1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 | import facebook import pandas as pd import requests token = '' fields = [ 'id', 'name', 'username', 'about', 'website', 'link', 'category', 'checkins', 'description', 'fan_count', 'talking_about_count', 'price_range', 'is_always_open', #'featured_video', #'founded', #'general_info', #'hours', #'location', #'mission', #'phone', #'products', #'restaurant_services', #'single_line_address', ] fields = ','.join(fields) exclude = [ 'Apartment & Condo Building', 'Home', 'Hotel', 'Hotel & Lodging', 'Inn', 'Men\'s Clothing Store', 'Night Market', 'Parking Garage / Lot', 'Performance & Event Venue', 'Real Estate', 'Region', 'Shopping & Retail', 'Tour Agency', 'Vacation Home Rental', ] graph = facebook.GraphAPI(access_token = token,version='2.10') fc = graph.search(type='place',q='逢甲+夜市',center="24.1759238,120.6456042",distance=1000,fields=fields) pagelist = [] while True: if 'data' in fc: pagelist.extend(fc['data']) else: break if 'paging' in fc: if 'next' in fc['paging']: fc = requests.get(fc['paging']['next']).json() else: break pagelist = [page for page in pagelist if page['is_always_open']!=True] pagelist = [page for page in pagelist if page['category'] not in exclude] writer = pd.ExcelWriter('fb.xlsx') fcdata = pd.DataFrame(pagelist) fcdata.to_excel(writer,'pages') writer.save() |
Direct link: https://paste.plurk.com/show/rD2vYLnOGALmxR1TFqzF