Full google-play-scraper review script

full_gps_script.py

## Loop through apps to get reviews
for app_name, app_id in zip(app_names, app_ids):
    
    # Get start time
    start = dt.datetime.now(tz=get_localzone())
    fmt= "%m/%d/%y - %T %p"    
    
    # Print starting output for app
    print('---'*20)
    print('---'*20)    
    print(f'***** {app_name} started at {start.strftime(fmt)}')
    print()
    
    # Empty list for storing reviews
    app_reviews = []
    
    # Number of reviews to scrape per batch
    count = 200
    
    # To keep track of how many batches have been completed
    batch_num = 0
    
    
    # Retrieve reviews (and continuation_token) with reviews function
    rvws, token = reviews(
        app_id,           # found in app's url
        lang='en',        # defaults to 'en'
        country='us',     # defaults to 'us'
        sort=Sort.NEWEST, # start with most recent
        count=count       # batch size
    )
    
    
    # For each review obtained
    for r in rvws:
        r['app_name'] = app_name # add key for app's name
        r['app_id'] = app_id     # add key for app's id
     
    
    # Add the list of review dicts to overall list
    app_reviews.extend(rvws)
    
    # Increase batch count by one
    batch_num +=1 
    print(f'Batch {batch_num} completed.')
    
    # Wait 1 to 5 seconds to start next batch
    time.sleep(random.randint(1,5))
    
    
    
    # Append review IDs to list prior to starting next batch
    pre_review_ids = []
    for rvw in app_reviews:
        pre_review_ids.append(rvw['reviewId'])
    
    
    # Loop through at most max number of batches
    for batch in range(4999):
        rvws, token = reviews( # store continuation_token
            app_id,
            lang='en',
            country='us',
            sort=Sort.NEWEST,
            count=count,
            # using token obtained from previous batch
            continuation_token=token
        )
        
        # Append unique review IDs from current batch to new list
        new_review_ids = []
        for r in rvws:
            new_review_ids.append(r['reviewId'])
            
            # And add keys for name and id to ea review dict
            r['app_name'] = app_name # add key for app's name
            r['app_id'] = app_id     # add key for app's id
     
        # Add the list of review dicts to main app_reviews list
        app_reviews.extend(rvws)
        
        # Increase batch count by one
        batch_num +=1
        
        # Break loop and stop scraping for current app if most recent batch
          # did not add any unique reviews
        all_review_ids = pre_review_ids + new_review_ids
        if len(set(pre_review_ids)) == len(set(all_review_ids)):
            print(f'No reviews left to scrape. Completed {batch_num} batches.\n')
            break
        
        # all_review_ids becomes pre_review_ids to check against 
          # for next batch
        pre_review_ids = all_review_ids
        
        
        # At every 100th batch
        if batch_num%100==0:
            
            # print update on number of batches
            print(f'Batch {batch_num} completed.')
            
            # insert reviews into collection
            review_collection.insert_many(app_reviews)
            
            # print update about num reviews inserted
            store_time = dt.datetime.now(tz=get_localzone())
            print(f"""
            Successfully inserted {len(app_reviews)} {app_name} 
            reviews into collection at {store_time.strftime(fmt)}.\n
            """)
            
            # empty our list for next round of 100 batches
            app_reviews = []
        
        # Wait 1 to 5 seconds to start next batch
        time.sleep(random.randint(1,5))
      
    
    # Print update when max number of batches has been reached
      # OR when last batch didn't add any unique reviews
    print(f'Done scraping {app_name}.')
    print(f'Scraped a total of {len(set(pre_review_ids))} unique reviews.\n')
    
    
    # Insert remaining reviews into collection
    review_collection.insert_many(app_reviews)
    
    # Get end time
    end = dt.datetime.now(tz=get_localzone())
    
    # Print ending output for app
    print(f"""
    Successfully inserted all {app_name} reviews into collection
    at {end.strftime(fmt)}.\n
    """)
    print(f'Time elapsed for {app_name}: {end-start}')
    print('---'*20)
    print('---'*20)
    print('\n')
    
    # Wait 1 to 5 seconds to start scraping next app
    time.sleep(random.randint(1,5))

Does not work at all.

Does not work at all.

I'd be happy to try and troubleshoot as this has worked for myself and others. Are you running into specific error messages?

Trying to download reviews of this
https://play.google.com/store/apps/details?id=in.gov.umang.negd.g2c&hl=en_IN&gl=US
modified the script for
app_names = ("UMANG")
app_ids = ("in.gov.umang.negd.g2c")

Errors out into

***** A started at 05/20/21 - 22:40:47 PM

Batch 1 completed.
No reviews left to scrape. Completed 2 batches.

Done scraping A.
Scraped a total of 0 unique reviews.

Traceback (most recent call last):
File "cool.py", line 155, in
review_collection.insert_many(app_reviews)
NameError: name 'review_collection' is not defined

@graizada You forgot to define review_collection. Add the following code before review scraping.

review_collection = app_proj_db['review_collection']

for complete guide follow this link: https://python.plainenglish.io/scraping-storing-google-play-app-reviews-with-python-5640c933c476