Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -290,7 +290,7 @@ def scrape_and_download_data(app_packages, language, country, sort, score, start
|
|
| 290 |
# show only column title, at, sortOrder, reviewId, userName, userImage, content, score, thumbsUpCount, replyContent, repliedAt, rating
|
| 291 |
df = df[['title','at', 'sortOrder', 'reviewId', 'userName', 'userImage', 'content', 'score', 'thumbsUpCount', 'replyContent', 'repliedAt', 'rating']].rename(columns={'at': 'date'}) # Rename 'at' to 'date
|
| 292 |
df = df.sort_values(by='date', ascending=False)
|
| 293 |
-
df = df.drop_duplicates(subset=['title','
|
| 294 |
|
| 295 |
return df
|
| 296 |
|
|
|
|
| 290 |
# show only column title, at, sortOrder, reviewId, userName, userImage, content, score, thumbsUpCount, replyContent, repliedAt, rating
|
| 291 |
df = df[['title','at', 'sortOrder', 'reviewId', 'userName', 'userImage', 'content', 'score', 'thumbsUpCount', 'replyContent', 'repliedAt', 'rating']].rename(columns={'at': 'date'}) # Rename 'at' to 'date
|
| 292 |
df = df.sort_values(by='date', ascending=False)
|
| 293 |
+
df = df.drop_duplicates(subset=['title','date','reviewId','content','rating'], keep='first')
|
| 294 |
|
| 295 |
return df
|
| 296 |
|