RizqiEka

#Restaurant Price for 2
try:
    price_for_2_anchor = driver.find_element_by_xpath("""/html/body/div[1]/div[2]/main/div/section[4]/section/section/article[1]/section[2]/p[1]""")
    price_for_2_text = price_for_2_anchor.text

except NoSuchElementException:
    price_for_2_text = "No Price Data Found"
    pass   
            
if (price_for_2_text[0:2] == 'Rp') or (price_for_2_text[0:2] == 'No'):

RizqiEka

#Restaurant Additional Information
addt_info_list = []
addt_info_bigelt = driver.find_element_by_xpath("""/html/body/div[1]/div[2]/main/div/section[4]/section/section/article[1]/section[2]/div[3]""")
addt_info_eltlist = addt_info_bigelt.find_elements_by_tag_name('p')

for addt_info_anchor in addt_info_eltlist:
    addt_info_text = addt_info_anchor.text
    addt_info_list.append(addt_info_text)

rest_info.append(addt_info_list)

RizqiEka

#Restaurant Latitude and Longitude
map_url = driver.find_element_by_xpath("""/html/body/div[1]/div[2]/main/div/section[4]/section/article/section/div[2]/a""").get_attribute("href")
lat = map_url[-28:-15]
long = map_url[-14:-1]
rest_lat.append(lat)
rest_long.append(long)
print(f'Scraping Restaurant Latitude-Longitude - {name} - {lat} - {long} - OK')

RizqiEka

# Import Libraries
import requests
import json
import datetime
import pandas as pd

# Define Parameters Dictionary
params = dict()
params['access_token'] = 'XXXXXXXXXXXXXXXXXXX'        # not an actual access token
params['client_id'] = '111111111111'                  # not an actual client id

RizqiEka

# Define Endpoint Parameters
endpointParams = dict()
endpointParams['input_token'] = params['access_token']
endpointParams['access_token'] = params['access_token']

# Define URL
url = params['graph_domain'] + '/debug_token'

# Requests Data
data = requests.get(url, endpointParams)

RizqiEka

print("Token Expires: ", datetime.datetime.fromtimestamp(access_token_data['data']['expires_at']))

RizqiEka

# Define URL
url = params['endpoint_base'] + 'oauth/access_token'

# Define Endpoint Parameters
endpointParams = dict() 
endpointParams['grant_type'] = 'fb_exchange_token'
endpointParams['client_id'] = params['client_id']
endpointParams['client_secret'] = params['client_secret']
endpointParams['fb_exchange_token'] = params['access_token']

RizqiEka

# Define URL
url = params['endpoint_base'] + params['instagram_account_id'] + '/media'

# Define Endpoint Parameters
endpointParams = dict()
endpointParams['fields'] = 'id,caption,media_type,media_url,permalink,thumbnail_url,timestamp,username,like_count,comments_count'
endpointParams['access_token'] = params['access_token']

# Requests Data
data = requests.get(url, endpointParams )

RizqiEka

df = pd.DataFrame(basic_insight['data'])
df.columns = ['id', 'Caption', 'Media_Type', 'Media_URL', 'Permalink', 'Timestamp', 'Username', 'Likes', 'Comments']
df.head()

RizqiEka

media_insight = []

# Loop Over 'Media ID'
for i in basic_insight['data']:
    params['latest_media_id'] = i['id']
    
    # Define URL
    url = params['endpoint_base'] + params['latest_media_id'] + '/insights'

    # Define Endpoint Parameters