i need your help, i am trying to export the data mining by tweepy to an xlsx file by xlsxwriter, but it is giving error. How can I solve?
EDIT 1:
(One Solution, by user Eli Lopez)
Its worked, but wrote one line... How to solve this?
Or others solutions?
(There are many tweets caught, I need to export in xlsx.)
This is my code:
import json
import csv
import xlsxwriter
import tweepy
from tweepy import OAuthHandler
consumer_key = "my_key"
consumer_secret = "my_key"
access_token = "my_key"
access_token_secret = "my_key"
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
api = tweepy.API(auth)
def tweet_to_xlsx(tweet):
tweet_list = []
tweet_list.append([tweet.user.screen_name, tweet.text])
# tweet_list.append(tweet.text)
workbook = xlsxwriter.Workbook('tweet.xlsx')
worksheet = workbook.add_worksheet()
row = 0
col = 0
for user, tweet in tweet_list:
worksheet.write(row, col, user)
worksheet.write(row, col + 1, tweet)
row += 1
workbook.close()
results = api.search(q=name, lang=lang, count=tweetCount)
for tweet in results:
print(tweet.user.screen_name, "Twittou:", tweet.text)
tweet_to_xlsx(tweet)
Error:
Traceback (most recent call last):
File "extTwitter.py", line 113, in <module>
tweet_to_xlsx(tweet)
File "extTwitter.py", line 60, in tweet_to_xlsx
for user, tweet in tweet_list:
ValueError: too many values to unpack (expected 2)
When you are appending, you're appending items not lists
tweet_list = [USER, TWEET USER, TWEET]
what you want is a list of lists
tweet_list = [[USER, TWEET], [USER, TWEET]]
What your code should be:
tweet_list.append([tweet.user.screen_name, tweet.text])
# you could also use () instead of [] as tuples are faster
Related
I am trying to get all tweets within a certain radius around given coordinates. The script actually works but zero entries are returned. The strange thing is that exactly the same code worked for me a few days ago and now it does not and I am stuck :(
import tweepy
from tweepy import Stream
from tweepy import OAuthHandler
from tweepy.streaming import StreamListener
import json
import pandas as pd
import tweepy
#Twitter credentials for the app
consumer_key = 'xxx'
consumer_secret = 'xxx'
access_key= 'xxx'
access_secret = 'xxx'
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_key, access_secret)
api = tweepy.API(auth, wait_on_rate_limit=True)
#Create list for column names
COLS = ['id','created_at','lang','original text','user_name', 'place', 'place type', 'bbx', 'coordinates']
geo='48.136353, 11.575004, 25km'
def write_tweets(keyword):
#create dataframe from defined column list
df = pd.DataFrame(columns=COLS)
#iterate through pages with given condition
#using tweepy.Cursor object with items() method
for page in tweepy.Cursor(api.search, q=keyword,
include_rts=False,
geocode=geo).pages():
for tweet in page:
#creating string array
new_entry = []
#storing all JSON data from twitter API
tweet = tweet._json
#Append the JSON parsed data to the string list:
new_entry += [tweet['id'], tweet['created_at'], tweet['lang'], tweet['text'],
tweet['user']['name']]
#check if place name is available, in case not the entry is named 'no place'
try:
place = tweet['place']['name']
except TypeError:
place = 'no place'
new_entry.append(place)
try:
place_type = tweet['place']['place_type']
except TypeError:
place_type = 'na'
new_entry.append(place_type)
try:
bbx = tweet['place']['bounding_box']['coordinates']
except TypeError:
bbx = 'na'
new_entry.append(bbx)
#check if coordinates is available, in case not the entry is named 'no coordinates'
try:
coord = tweet['coordinates']['coordinates']
except TypeError:
coord = 'no coordinates'
new_entry.append(coord)
# wrap up all the data into a data frame
single_tweet_df = pd.DataFrame([new_entry], columns=COLS)
df = df.append(single_tweet_df, ignore_index=True)
#get rid of tweets without a place
df_cleaned = df[df.place != 'no place']
print("tweets with place:")
print(len(df[df.place != 'no place']))
print("tweets with coordinates:")
print(len(df[df.coordinates != 'no coordinates']))
df_cleaned.to_csv('tweets_'+geo+'.csv', columns=COLS,index=False)
#declare keywords as a query
keyword='*'
#call main method passing keywords and file path
write_tweets(keyword)
The geocode actually should work like this.
