tableau_public_api/Python/get_featured_authors.py at main · wjsutton/tableau_public_api · GitHub

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 json
import urllib3
import pandas as pd
import math

http = urllib3.PoolManager()

fa_call = 'https://public.tableau.com/public/apis/bff/discover/v3/authors/tableau-visionaries?startIndex=0&limit=12'
fa_json = json.loads(http.request('GET',fa_call).data)
featured_authors = pd.json_normalize(fa_json['contents'], max_level=0)

n_featured_authors = len(featured_authors)
author_loops = range(n_featured_authors)

# initialise dataframes
profile_df =[]
websites_df =[]
workbook_df =[]

for i in range(n_featured_authors):
    your_username = featured_authors['profileName'][i]
    print("Working on " + featured_authors['profileName'][i] +"'s profile")
    profile_call = "https://public.tableau.com/profile/api/" + your_username

    tableau_profile = json.loads(http.request('GET',profile_call).data)
    profile = pd.json_normalize(tableau_profile, max_level=0)
    profile['author_description'] = featured_authors['bio'][i]

    del profile['websites']
    if 'address' in profile.columns:
        del profile['address']

    profile_df.append(profile)

    websites = pd.json_normalize(tableau_profile['websites'], max_level=0)
    websites['profileName'] = your_username
    websites_df.append(websites)

    n_workbooks = profile['visibleWorkbookCount']
    workbook_loops = math.ceil(n_workbooks / 50)

    for j in range(workbook_loops):
        print('Getting workbooks page: ' + str(j))
        start = j * 50
        workbook_call = 'https://public.tableau.com/public/apis/workbooks?profileName=' + your_username + '&start='+str(start)+'&count=50&visibility=NON_HIDDEN'
        tableau_workbooks = json.loads(http.request('GET',workbook_call).data)
        workbooks = pd.json_normalize(tableau_workbooks['contents'], max_level=0)
        workbooks['profileName'] = your_username
        workbook_df.append(workbooks)

# Combine data frames from loop
profile_df = pd.concat(profile_df)
workbook_df = pd.concat(workbook_df)
websites_df = pd.concat(websites_df)

# Get VOTD data
votd_df =[]
start = 0
while start != -1:
    print('Getting VOTDs from index: ' + str(start))
    votd = json.loads(http.request('GET',"https://public.tableau.com/public/apis/bff/discover/v2/vizzes/viz-of-the-day?startIndex=" + str(start) + "&limit=12").data)
    votd_df.append(pd.json_normalize(votd['contents'], max_level=1))
    start = votd['next']

# Combine data frames from loop
votd_df = pd.concat(votd_df)

votd_df['VOTD_flag'] = 'VOTD'
votd_lookup = votd_df[['workbookRepoUrl','VOTD_flag']]

workbook_df = pd.merge(workbook_df,votd_lookup,how='left',on='workbookRepoUrl')

# Save locally
profile_df.to_csv('fa_profiles.csv', index=False)
workbook_df.to_csv('fa_workbooks.csv', index=False)
websites_df.to_csv('fa_websites.csv', index=False)