Spaces:
Runtime error
Runtime error
Commit
•
0fabb50
1
Parent(s):
e442e8d
Update scripts/twitter_scraper.py
Browse files- scripts/twitter_scraper.py +58 -40
scripts/twitter_scraper.py
CHANGED
@@ -5,48 +5,66 @@ from tqdm import tqdm
|
|
5 |
import requests
|
6 |
from scripts import sentiment
|
7 |
|
|
|
|
|
|
|
|
|
|
|
8 |
def get_latest_account_tweets(handle):
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
access_token
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
|
40 |
-
df_tweets = pd.DataFrame(data=[t._json for t in tweets])
|
41 |
-
df_tweets["created_at"] = pd.DataFrame(df_tweets["created_at"])
|
42 |
-
df_tweets = df_tweets.sort_values("created_at")
|
43 |
-
# print the tweet texts
|
44 |
-
tweets_txt = []
|
45 |
-
for tweet in tweets:
|
46 |
-
tweets_txt.append(sentiment.tweet_cleaner(tweet.full_text))
|
47 |
-
df_tweets["clean_text"] = tweets_txt
|
48 |
-
df_tweets["handle"] = df_tweets.user.iloc[0]["screen_name"]
|
49 |
-
return df_tweets
|
50 |
|
51 |
def get_tweets(
|
52 |
query: str,
|
|
|
5 |
import requests
|
6 |
from scripts import sentiment
|
7 |
|
8 |
+
import tweepy
|
9 |
+
import configparser
|
10 |
+
import os
|
11 |
+
import pandas as pd
|
12 |
+
|
13 |
def get_latest_account_tweets(handle):
|
14 |
+
try:
|
15 |
+
if os.path.exists("tweepy_auth.ini"):
|
16 |
+
config = configparser.ConfigParser()
|
17 |
+
config.read("tweepy_auth.ini")
|
18 |
+
# Get the authentication details
|
19 |
+
authentication_section = config['AUTHENTICATION']
|
20 |
+
consumer_key = authentication_section["twitter_consumer_key"]
|
21 |
+
consumer_secret = authentication_section["twitter_consumer_secret"]
|
22 |
+
access_token = authentication_section["twitter_access_token"]
|
23 |
+
access_token_secret = authentication_section["twitter_access_token_secret"]
|
24 |
+
else:
|
25 |
+
consumer_key = os.environ['twitter_consumer_key']
|
26 |
+
consumer_secret = os.environ["twitter_consumer_secret"]
|
27 |
+
access_token = os.environ["twitter_access_token"]
|
28 |
+
access_token_secret = os.environ["twitter_access_token_secret"]
|
29 |
+
|
30 |
+
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
|
31 |
+
auth.set_access_token(access_token, access_token_secret)
|
32 |
+
|
33 |
+
# create the API object
|
34 |
+
api = tweepy.API(auth)
|
35 |
+
|
36 |
+
# load the tweets from a specific user
|
37 |
+
tweets = api.user_timeline(
|
38 |
+
screen_name=handle, count=10000000, tweet_mode="extended"
|
39 |
+
)
|
40 |
+
|
41 |
+
df_tweets = pd.DataFrame(data=[t._json for t in tweets])
|
42 |
+
df_tweets["created_at"] = pd.to_datetime(df_tweets["created_at"])
|
43 |
+
df_tweets = df_tweets.sort_values("created_at")
|
44 |
+
|
45 |
+
# print the tweet texts
|
46 |
+
tweets_txt = []
|
47 |
+
for tweet in tweets:
|
48 |
+
tweets_txt.append(sentiment.tweet_cleaner(tweet.full_text))
|
49 |
+
df_tweets["clean_text"] = tweets_txt
|
50 |
+
df_tweets["handle"] = df_tweets.user.iloc[0]["screen_name"]
|
51 |
+
|
52 |
+
return df_tweets
|
53 |
+
|
54 |
+
except tweepy.TweepError as e:
|
55 |
+
# Handle specific error conditions
|
56 |
+
if e.api_code == 63:
|
57 |
+
print("User has been suspended.")
|
58 |
+
elif e.api_code == 88:
|
59 |
+
print("Rate limit exceeded. Please try again later.")
|
60 |
+
else:
|
61 |
+
print("Error occurred during API call:", str(e))
|
62 |
+
|
63 |
+
except Exception as e:
|
64 |
+
print("An error occurred:", str(e))
|
65 |
+
|
66 |
+
return None
|
67 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
|
69 |
def get_tweets(
|
70 |
query: str,
|