Does anyone have an idea?
When you declare variable geo don't leave any spaces between the comma and the numbers.
It should look like this:
geo='48.136353,11.575004,25km'
I am scraping data from Twitter for tweets, since Twitter has a limitation on this, I am scraping 2500 tweets data every 15 minutes, however, I observe that each run after 15 minutes is returning me the same tweets. Is there any way how I can skip the previously scraped tweet data using some offset.
Thank You!
Here is my code:
# Import libraries
from tweepy import OAuthHandler
#from tweepy.streaming import StreamListener
import tweepy
import csv
import pandas as pd
#import re
#from textblob import TextBlob
#import string
#import preprocessor as p
#import os
import time
# Twitter credentials
consumer_key = ''
consumer_secret = ''
access_key = ''
access_secret = ''
# Pass your twitter credentials to tweepy via its OAuthHandler
auth = OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_key, access_secret)
api = tweepy.API(auth)
def extract_tweets(search_words,date_since,numTweets):
return(tweepy.Cursor(api.search, q=search_words, lang="en", since=date_since, tweet_mode='extended').items(numTweets))
def scrapetweets(search_words, date_since, numTweets, numRuns):
# Define a pandas dataframe to store the date:
db_tweets = pd.DataFrame(columns = ['username', 'acctdesc', 'location', 'following', 'followers', 'totaltweets', 'usercreatedts', 'tweetcreatedts', 'retweetcount', 'text', 'hashtags'])
#db_tweets = pd.DataFrame()
for i in range(numRuns):
tweets = extract_tweets(search_words,date_since,numTweets)
# Store these tweets into a python list
tweet_list = [tweet for tweet in tweets]
print(len(tweet_list))
noTweets = 0
for tweet in tweet_list:
username = tweet.user.screen_name
acctdesc = tweet.user.description
location = tweet.user.location
following = tweet.user.friends_count
followers = tweet.user.followers_count
totaltweets = tweet.user.statuses_count
usercreatedts = tweet.user.created_at
tweetcreatedts = tweet.created_at
retweetcount = tweet.retweet_count
hashtags = tweet.entities['hashtags']
lst=[]
for h in hashtags:
lst.append(h['text'])
try:
text = tweet.retweeted_status.full_text
except AttributeError: # Not a Retweet
text = tweet.full_text
itweet = [username,acctdesc,location,following,followers,totaltweets,usercreatedts,tweetcreatedts,retweetcount,text,lst]
db_tweets.loc[len(db_tweets)] = itweet
noTweets += 1
print(noTweets,itweet)
#filename = "tweets.csv"
#with open(filename, "a", newline='') as fp:
# wr = csv.writer(fp, dialect='excel')
# wr.writerow(itweet)
print('no. of tweets scraped for run {} is {}'.format(i + 1, noTweets))
if i+1 != numRuns:
time.sleep(920)
filename = "tweets.csv"
# Store dataframe in csv with creation date timestamp
db_tweets.to_csv(filename, mode='a', index = False)
# Initialise these variables:
search_words = "#India OR #COVID-19"
date_since = "2020-04-29"
#date_until = "2020-05-01"
numTweets = 2500
numRuns = 10
# Call the function scrapetweets
program_start = time.time()
scrapetweets(search_words, date_since, numTweets, numRuns)
program_end = time.time()
print('Scraping has completed!')
print('Total time taken to scrape is {} minutes.'.format(round(program_end - program_start)/60, 2))
I referred to a blog on medium for this purpose.
