scraps facebook ads

scrap_fb_ads.py

import requests
import csv
import time
import sys
reload(sys)
sys.setdefaultencoding('utf8')


access_token=''
url='https://graph.facebook.com/v3.3/ads_archive?fields=impressions,ad_creation_time,ad_creative_body,ad_creative_link_caption,ad_creative_link_description,ad_creative_link_title,ad_delivery_start_time,ad_delivery_stop_time,ad_snapshot_url,currency,demographic_distribution,funding_entity,page_id,page_name,region_distribution,spend'
params = {
'search_terms':'ireland',
'ad_active_status':'ALL',
'ad_type':'POLITICAL_AND_ISSUE_ADS',
'ad_reached_countries':'IE',
'access_token':access_token,
}
res = requests.get(url, params=params)
jres = res.json()

with open('fb_inactive_and_active_ie.csv', 'w') as csvfile:
	spamwriter = csv.writer(csvfile, delimiter=';',
							quotechar='"', quoting=csv.QUOTE_MINIMAL)
	spamwriter.writerow([
		'impressions_low',
		'impressions_up',
		'ad_creation_time',
		'ad_creative_body',
		'currency',
		'ad_delivery_start_time',
		'ad_delivery_stop_time',
		'ad_snapshot_url',
		'demographic_distribution',
		'funding_entity',
		'page_id',
		'page_name',
		'region_distribution',
		'spend_low',
		'spend_up'
		])

	for page in range(100000):
		time.sleep(2)
		print('------------------------------')
		print(page)
		for i in jres['data']:
			if 'funding_entity' not in i:
				i['funding_entity']='?'
				print('no funding entity')
			if 'ad_creative_body' not in i:
				i['ad_creative_body']='?'
				print('no ad_creative_body')
			if 'ad_delivery_stop_time' not in i:
				i['ad_delivery_stop_time']='?'
				print('no ad_delivery_stop_time')

			spamwriter.writerow([
			i['impressions']['lower_bound'],
			i['impressions']['upper_bound'],
			i['ad_creation_time'],
			i['ad_creative_body'],
			i['currency'],
			i['ad_delivery_start_time'],
			i['ad_delivery_stop_time'],
			i['ad_snapshot_url'],
			i['demographic_distribution'],
			i['funding_entity'],
			i['page_id'],
			i['page_name'],
			i['region_distribution'],
			i['spend']['lower_bound'],
			i['spend']['upper_bound'],
			])
		next_page=jres['paging']['next']
		res = requests.get(next_page)
		jres = res.json()