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
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
|
"""
Converts directory of JSON API output files to CSV format
"""
from glob import glob
import os
from os.path import join
from pathlib import Path
import click
from app.settings import types
from app.utils import click_utils
from app.settings import app_cfg as cfg
from app.utils import logger_utils
import pandas as pd
from PIL import Image, ImageOps, ImageFilter
from app.utils import file_utils, im_utils
data_types = ['nsid_url', 'nsid_profile']
log = logger_utils.Logger.getLogger()
@click.command()
@click.option('-i', '--input', 'opt_fp_in', required=True,
help='Input directory')
@click.option('-o', '--output', 'opt_fp_out', required=True,
help='Output file')
@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None),
help='Slice list of files')
@click.option('-q', '--query', 'opt_query', required=True, type=click.Choice(data_types),
help='Flickr API data type')
@click.option('-f', '--force', 'opt_force', is_flag=True,
help='Force overwrite')
@click.pass_context
def cli(ctx, opt_fp_in, opt_fp_out, opt_slice, opt_force, opt_query):
"""Fetches Flickr API for user info. Saves to JSON"""
from tqdm import tqdm
from glob import glob
import json
# -------------------------------------------------
# process
if Path(opt_fp_out).is_file() and not opt_force:
log.error('File exists. Use "--force" to overwrite it')
return
fp_files = glob(join(opt_fp_in, '*.json'))
fp_files = [f for f in fp_files if 'error' not in f]
if opt_slice:
fp_files = fp_files[opt_slice[0]:opt_slice[1]]
log.debug(f'Found {len(fp_files)} files')
items = []
"""
{
"stat": "ok",
"user": {
"id": "95216244@N04",
"username": {
"_content": "AfghanistanWien"
}
}
}
"""
"""
{
"profile": {
"city": "Oslo",
"country": "Norway",
"facebook": "",
"first_name": "US Embassy",
"hometown": "Oslo",
"id": "133886098@N05",
"instagram": "",
"join_date": "1436521589",
"last_name": "Oslo",
"nsid": "133886098@N05",
"occupation": "",
"pinterest": "",
"profile_description": "This is the official Flickr profile of the U.S. Embassy in Oslo, Norway. Contact us: osloirc@state.gov.",
"showcase_set": "72157677372281094",
"showcase_set_title": "Profile Showcase",
"tumblr": "",
"twitter": "",
"website": "http://norway.usembassy.gov/index.html"
},
"stat": "ok"
}
"""
# Convert to |nsid|username|
for fp_file in tqdm(fp_files):
metadata = file_utils.load_json(fp_file)
if opt_query == 'nsid_url':
path_alias = Path(fp_file).stem
metadata = metadata.get('user')
nsid = metadata.get('id')
username = metadata.get('username').get('_content')
url = f'https://www.flickr.com/photos/{path_alias}'
obj = {
'nsid': nsid,
'username': username,
'url': url,
'path_alias': path_alias,
'filename': f'{path_alias}.json'
}
elif opt_query == 'nsid_profile':
obj = metadata.get('profile')
items.append(obj)
# conver to DataFrame
df = pd.DataFrame.from_dict(items)
df.to_csv(opt_fp_out, index=False)
log.info(f'Wrote {len(df)} to {opt_fp_out}')
|
