Created
December 22, 2020 20:22
-
-
Save oliver-batey/146522befd1f7321948ec0fb63aec8fd to your computer and use it in GitHub Desktop.
Instagram Post Info
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
import pandas as pd | |
from instascrape import Post, Profile | |
def get_post_data(post_object, | |
attributes=['caption', | |
'upload_date', | |
'location', | |
'likes', | |
'comments', | |
'id']): | |
''' | |
Inputs: | |
post_object: an instascrape Post object | |
attributes: list of keys we want to extract from post_object | |
Returns: | |
Dictonary containing the key-value pairs specifed in attributes | |
''' | |
return {key:post_object[key] for key in attributes} | |
if __name__ == '__main__': | |
#Substitute 'username' with the name of the instagram | |
#profile you want to scrape (as a string) | |
profile = Profile('username') | |
#Scrape the profile | |
profile.scrape() | |
#Get list of the recent posts | |
recents = profile.get_recent_posts() | |
#Build dataframe | |
data = pd.DataFrame([get_post_data(post) for post in recents]) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment