Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

multiple stories #3

Merged
merged 35 commits into from
Apr 12, 2022
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
35 commits
Select commit Hold shift + click to select a range
ecb79ac
multiple stories
sspathare97 Apr 10, 2022
38cf654
location bottleneck
sspathare97 Apr 10, 2022
83fdc99
images
sspathare97 Apr 10, 2022
957aa2b
image fix
sspathare97 Apr 10, 2022
2d13db2
kbint
sspathare97 Apr 10, 2022
283d95e
more
sspathare97 Apr 10, 2022
5c0def6
gcp
sspathare97 Apr 10, 2022
cda1acf
error time
sspathare97 Apr 10, 2022
60f1f01
more data
sspathare97 Apr 10, 2022
2f6275e
len
sspathare97 Apr 10, 2022
f73782c
location collection
sspathare97 Apr 11, 2022
781abf4
saved locations
sspathare97 Apr 11, 2022
50aa702
geocode sample
sspathare97 Apr 11, 2022
ff319bb
bing limit
sspathare97 Apr 11, 2022
2456a26
geocode gmaps
sspathare97 Apr 11, 2022
83effd6
log
sspathare97 Apr 11, 2022
8e31596
node batch
sspathare97 Apr 11, 2022
3e9f17e
30 percent
sspathare97 Apr 11, 2022
d8d8156
more
sspathare97 Apr 11, 2022
24aae61
more
sspathare97 Apr 11, 2022
0ebfeb2
2k
sspathare97 Apr 11, 2022
880786c
more
sspathare97 Apr 11, 2022
06ecf2b
logging
sspathare97 Apr 11, 2022
0f5441b
data
sspathare97 Apr 11, 2022
4487f01
more data
sspathare97 Apr 11, 2022
ca6456b
49k
sspathare97 Apr 11, 2022
51481c1
timeout retry
sspathare97 Apr 11, 2022
fe34aa6
finished
sspathare97 Apr 11, 2022
6be9790
refactor
sspathare97 Apr 11, 2022
25ff637
locations json
sspathare97 Apr 12, 2022
fa69684
location trim
sspathare97 Apr 12, 2022
2afaa49
locations null
sspathare97 Apr 12, 2022
eee5770
locations
sspathare97 Apr 12, 2022
54811f5
unique locations
sspathare97 Apr 12, 2022
925690f
queries
sspathare97 Apr 12, 2022
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion .gitignore
Original file line number Diff line number Diff line change
@@ -1,3 +1,6 @@
mongodbconfig.py
env.py
*.pyc
pycache/*
pycache/*
node_modules/
.env
16 changes: 0 additions & 16 deletions FailedCalls.csv

This file was deleted.

2 changes: 2 additions & 0 deletions NYTSampleResponse.py

Large diffs are not rendered by default.

File renamed without changes.
7 changes: 7 additions & 0 deletions extras/duration.csv
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
2000,2017,18,0:36:06.103692
2020,2021,2,0:03:35.893334
2021,2020,2,0:03:52.235375
2000,2021,22,0:26:31.983755
2000,1980,21,0:25:35.200808
1979,1960,20,0:24:04.912506
1959,1950,10,0:12:20.685440
45 changes: 45 additions & 0 deletions extras/geocode-gmaps.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,45 @@
import os, sys, inspect, json, requests
currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
parentdir = os.path.dirname(currentdir)
sys.path.insert(0, parentdir)

import env


def extract_lat_long_via_location(location):
base_url = "https://maps.googleapis.com/maps/api/geocode/json"
endpoint = f"{base_url}?address={location}&key={env.google_api_key}"
r = requests.get(endpoint)
if r.status_code not in range(200, 299):
return None
try:
'''
This try block incase any of our inputs are invalid. This is done instead
of actually writing out handlers for all kinds of responses.
'''
results = r.json()['results'][0]
latitude = results['geometry']['location']['lat']
longitude = results['geometry']['location']['lng']
return latitude, longitude
except:
return None


