I'm extracting twitter data by specifying longitude, latitude, and range. However, I want to extract tweets from a rectangular area specifying two coordinate pairs of latitude and longitude.
Code:
from twitter import *
import sys
import csv
latitude = 51.474144 # geographical centre of search
longitude = -0.035401 # geographical centre of search
max_range = 1 # search range in kilometres
num_results = 1000 # minimum results to obtain
outfile = "output.csv"
import sys
sys.path.append(".")
import config
consumer_key = '*************************'
consumer_secret = '*******************************'
access_key = '***************************************'
access_secret = '*****************************'
twitter = Twitter(auth = OAuth(access_key, access_secret, consumer_key,
consumer_secret))
csvfile = open(outfile, "w")
csvwriter = csv.writer(csvfile)
row = [ "user", "text", "latitude", "longitude" ]
csvwriter.writerow(row)
result_count = 0
last_id = None
while result_count < num_results:
query = twitter.search.tweets(q = "", geocode = "%f,%f,%dkm" % (latitude,
longitude, max_range), count = 1000, max_id = last_id)
for result in query["statuses"]:
if result["geo"]:
user = result["user"]["screen_name"]
text = result["text"]
text = text.encode('ascii', 'replace')
latitude = result["geo"]["coordinates"][0]
longitude = result["geo"]["coordinates"][1]
row = [ user, text, latitude, longitude ]
csvwriter.writerow(row)
result_count += 1
last_id = result["id"]
print("got %d results" % result_count)
csvfile.close()
print("written to %s" % outfile)
Any help will be highly appreciated.
from tweepy.streaming import StreamListener
from tweepy import OAuthHandler
from tweepy import Stream
import time
import json
import re
from urllib3.exceptions import ProtocolError
access_token = 'xxxx'
access_token_secret = 'xxxx'
consumer_key = 'xxxx'
consumer_secret = 'xxxx'
class StdOutListener(StreamListener):
def on_data(self, data):
print (data)
return True
def on_error(self, status):
print ('Encountered error with status code:',status)
if __name__ == '__main__':
#This handles Twitter authetification and the connection to Twitter Streaming API
l = StdOutListener()
auth = OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
stream = Stream(auth, l)
while True:
try:
stream.filter(locations = [144.9385,-37.8246,144.9761,-37.7955], stall_warnings=True)
except (ProtocolError, AttributeError):
continue
If Twitter only allowed you to search within a circle of specified radius, it appears the only practical way to do this would to compute the centre and diagonal radius of your rectangle, then retrieve those and exclude the ones that lie outside your chosen rectangle (which you can do by verifying each axis individually).
Fortunately they also implement a search by bounding box (see this documentation page).
Studying https://developer.twitter.com/en/docs/tweets/data-dictionary/overview/geo-objects may help you in formulating your request.
Related
I'm trying to scrape twitter data for my thesis work. But in this below's code, dataframe isn't working. I mean, dataframe isn't showing at the output line. How can I modify this code to build my dataframe? Another problem is that I want to scrape data by filtering location. How can I do this?
import tweepy
import re
import pandas as pd
import itertools
import collections
import nltk
from nltk.corpus import stopwords
import matplotlib.pyplot as plt
from textblob import TextBlob
import os
consumer_key = ""
consumer_secret = ""
access_token = ""
access_token_secret = ""
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
api = tweepy.API(auth,wait_on_rate_limit=True,wait_on_rate_limit_notify=True)
latitude = 56.130367 # geographical centre of search
longitude = -106.346771 # geographical centre of search
max_range = 1
tweets = tweepy.Cursor(api.search,
q="Shopify" + " -filter:retweets",
#geocode = "%f,%f,%dkm" % (latitude,longitude,max_range),
lang="en",
since="2020-01-01").items(10)
for tweet in tweets:
print(tweet.text)
analysis = TextBlob(tweet.text)
print('Date=', tweet.created_at,'Location=', tweet.user.location)
print(analysis.sentiment)
if analysis.sentiment[0] > 0:
print('Positive')
elif analysis.sentiment[0] < 0:
print('Negative')
else:
print('Neutral')
print('====================================================================')
print()
user_data = [[tweet.created_at, remove_characters(tweet.user.name), tweet.user.location,
remove_characters(tweet.text), TextBlob(tweet.text).sentiment[0],
'Positive' if TextBlob(tweet.text).sentiment[0] > 0
else 'Negative' if TextBlob(tweet.text).sentiment[0] < 0
else 'Nuetral']
for tweet in tweets]
tweet_df = pd.DataFrame(data=user_data,
columns=['Created At', "User", 'Location', 'Text', 'Sentiment', 'Polarity', 'favorite_count'])
tweet_df.head(10)
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 wrote the code.
