import requests
import numpy as np
import pandas as pd
import argparse
import json
from string import Template
from datetime import datetime, timezone
import sys
# gets instagram "locations" around a particular lat/lng using internal API
# (requires session cookie for authentication)
def get_instagram_locations(lat, lng, cookie):
locs = requests.get("https://www.instagram.com/location_search/?latitude=" + str(lat) + "&longitude=" + str(lng) + "&__a=1", headers={
'Cookie': cookie
}).json()
return locs['venues']
def get_instagram_locations_by_query(query):
locs = requests.get("https://www.instagram.com/web/search/topsearch/?context=place&query=" + query).json()
return [v['place']['location'] for v in locs['places']]
# queries the instagram location API for several points around a central lat/lng
# in order to return additional results
def get_fuzzy_locations(lat, lng, cookie, sigma=2):
locs = get_instagram_locations(lat, lng, cookie)
std_lat = np.std([v['lat'] for v in locs if 'lat' in v])
std_lng = np.std([v['lng'] for v in locs if 'lng' in v])
for delta_lat in range(-sigma, sigma+1):
for delta_lng in range(-sigma, sigma+1):
new_locs = get_instagram_locations(lat + delta_lat * std_lat, lng + delta_lng * std_lng, cookie)
loc_ids = [v['external_id'] for v in locs]
for loc in new_locs:
if loc['external_id'] not in loc_ids:
locs.append(loc)
return locs
# converts list of instagram locations into valid geojson
def make_geojson(locations):
features = []
for location in [location for location in locations if 'lng' in location]:
feature = {
"type": "Feature",
"geometry": {
"type": "Point",
"coordinates": [location["lng"], location["lat"]]
},
"properties": location}
features.append(feature)
return {"type": "FeatureCollection", "features": features}
def encode_date(date_str: str):
'''Convert date into Instagram "snowflake" ID'''
try:
date = datetime.strptime(date_str, '%Y-%m-%d')
except ValueError:
try:
date = datetime.strptime(date_str, '%Y-%m-%d')
except ValueError:
print('Unable to parse date. Please use format "yyyy-mm-dd".', file=sys.stderr)
sys.exit(1)
date = date.replace(hour=23, minute=59, second=59, tzinfo=timezone.utc)
date_ts = int(date.timestamp()) * 1000 # milliseconds
insta_epoch = date_ts - 1314220021300
max_id_num = insta_epoch << 23
return str(max_id_num)
html_template = '''
Instagram location visualizations
'''
def main():
parser = argparse.ArgumentParser(description="Get a list of Instagram locations near a lat/lng")
parser.add_argument("--cookie", action="store", dest="cookie")
parser.add_argument("--json", action="store", dest="output")
parser.add_argument("--geojson", action="store", dest="geojson")
parser.add_argument("--map", action="store", dest="map")
parser.add_argument("--csv", action="store", dest="csv")
parser.add_argument("--lat", action="store", dest="lat")
parser.add_argument("--lng", action="store", dest="lng")
parser.add_argument("--date", action="store", dest="date")
parser.add_argument("--ids", action="store", dest="dump_ids")
args = parser.parse_args()
cookie = args.cookie
date_var = ''
if args.date is not None:
date_var = '?max_id=' + encode_date(args.date)
locations = get_fuzzy_locations(float(args.lat), float(args.lng), cookie)
if (args.output):
json.dump(locations, open(args.output, 'w'))
if (args.geojson):
json.dump(make_geojson(locations), open(args.geojson, 'w'))
if (args.map):
s = Template(html_template)
viz = s.substitute(lat=args.lat, lng=args.lng, locs=json.dumps(make_geojson(locations)), date_var=date_var)
f = open(args.map, 'w')
f.write(viz)
f.close()
if (args.csv):
df = pd.DataFrame(locations)
df['url'] = df['external_id'].apply(lambda v: 'https://www.instagram.com/explore/locations/' + str(v) + date_var)
df.to_csv(args.csv)
if (args.dump_ids):
ids = map(lambda loc: str(loc['external_id']), locations)
with open(args.dump_ids, 'w') as f:
f.write('\n'.join(ids))
if __name__ == "__main__":
main()