEY = #YOUR API KEY

PDL_URL = "https://api.peopledatalabs.com/v5/company/search"

H = {
"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

ES_QUERY = {
  "query": {
    "bool": {
      "must": [
        {"terms": {"size": ["1-10", "11-50"]}},
        {"term": {"industry" : "biotechnology"}},
        {"term": {"location.locality": "san francisco"}}
      ]
    }
  }
}

P = {
    "query": json.dumps(ES_QUERY),
    "size": 100
}

response = requests.get(
    PDL_URL,
    headers=H,
    params=P
).json()

if response["status"] == 200:
  
  data = response['data']
  
  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
API_KEY = #YOUR API KEY

PDL_URL = "https://api.peopledatalabs.com/v5/company/search"

H = {
"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

SQL_QUERY = \
f"""
  SELECT * FROM company
  WHERE size IN ('1-10, '11-50')
  AND industry = 'biotechnology'
  AND location.locality='san francisco';
"""

P = {
  'sql': SQL_QUERY,
  'size': 100
}

response = requests.get(
  PDL_URL,
  headers=H,
  params=P
).json()

if response["status"] == 200:
  
  data = response['data']
  
  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, time, csv

API_KEY = # ENTER YOUR API KEY

# Limit the number of records to pull (to prevent accidentally using up 
# 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

PDL_URL = "https://api.peopledatalabs.com/v5/company/search"

H = {
  'Content-Type': "application/json",
  'X-api-key': API_KEY
}

ES_QUERY = {
  'query': {
    'bool': {
      'must': [
        {'term': {'industry': "automotive"}},
        {'term': {'location.metro': "detroit, michigan"}}
      ]
    }
  }
}

P = {
  'query': json.dumps(ES_QUERY),
  'size': 100,
  'pretty': True
}

# Pull all results in multiple batches
batch = 1
all_records = []
start_time = time.time()
found_all_records = False
continue_scrolling = True

while continue_scrolling and not found_all_records: 

  # Check if we reached the maximum number of records we wanted to pull
  if USE_MAX_NUM_RECORDS_LIMIT:
    num_records_to_request = MAX_NUM_RECORDS_LIMIT - len(all_records)
    P['size'] = max(0, min(100, num_records_to_request))
    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

  # Send Response
  response = requests.get(
    PDL_URL,
    headers=H,
    params=P
  ).json()

  # Check response status code:
  if response['status'] == 200:
    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 'scroll_token' in response:
    P['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
 
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

API_KEY = # ENTER YOUR API KEY

# Limit the number of records to pull (to prevent accidentally using up 
# 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

PDL_URL = "https://api.peopledatalabs.com/v5/company/search"

H = {
  'Content-Type': "application/json",
  'X-api-key': API_KEY
}

SQL_QUERY = \
f"""
  SELECT * FROM company
  WHERE industry = 'automotive'
  AND location.metro='detroit, michigan';
"""

P = {
  'sql': SQL_QUERY,
  'size': 100,
  'pretty': True
}

# Pull all results in multiple batches
batch = 1
all_records = []
start_time = time.time()
found_all_records = False
continue_scrolling = True

while continue_scrolling and not found_all_records: 

  # Check if we reached the maximum number of records we wanted to pull
  if USE_MAX_NUM_RECORDS_LIMIT:
    num_records_to_request = MAX_NUM_RECORDS_LIMIT - len(all_records)
    P['size'] = max(0, min(100, num_records_to_request))
    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

  # Send Response
  response = requests.get(
    PDL_URL,
    headers=H,
    params=P
  ).json()

  # Check response status code:
  if response['status'] == 200:
    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 'scroll_token' in response:
    P['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
 
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
API_KEY = #YOUR API KEY

PDL_URL = "https://api.peopledatalabs.com/v5/company/search"

H = {
"Content-Type": "application/json",
"X-api-key": API_KEY
}

ES_QUERY = {
  "query": {
    "bool": {
      "must": [
        {"term": {"affiliated_profiles": "amazon"}}
      ]
    }
  }
}

P = {
    "query": json.dumps(ES_QUERY),
    "size": 100
}

response = requests.get(
    PDL_URL,
    headers=H,
    params=P
).json()

if response["status"] == 200:
  data = response['data']
  
  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
API_KEY = #YOUR API KEY

PDL_URL = "https://api.peopledatalabs.com/v5/company/search"

H = {
"Content-Type": "application/json",
"X-api-key": API_KEY
}

SQL_QUERY = \
f"""
  SELECT * FROM company
  WHERE affiliated_profiles = 'amazon';
"""

P = {
  'sql': SQL_QUERY,
  'size': 100
}

response = requests.get(
  PDL_URL,
  headers=H,
  params=P
).json()

if response["status"] == 200:
  
  data = response['data']
  
  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)