But I don't think it's going to work.
I want to extract words from the concept of " or " rather than the concept of " and ".
It seems like only ' keyword 1 ' is extracted.
How do I make corrections?
import tweepy
import time
import os
search_term = 'keyword1'
search_term2= 'keyword2'
lat = "37.6"
lon = "127.0"
radius = "200km"
location = "%s,%s,%s" % (lat, lon, radius)
API_key = "11111"
API_secret = "22222"
Access_token = "33333"
Access_token_secret = "444"
auth = tweepy.OAuthHandler(API_key, API_secret)
auth.set_access_token(Access_token, Access_token_secret)
api = tweepy.API(auth)
c=tweepy.Cursor(api.search,
q=(search_term or search_term2),
rpp=1000,
geocode=location,
include_entities=True)
data = {}
i = 1
for tweet in c.items():
data['text'] = tweet.text
print(i, ":", data)
i += 1
time.sleep(1)
wfile = open(os.getcwd()+"/twtw2.txt", mode='w')
data = {}
i = 0
for tweet in c.items():
data['text'] = tweet.text
wfile.write(data['text']+'\n')
i += 1
time.sleep(1)
wfile.close()
Maybe change this line
q=(search_term or search_term2),
to
q="{}+OR+{}".format(search_term,search_term2),
Case matters here for the OR operator
enter q as a string, not as an expression that is short-circuit evaluated
By the way, your credentials (from your post) also work for me.
crwaling(scraping,streaming) result is very good
ex. 973 : {'text': 'RT #1111: hihihihihihi' }
BUT! Unable to save.
How do I fix it?
import tweepy
import time
import os
import json
import simplejson
search_term = '5555'
search_term2= '4444'
search_term3='3333'
search_term4='2222'
search_term5='1111'
lat = "11.11"
lon = "11.11"
radius = "100km"
API_key = "0"
API_secret = "0"
Access_token = "0"
Access_token_secret = "0"
location = "%s,%s,%s" % (lat, lon, radius)
auth = tweepy.OAuthHandler(API_key, API_secret)
auth.set_access_token(Access_token, Access_token_secret)
api = tweepy.API(auth)
c=tweepy.Cursor(api.search,
q="{}+OR+{}".format(search_term, search_term2, search_term3, search_term4, search_term5),
rpp=1000,
geocode=location,
include_entities=True)
data = {}
i = 1
for tweet in c.items():
data['text'] = tweet.text
print(i, ":", data)
time.sleep(0.4)
i += 1
txt file is not made. ->There is no error message.
Or, txt file is made. but, there is no "tweet text and tweet date" in the txt. ->There is no error message.
(Not necessarily a txt file.Save Excel file.)
wfile = open(os.getcwd()+"/tqtq.txt", mode='w')
data = {}
i = 0
for tweet in c.items():
data['text'] = tweet.text
data['date']= tweet.text
wfile.write(data['text','date']+'\n')
i += 1
time.sleep(0.4)
wfile.close()
You may try using pickle
import pickle
pickle.dump(obj, filename)
To load it back result = pickle.load(filename)