Spaces:
Runtime error
Runtime error
wira.indra
commited on
Commit
•
b99df17
1
Parent(s):
d990ea1
add twitter feature
Browse files- app.py +1 -1
- twitter_scraper.py +15 -4
app.py
CHANGED
@@ -72,8 +72,8 @@ if __name__ == "__main__":
|
|
72 |
with gr.Row():
|
73 |
with gr.Column():
|
74 |
input_text = gr.Textbox(label="Input Text")
|
75 |
-
examples_bar = gr.Examples(examples=examples, inputs=input_text)
|
76 |
analyze_button = gr.Button(label="Analyze")
|
|
|
77 |
with gr.Column():
|
78 |
sent_output = gr.Label(label="Sentiment Analysis")
|
79 |
ner_output = gr.HighlightedText(label="Named Entity Recognition")
|
|
|
72 |
with gr.Row():
|
73 |
with gr.Column():
|
74 |
input_text = gr.Textbox(label="Input Text")
|
|
|
75 |
analyze_button = gr.Button(label="Analyze")
|
76 |
+
examples_bar = gr.Examples(examples=examples, inputs=input_text)
|
77 |
with gr.Column():
|
78 |
sent_output = gr.Label(label="Sentiment Analysis")
|
79 |
ner_output = gr.HighlightedText(label="Named Entity Recognition")
|
twitter_scraper.py
CHANGED
@@ -7,10 +7,21 @@ import tqdm
|
|
7 |
def scrape_tweets(query, max_tweets=10, output_path="./scraper/output/" ):
|
8 |
tweets_list = []
|
9 |
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
|
15 |
df = pd.DataFrame(tweets_list, columns=['Datetime', 'Tweet Id', 'Text', 'Username', 'Likes', 'Retweets', 'Replies', 'Quotes', 'URL', 'Language'])
|
16 |
df = df[df["Language"] == "in"]
|
|
|
7 |
def scrape_tweets(query, max_tweets=10, output_path="./scraper/output/" ):
|
8 |
tweets_list = []
|
9 |
|
10 |
+
tweets_list = []
|
11 |
+
if sys.version_info.minor>=8:
|
12 |
+
for i,tweet in tqdm(enumerate(sntwitter.TwitterSearchScraper(query).get_items())):
|
13 |
+
if max_tweets != -1 and i >= int(max_tweets):
|
14 |
+
break
|
15 |
+
tweets_list.append([tweet.date, tweet.id, tweet.content, tweet.user.username, tweet.likeCount, tweet.retweetCount, tweet.replyCount, tweet.quoteCount, tweet.url, tweet.lang])
|
16 |
+
|
17 |
+
df = pd.DataFrame(tweets_list, columns=['Datetime', 'Tweet Id', 'Text', 'Username', 'Likes', 'Retweets', 'Replies', 'Quotes', 'URL', 'Language'])
|
18 |
+
df = df[df["Language"] == "in"]
|
19 |
+
else:
|
20 |
+
for i,tweet in tqdm(enumerate(sntwitter.TwitterSearchScraper(query).get_items())):
|
21 |
+
if max_tweets != -1 and i >= int(max_tweets):
|
22 |
+
break
|
23 |
+
tweets_list.append([tweet.date, tweet.id, tweet.content])
|
24 |
+
df = pd.DataFrame(tweets_list, columns=['Datetime', 'Tweet Id', 'Text'])
|
25 |
|
26 |
df = pd.DataFrame(tweets_list, columns=['Datetime', 'Tweet Id', 'Text', 'Username', 'Likes', 'Retweets', 'Replies', 'Quotes', 'URL', 'Language'])
|
27 |
df = df[df["Language"] == "in"]
|