19 lines
751 B
Python
19 lines
751 B
Python
import snscrape.modules.twitter as sntwitter
|
|
import pandas as pd
|
|
|
|
def scrape(limit=0):
|
|
# prepare variables
|
|
tweet_list = list()
|
|
query = '(Odense OR odense OR #odense OR #Odense) until:2022-12-17 since:2017-01-01 -filter:replies'
|
|
# begin scraping
|
|
for i, tweet in enumerate(sntwitter.TwitterSearchScraper(query).get_items()):
|
|
# if limit is reached, break out of loop
|
|
if limit > 0 and i > limit: break
|
|
# if another 100 tweets found, tell it
|
|
if i % 100 == 0:
|
|
print(f'found {i} tweets')
|
|
tweet_list.append([tweet.date, tweet.id, tweet.content, tweet.user.username])
|
|
# create dataframe
|
|
df = pd.DataFrame(tweet_list, columns=['Datetime', 'Id', 'Text', 'Username'])
|
|
return df
|