you can add a variable as validator an store it to a file that may be a tweetid.txt
and each time you run the script, you open di tweetid.txt
if tweetid same in tweet id in txt, you pass it.
here is my code..i want to extract tweets from twitter with some keywords....my code dont give any errors but i am not getting the output file generated...please help me........
import re
import csv
import tweepy
from tweepy import OAuthHandler
#TextBlob perform simple natural language processing tasks.
from textblob import TextBlob
def search():
#text = e.get() **************************
consumer_key = ''
consumer_secret = ''
access_token = ' '
access_token_secret = ' '
# create OAuthHandler object
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
# set access token and secret
auth.set_access_token(access_token, access_token_secret)
# create tweepy API object to fetch tweets
api = tweepy.API(auth)
def get_tweets(query, count = 300):
# empty list to store parsed tweets
tweets = []
target = open("tweets.txt", 'w',encoding="utf-8")
t1 = open("review.txt", 'w',encoding="utf-8")
# call twitter api to fetch tweets
q=str(query)
a=str(q+" sarcasm")
b=str(q+" sarcastic")
c=str(q+" irony")
fetched_tweets = api.search(a, count = count)+ api.search(b, count = count)+ api.search(c, count = count)
# parsing tweets one by one
print(len(fetched_tweets))
for tweet in fetched_tweets:
# empty dictionary to store required params of a tweet
parsed_tweet = {}
# saving text of tweet
parsed_tweet['text'] = tweet.text
if "http" not in tweet.text:
line = re.sub("[^A-Za-z]", " ", tweet.text)
target.write(line+"\n")
t1.write(line+"\n")
return tweets
# creating object of TwitterClient Class
# calling function to get tweets
tweets = get_tweets(query =text, count = 20000)
root.mainloop()
From this code i am nor getting the output generated file. Can anyone tell me what i am doing wrong ?
Thanks in advance!
I just made some slight changes and it was working perfectly for me. Removed or commented some unnecessary statements (like the review file). Changed the open function to io.open since I have python version 2.7. Here is the running code, hope it helps!!
`
import re
import io
import csv
import tweepy
from tweepy import OAuthHandler
#TextBlob perform simple natural language processing tasks.
#from textblob import TextBlob
consumer_key = 'sz6x0nvL0ls9wacR64MZu23z4'
consumer_secret = 'ofeGnzduikcHX6iaQMqBCIJ666m6nXAQACIAXMJaFhmC6rjRmT'
access_token = '854004678127910913-PUPfQYxIjpBWjXOgE25kys8kmDJdY0G'
access_token_secret = 'BC2TxbhKXkdkZ91DXofF7GX8p2JNfbpHqhshW1bwQkgxN'
# create OAuthHandler object
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
# set access token and secret
auth.set_access_token(access_token, access_token_secret)
# create tweepy API object to fetch tweets
api = tweepy.API(auth)
def get_tweets(query, count = 300):
# empty list to store parsed tweets
tweets = []
target = io.open("mytweets.txt", 'w', encoding='utf-8')
# call twitter api to fetch tweets
q=str(query)
a=str(q+" sarcasm")
b=str(q+" sarcastic")
c=str(q+" irony")
fetched_tweets = api.search(a, count = count)+ api.search(b, count = count)+ api.search(c, count = count)
# parsing tweets one by one
print(len(fetched_tweets))
for tweet in fetched_tweets:
# empty dictionary to store required params of a tweet
parsed_tweet = {}
# saving text of tweet
parsed_tweet['text'] = tweet.text
if "http" not in tweet.text:
line = re.sub("[^A-Za-z]", " ", tweet.text)
target.write(line+"\n")
return tweets
# creating object of TwitterClient Class
# calling function to get tweets
tweets = get_tweets(query ="", count = 20000)
`
I'm trying to extract tweets using the following code, and I just realized I'm only getting the first 140 characters. I'm a bit new at this and now I need to put tweet_mode=extended and full_text somewhere, so if someone could point out exactly where I'd be very appreciative. Thank you!