# locations = ['PHILIPSE MANOR HALL (YONKERS, NY)', 'BALDWIN', 'GREAT NECK ESTATES, NY', 'Europe', 'North Pole']
locations = json.load(open('locations.json', 'r'))
# print(locations)

start = 0
# end = 4
end = len(locations)
locations = locations[start:end]
for index, location in enumerate(locations):
print(f"Fetching location {start + index}")
res = extract_lat_long_via_location(location)
op = f"{index},\"{location}\","
if res is None:
op += "null,null"
else:
op += f"{res[0]},{res[1]}"
with open('locationres.csv', 'a') as f:
f.write(f"{op}\n")
19 changes: 19 additions & 0 deletions extras/geocode.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
import geocoder, os, sys, inspect, json
currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
parentdir = os.path.dirname(currentdir)
sys.path.insert(0, parentdir)

import env

# locations = ['PHILIPSE MANOR HALL (YONKERS, NY)', 'BALDWIN', 'GREAT NECK ESTATES, NY', 'Europe', 'North Pole']
locations = json.load(open('locations.json', 'r'))
# print(locations)

locations = locations[:50]

g = geocoder.bing(locations, method='batch', key=env.bing_api_key)
res = []
for result in g:
res.append(result.latlng)
# print(res)
json.dump(res, open('locationres.json', 'w'), indent=2)
File renamed without changes.
22 changes: 22 additions & 0 deletions extras/location1res.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
[
[
40.930793762207,
-73.8982925415039
],
[
40.6630020141602,
-73.610710144043
],
[
40.7853736877441,
-73.7383270263672
],
[
54.2612228393555,
17.6698455810547
],
[
64.7503356933594,
-147.354187011719
]
]
199 changes: 199 additions & 0 deletions extras/locationres.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,199 @@
[
[
32.5399589538574,
-82.9045486450195
],
[
40.7130470275879,
-74.0072326660156
],
[
38.6353569030762,
-90.2009887695313
],
[
39.1720542907715,
-120.139579772949
],
[
29.6641635894775,
-95.0192794799805
],
[
40.7668914794922,
-73.92138671875
],
[
39.9510612487793,
-75.1656188964844
],
[
40.6630020141602,
-73.610710144043
],
[
-23.6573390960693,
-46.5322494506836
],
[
38.6158447265625,
-122.871940612793
],
[
40.930793762207,
-73.8982925415039
],
[
32.7830619812012,
-79.934440612793
],
[
22.345308303833,
76.2188339233398
],
[
18.9492219805194,
72.8232993261008
],
[
40.8095054626465,
-73.9635238647461
],
[
40.7853736877441,
-73.7383270263672
],
[
32.842155456543,
-104.401077270508
],
[
40.8875923156738,
-72.9422378540039
],
[
40.7471361500429,
-73.9779305502094
],
[
51.1455917358398,
-120.116546630859
],
[
48.6476936340332,
-118.73804473877
],
[
30.4488182067871,
-96.6569213867188
],
[
-27.4830551147461,
153.00666809082
],
[],
[
46.7779655456543,
-56.1783142089844
],
[
40.795970916748,
-74.4944839477539
],
[
41.0712776184082,
-72.3392105102539
],
[
40.5339622497559,
-74.173828125
],
[
0.0401530005037785,
-51.056957244873
],
[
31.9490756988525,
-81.311653137207
],
[
50.2114372253418,
-5.48076105117798
],
[
41.0282974243164,
-75.6701889038086
],
[
40.895637512207,
71.7276916503906
],
[
-26.2129383087158,
28.1638259887695
],
[
46.2218055725098,
15.3103542327881
],
[
51.0931243896484,
10.3802080154419
],
[
41.6258201599121,
-74.7402038574219
],
[
44.4759902954102,
-73.2109985351563
],
[
17.00599,
99.82669
],
[
34.0522384643555,
-118.243347167969
],
[
43.4570465087891,
-71.2216796875
],
[
39.8280309129997,
-77.2365792157431
],
[
40.7204170227051,
-73.7432327270508
],
[
40.8527565002441,
-74.0431671142578
],
[
38.5467262268066,
-121.744338989258
],
[
38.4847297668457,
-98.3801803588867
],
[
42.4404945373535,
-76.4957046508789
],
[
40.4421691894531,
-79.9949569702148
],
[
42.5171356201172,
-82.9255218505859
],
[
36.7316551208496,
-119.785858154297
]
]
Loading