Created
June 15, 2022 10:36
-
-
Save dimitryzub/271e082691ceb02fa8657a3664635a09 to your computer and use it in GitHub Desktop.
Scrape all Google Maps Local Results with Python and SerpApi
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from serpapi import GoogleSearch | |
from urllib.parse import urlsplit, parse_qsl | |
import pandas as pd | |
import json | |
params = { | |
"api_key": "YOUR-API-KEY", # your serpapi api key | |
"engine": "google_maps", # serpapi search engine | |
"type": "search", # type of the search. Search, Place.. | |
"q": "Burger", # search query | |
"hl": "en", # language of the search | |
"ll": "@47.6080482,-122.3074315,13z" # GPS coordinates of location to search places from | |
} | |
search = GoogleSearch(params) # where data extraction happens on the backend | |
local_place_results = [] | |
page_num = 0 | |
while True: | |
page_num += 1 # track from which page result comes from | |
results = search.get_dict() # JSON -> Python dictionary | |
if not "error" in results: | |
for result in results.get("local_results"): | |
print(f"Extracting data from {result.get('title')}") | |
local_place_results.append({ | |
"page_num": page_num, | |
"place_name": result.get("title"), | |
"rating": result.get("rating"), | |
"reviews": result.get("reviews"), | |
"place_id": result.get("place_id"), | |
"address": result.get("address"), | |
"phone": result.get("phone"), | |
"website": result.get("website"), | |
"reviews_link": result.get("reviews_link"), | |
"photos_link": result.get("photos_link"), | |
"gps_coordinates": result.get("gps_coordinates"), | |
"thumbnail": result.get("thumbnail") | |
# many other types of data | |
}) | |
else: | |
print(results["error"] + " Or there's no results to be extracted.") | |
if "next" in results.get("serpapi_pagination", {}): | |
search.params_dict.update(dict(parse_qsl(urlsplit(results["serpapi_pagination"]["next"]).query))) | |
else: | |
break | |
# https://stackoverflow.com/a/51634732/15164646 | |
unique_local_place_results = pd.DataFrame(local_place_results).astype(str).drop_duplicates().to_dict("records") | |
print(json.dumps(local_place_results, indent=2, ensure_ascii=False)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment