I have written code to extract tweets from a list of users [handles]. I am writing the information to a .txt file called "results".
with open("results", "w") as fp:
for handle in handles:
print("Analyzing tweets from " + handle + "...")
user = api.get_user(id=handle)
fp.write("Handle: " + handle + "\n")
fp.write("Name: " + user.name + "\n")
fp.write("Description: " + str(user.description.encode(sys.stdout.encoding, errors='replace')) + "\n")
fp.write("Followers: " + str(user.followers_count) + "\n")
fp.write("Following: " + str(user.friends_count) + "\n")
tweet_counter = 0
prosocial_tweets_count = 0
regular_tweets_count = 0
all_tweets = []
social_tweets_len = []
regular_tweets_len = []
social_tweets_valence = []
regular_tweets_valence = []
regular_attachments = 0
social_attachments = 0
for tweet in tweepy.Cursor(api.user_timeline, id=user.id).items():
#control for timeline
dt = tweet.created_at
if dt > date_until:
continue
if dt < date_from:
break # XXX: I hope it's OK to break here
if include_retweets == "no" and tweet.text.startswith("RT"):
continue
if include_replies == "no" and tweet.in_reply_to_user_id:
continue
tweet_counter += 1
for word in vocabulary:
if word in tweet.text.lower():
#increase count of pro social tweets
prosocial_tweets_count += 1
#clean the tweet for valence analysis
clean = TextBlob(tweet.text.lower())
#calculate valence
valence = clean.sentiment.polarity
#append the valence to a list
social_tweets_valence.append(valence)
#append the length of the tweet to a list
social_tweets_len.append(len(tweet.text))
#check if there is an attachment
counting = tweet.text.lower()
counting_attachments = counting.count(" https://t.co/")
social_attachments = social_attachments + counting_attachments
#write date
fp.write(" * " + str(dt) + "\n")
#write the tweet
fp.write(" " + str(tweet.text.encode(sys.stdout.encoding, errors='replace')) + "\n")
#write the length of the tweet
fp.write(" Length of tweet " + str(len(tweet.text)) + "\n")
#write the valence of the tweet
fp.write(" Tweet valance " + str(valence) + "\n")
#write the retweets of the tweet
fp.write(" Retweets count: " + str(tweet.retweet_count) + "\n")
#write the likes of the tweet
fp.write(" Likes count: " + str(tweet.favorite_count) + "\n")
# Report each tweet only once whenever it contains more than one prosocial words
break
else:
#this code runs if the tweet is not prosocial
regular_tweets_count += 1
clean = TextBlob(tweet.text.lower())
valence = clean.sentiment.polarity
counting = tweet.text.lower()
counting_attachments = counting.count(" https://t.co/")
regular_attachments = regular_attachments + counting_attachments
regular_tweets_valence.append(valence)
regular_tweets_len.append(len(tweet.text))
attachments = regular_attachments + social_attachments
I was wondering whether anyone knows of any nice way to check if the tweets contains images or videos. I would also like to create a list of average use of images and videos per user.