#!/usr/bin/env python
encoding: utf-8
import tweepy #https://github.com/tweepy/tweepy
import csv
#Twitter API credentials
consumer_key = "5f55VEYRnHuBvVESy11OrBayI"
consumer_secret = "r0PcvNast4FLYD1HNQiJIsIDGtk72hhVFPzR3BfrIWfuSn2SWD"
access_key = "949748064985722880-Wpc3hErpGEeDC75MBfcDoo07X9WVcAo"
access_secret = "w02RdHMg1izgaFlKUJH3C5s9cDNue2h8XJv87E3TE0Whm"
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=200,)
#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 subsiquent 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))
#transform the tweepy tweets into a 2D array that will populate the csv
outtweets = [[tweet.id_str, tweet.created_at, tweet.text.encode("utf-
8"),tweet.retweet_count,tweet.favorite_count] for tweet in alltweets]
#write the csv
with open('%s_tweets.csv' % screen_name, 'wb') as f:
writer = csv.writer(f)
writer.writerow(["id","created_at","full_text","retweet_count","favorite_count"])
writer.writerows(outtweets)
pass
if __name__ == '__main__':
#pass in the username of the account you want to download
get_all_tweets("realdonaldtrump")
Put "tweet_mode=extended" here:
new_tweets = api.user_timeline(screen_name = screen_name,
count=200,
tweet_mode=extended)
And here:
while len(new_tweets) > 0:
new_tweets = api.user_timeline(screen_name = screen_name,
count=200,
max_id=oldest,
tweet_mode=extended)
Put "full_tweet" here:
outtweets = [[tweet.id_str,
tweet.created_at,
tweet.full_tweet.encode("utf-8"),
tweet.retweet_count,
tweet.favorite_count] for tweet in alltweets]
I am trying to pull tweets using since_id and max_id. The problem with since_id is that it correctly prints all the tweets in my eclipse console but when I try to store it line by line as csv file it does not return me all the tweets. I tried running it 4-5 times but every time I get different number of tweets.The problem with max_id is that it is not running. My code is as follows and the traceback is included after the code (For since_id I am just replacing max_id with since_id only)
#!/usr/bin/python
import tweepy
import csv
from datetime import *
import time
access_token = ''
access_secret = ''
consumer_key = ''
consumer_secret = ''
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_secret)
api = tweepy.API(auth)
#data = api.get_user('abhi1868sharma')#'mishra1_P_K'
csvFile = open('a.csv','a')
csvWriter = csv.writer(csvFile, delimiter=',')#, tweet.favourited
i = 1
tweets = tweepy.Cursor(api.user_timeline, id = '', max_id = 510064587115225000).items()
while True:
try:
for tweet in tweets:
csvWriter.writerow([i, tweet.retweet_count, tweet.favorite_count, str(tweet.id), tweet.created_at.hour,tweet.created_at.minute,tweet.created_at.weekday(),tweet.created_at.day,tweet.created_at.month,tweet.created_at.year,tweet.created_at ,tweet.text.encode('utf8'), tweet.user.id, tweet.geo, tweet.in_reply_to_user_id, tweet.in_reply_to_status_id_str, tweet.place, tweet.retweeted, tweet.truncated, tweet.source])
print i
i+=1
except tweepy.TweepError:
time.sleep(60 * 15)
continue
except StopIteration:
break
csvFile.close()
This is my traceback for the max_id (for since_id it is not throwing any error)
for tweet in tweets:
File "C:\Python27\lib\site-packages\tweepy\cursor.py", line 181, in next
self.current_page = self.page_iterator.next()
File "C:\Python27\lib\site-packages\tweepy\cursor.py", line 99, in next
data = self.method(max_id=self.max_id, parser=RawParser(), *self.args, **self.kargs)
TypeError: _call() got multiple values for keyword argument 'max_id'
One more thing as I am storing the file in csv file my tweet_ids get rounded off. Is there any way to get around it. And the tweet_id that I am using for since_id and max_id are also rounded out tweet ids.