Get twitter user's photo url's from tweets - download all images from twitter user

tweet_image_dumper.py

#!/usr/bin/env python
# encoding: utf-8

import tweepy #https://github.com/tweepy/tweepy
import csv
import sys

#Twitter API credentials
consumer_key = ""
consumer_secret = ""
access_key = ""
access_secret = ""


def get_all_tweets(screen_name):
        #Twitter only allows access to a users most recent 3240 tweets with this method

        #authorize twitter, initialize tweepy
        auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
        auth.set_access_token(access_key, access_secret)
        api = tweepy.API(auth)

        #initialize a list to hold all the tweepy Tweets
        alltweets = []

        #make initial request for most recent tweets (200 is the maximum allowed count)
        new_tweets = api.user_timeline(screen_name = screen_name,count=1)

        #save most recent tweets
        alltweets.extend(new_tweets)

        #save the id of the oldest tweet less one
        oldest = alltweets[-1].id - 1

        #keep grabbing tweets until there are no tweets left to grab
        while len(new_tweets) > 0:
                print "getting tweets before %s" % (oldest)

                #all subsequent requests use the max_id param to prevent duplicates
                new_tweets = api.user_timeline(screen_name = screen_name,count=200,max_id=oldest)

                #save most recent tweets
                alltweets.extend(new_tweets)

                #update the id of the oldest tweet less one
                oldest = alltweets[-1].id - 1

                print "...%s tweets downloaded so far" % (len(alltweets))

        #go through all found tweets and remove the ones with no images 
        outtweets = [] #initialize master list to hold our ready tweets
        for tweet in alltweets:
                #not all tweets will have media url, so lets skip them
                try:
                        print tweet.entities['media'][0]['media_url']
                except (NameError, KeyError):
                        #we dont want to have any entries without the media_url so lets do nothing
                        pass
                else:
                        #got media_url - means add it to the output
                        outtweets.append([tweet.id_str, tweet.created_at, tweet.text.encode("utf-8"), tweet.entities['media'][0]['media_url']])

        #write the csv  
        with open('%s_tweets.csv' % screen_name, 'wb') as f:
                writer = csv.writer(f)
                writer.writerow(["id","created_at","text","media_url"])
                writer.writerows(outtweets)

        pass


if __name__ == '__main__':
        #pass in the username of the account you want to download
        get_all_tweets("WansteadWomble")

Useful practice case for me, thanks a lot.

but can we get all pictures in one tweet?

Hi,
Is there anyway I can get hashtag as well in a separate column?

dont save in csv

dont save in csv

just remove the 'b' from 'wb'

Can't we use this to get URL of link shared by twitter

Hey, will this media method also download video URLs or it works only for images?

Hey, will this media method also download video URLs or it works only for images?

Looks like it won't. The script the author provided only shows thumbnail of the video. In order to get the link of the video, you would have to go under tweet.extended_entities["media"][0]["video_info"].

Now I am getting this error:
AttributeError: 'Status' object has no attribute 'entities'
Has there being a change in the API or something?

then you just download all of them with your favourite downloader... for example:
wget -i filename.csv

Where and how to write the command "wget -i '% s_tweets.csv'" to download a picture?

I'm a newbie. Does not work.

Thanks in advance

My edits in the code, downloads images :

#!/usr/bin/env python 3
# encoding: utf-8

import tweepy #https://github.com/tweepy/tweepy
import csv
import sys
import wget 


#Twitter API credentials
consumer_key = ""
consumer_secret = ""
access_key = ""
access_secret = ""


def get_all_tweets(screen_name):
        #Twitter only allows access to a users most recent 3240 tweets with this method

        #authorize twitter, initialize tweepy
        auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
        auth.set_access_token(access_key, access_secret)
        api = tweepy.API(auth)

        #initialize a list to hold all the tweepy Tweets
        alltweets = []

        #make initial request for most recent tweets (200 is the maximum allowed count)
        new_tweets = api.user_timeline(screen_name = screen_name,count=1)

        #save most recent tweets
        alltweets.extend(new_tweets)

        #save the id of the oldest tweet less one
        oldest = alltweets[-1].id - 1

        #keep grabbing tweets until there are no tweets left to grab
        while len(new_tweets) > 0:
                print ("getting tweets before получаем перед %s" % (oldest))

                #all subsequent requests use the max_id param to prevent duplicates
                new_tweets = api.user_timeline(screen_name = screen_name,count=200,max_id=oldest)

                #save most recent tweets
                alltweets.extend(new_tweets)

                #update the id of the oldest tweet less one
                oldest = alltweets[-1].id - 1

                print ("...%s tweets downloaded so far загружены на данный момент" % (len(alltweets)))

        #go through all found tweets and remove the ones with no images 
        outtweets = [] #initialize master list to hold our ready tweets
        for tweet in alltweets:
                #not all tweets will have media url, so lets skip them
                try:
                        print (tweet.entities['media'][0]['media_url'])
                        wget.download(tweet.entities['media'][0]['media_url'])
                except (NameError, KeyError):
                        #we dont want to have any entries without the media_url so lets do nothing
                        pass
                else:
                        #got media_url - means add it to the output
                        outtweets.append([tweet.id_str, tweet.created_at, tweet.text, tweet.entities['media'][0]['media_url']])

        #write the csv  
        with open('%s_tweets.csv' % screen_name, 'w', encoding='utf-8') as f:
                writer = csv.writer(f)
                writer.writerow(["id","created_at","text","media_url"])
                writer.writerows(outtweets)
                

        pass


if __name__ == '__main__':
        #pass in the username of the account you want to download
        get_all_tweets("nameofparse")