CODEWITHSUNDEEP
pythonpandasdataframecsv
Poppy
Poppy

Reputation: 31

Altering a column within a CSV in Python

How do i select column "id" within my CSV and add a string to it?

Column ID is a number like "5474548384". I would like to select this column and alter it to add the following: 'https://twitter.com/twitter/statuses/' to create a link. Screenshot of CSV is at the bottom of this post

Any suggestions on how to alter this column in my CSV?

import requests
import expansions
import os
import json
import pandas as pd
import csv
import sys
import time


bearer_token = "removed for privacy "

search_url = "https://api.twitter.com/2/tweets/search/all"

query_params = {'query': '("covid") i -is:retweet -is:verified -baby -lotion -shampoo lang:en has:geo place_country:US',
                'tweet.fields':'created_at,lang,text,geo,author_id,id,public_metrics,referenced_tweets',
                'expansions':'geo.place_id,author_id', 
                'place.fields':'contained_within,country,country_code,full_name,geo,id,name,place_type',
                'user.fields':'description,username,id',
                'start_time':'2021-02-27T00:00:01.000Z',
                'end_time':'2021-02-27T23:30:00.000Z',
                'max_results':'10'}

def create_headers(bearer_token):
    headers = {"Authorization": "Bearer {}".format(bearer_token)}
    return headers


def connect_to_endpoint(url, headers, params):
    response = requests.request("GET", search_url, headers=headers, params=params)

    if response.status_code != 200:
        raise Exception(response.status_code, response.text)
    return response.json()


def main():
    headers = create_headers(bearer_token)
    json_response = connect_to_endpoint(search_url, headers, query_params)

    json_response = expansions.flatten(json_response) 
    df = pd.json_normalize(json_response['data'])
    drop = df['author.description'].str.contains('news')
    
    result = df[-drop]
    result.to_csv("mydata.csv", encoding="utf-8-sig")
    
if __name__ == "__main__":
    main()

enter image description here

Upvotes: 1

Views: 46

Answers (1)

Yamuk
Yamuk

Reputation: 769

After getting the dataframe, you can add the prefix like this:

prefix = 'https://twitter.com/twitter/statuses/'
df['id'] = prefix + df['id'].astype(str)

Upvotes: 2

Related Questions