From c2b39918d277bb6e868066b8c3ad4c3277d43725 Mon Sep 17 00:00:00 2001
From: Yaochen <ys3593@columbia.com>
Date: Wed, 3 May 2023 22:13:07 -0400
Subject: [PATCH] add yelp scrapper

---
 Web-Scraping/Yelp-Scrapper/README.md   |  7 ++++++
 Web-Scraping/Yelp-Scrapper/scrapper.py | 35 ++++++++++++++++++++++++++
 2 files changed, 42 insertions(+)
 create mode 100644 Web-Scraping/Yelp-Scrapper/README.md
 create mode 100644 Web-Scraping/Yelp-Scrapper/scrapper.py

diff --git a/Web-Scraping/Yelp-Scrapper/README.md b/Web-Scraping/Yelp-Scrapper/README.md
new file mode 100644
index 0000000..e95a0f8
--- /dev/null
+++ b/Web-Scraping/Yelp-Scrapper/README.md
@@ -0,0 +1,7 @@
+# Yelp Scrapper
+
+## Description
+This python script is used to get restaurant data from yelp website, including name, cuisine, address, rating, review counts and zip code.
+
+## Implementation
+please replace API_key with your API_key obtained from https://www.yelp.com/developers/v3/manage_app
\ No newline at end of file
diff --git a/Web-Scraping/Yelp-Scrapper/scrapper.py b/Web-Scraping/Yelp-Scrapper/scrapper.py
new file mode 100644
index 0000000..63a3f97
--- /dev/null
+++ b/Web-Scraping/Yelp-Scrapper/scrapper.py
@@ -0,0 +1,35 @@
+import requests
+import decimal
+import csv
+
+available_cuisines = ['french', 'italian', 'spanish', 'chinese', 'japanese', 'indian', 'korean', 'american', 'mexican']
+# please replace location with the location you preferred
+location = 'manhattan'
+restaurants = {}
+
+file = open('yelp_data.csv', 'a', encoding='utf-8')
+writer = csv.writer(file)
+id = []
+
+for cuisine in available_cuisines:
+    for offset in range(0, 999, 50):
+        params = {
+            'term': cuisine,
+            'location': location,
+            'offset': offset,
+            'limit': 50
+        }
+
+        headers = {
+            # please replace API_key with your API_key obtained from https://www.yelp.com/developers/v3/manage_app
+            'Authorization': 'Bearer API_Key'
+        }
+
+        response = requests.get(url='https://api.yelp.com/v3/businesses/search', params=params, headers=headers)
+        restaurants = response.json()['businesses']
+        for restaurant in restaurants:
+            if restaurant['id'] not in id:
+                id.append(restaurant['id'])
+                writer.writerow([restaurant['id'], restaurant['name'], cuisine, ", ".join(restaurant['location']['display_address']),
+                                 decimal.Decimal(str(restaurant['coordinates']['latitude'])), decimal.Decimal(str(restaurant['coordinates']['longitude'])),
+                                 decimal.Decimal(str(restaurant['rating'])), restaurant['review_count'], restaurant['location']['zip_code']])
\ No newline at end of file