Created
November 28, 2012 15:30
-
-
Save mapmeld/4161980 to your computer and use it in GitHub Desktop.
Scrape Instagram geo-photos with a certain tag and date range
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
# InstaScan.py | |
# prints a CSV of all geolocated Instagram photos with a certain tag between dates | |
import json | |
import urllib | |
import datetime | |
createdate = datetime.datetime.now() | |
latestprint = datetime.datetime(2012, 11, 11) # Nov 11, 2012 | |
earliestprint = datetime.datetime(2012, 10, 28) # Oct 28, 2012 | |
access_token = "143532409.1fb234f.9abac8ccd7324f6cbc33fb6e2a14a4ea" | |
max_id = "" | |
tagname = "sandy" | |
csvout = open('sandygram.csv', 'w') | |
print "ID, CREATED_TIME, LATITUDE, LONGITUDE, INSTAGRAM URL, PHOTO URL" | |
csvout.write("ID,CREATED_TIME,LATITUDE,LONGITUDE,INSTAGRAM_URL,PHOTO_URL\n") | |
while(createdate > earliestprint): | |
apiout = urllib.urlopen("https://api.instagram.com/v1/tags/" + tagname + "/media/recent?max_id=" + max_id + "&access_token=" + access_token).read() | |
photopage = None | |
try: | |
photopage = json.loads( apiout ) | |
except: | |
print apiout | |
continue | |
photos = photopage["data"] | |
for photo in photos: | |
createdate = datetime.datetime.fromtimestamp(int(photo["created_time"]) ) | |
#print createdate | |
if(createdate < latestprint and createdate > earliestprint): | |
# inside timestamp bounds | |
if((photo.has_key("location") == True) and (photo["location"] is not None) and (photo["location"].has_key("latitude") == True)): | |
# has a location | |
latitude = str(photo["location"]["latitude"]) | |
longitude = str(photo["location"]["longitude"]) | |
# print out CSV format | |
print "\"" + (photo["id"] or "") + "\"," + (photo["created_time"] or "") + "000," + latitude + "," + longitude + ",\"" + (photo["link"] or "") + "\",\"" + (photo["images"]["standard_resolution"]["url"] or "") + "\"" | |
csvout.write("\"" + (photo["id"] or "") + "\"," + (photo["created_time"] or "") + "000," + latitude + "," + longitude + ",\"" + (photo["link"] or "") + "\",\"" + (photo["images"]["standard_resolution"]["url"] or "") + "\"\n") | |
max_id = photopage["pagination"]["next_max_tag_id"] | |
print "max_id = " + max_id | |
createdate = datetime.datetime.fromtimestamp( int( int( max_id ) / 1000 ) ) |
I'm receiving: KeyError: 'next_max_id' - Instagram
What am I missing?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
http://docs.python-requests.org/en/latest/