-
-
Save fordhamedu/01a3d04067274de9f0188cda50e8a1ed to your computer and use it in GitHub Desktop.
Get WeWork Office Locations - Latitude/Longitude and other info - see https://team.carto.com/u/sheehan-carto/builder/30233d8a-9661-11e6-9889-0e3ff518bd15/embed
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
import urllib2 | |
import json | |
import csv | |
import pandas as pd | |
import numpy as np | |
import decimal | |
D = decimal.Decimal | |
url = "https://www.wework.com/locations/all" | |
data = urllib2.urlopen(url).read() | |
data = json.loads(data) | |
ouJSON = 'data/wework.json' | |
with open(ouJSON, 'w') as f: | |
json.dump(data, f) | |
varsList = ['uuid','zip','line1','location_path','city','latitude','longitude','path','slug','open_for_touring','name','phone','image_url','location_address','format_desk_pricing','format_office_pricing'] | |
dataList = [] #dictionaries and json is cool, but just being lazy with this list. | |
for i in range(len(data)): | |
locVarsList = [] | |
for j in varsList: | |
locVarsList.append(data[i][j]) | |
dataList.append(locVarsList) | |
df = pd.DataFrame(dataList, columns=varsList) | |
df['url'] = 'https://www.wework.com' + df.path.map(str) | |
df['format_desk_pricing_us'] = (df['format_desk_pricing'].str.replace(r'[^-+\d.]', '').astype(D)) | |
df['format_office_pricing_us'] = (df['format_office_pricing'].str.replace(r'[^-+\d.]', '').astype(D)) | |
df['format_desk_pricing_us'] = df['format_desk_pricing_us'].astype(float) | |
df['format_office_pricing_us'] = df['format_office_pricing_us'].astype(float) | |
print df.dtypes | |
df['format_desk_pricing_us'] = np.where(df['format_desk_pricing_us'] <= 800, df['format_desk_pricing_us'], 0) #lazy hack to remove foreign values higher than the highest us values | |
df['format_office_pricing_us'] = np.where(df['format_office_pricing_us'] <= 1400, df['format_office_pricing_us'], 0) #lazy hack to remove foreign values higher than the highest us values | |
df.to_csv('data/weworklocations_20161019.csv',index=False, encoding='utf-8') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment