Fixed bug: repeated meeting ID crashed script

The script was not able to handle the case where the same meeting ID was
encountered more than once.  This is because each meeting ID is a
directory in the downloads directory, and creating a directory that
already exists is an error in Python.

While I was at it, I also put in a check for existing files so that
restarting the downloader will not start over from the beginning again.
This makes it easier to restart, but could lead to a file being
partially downloaded and then skipped over subsequently, but it is a
better place to be than restarting a download of hundreds of videos from
scratch.

diff --git a/README.md b/README.md
index 7078b595f82696e8b887dc2f1cc0228dd9743c2f..58f41aea5914e6f56da10778b5aa2e2f3e885b75 100644 (file)
--- a/README.md
+++ b/README.md
@@ -15,6 +15,11 @@ If you haven't done that before you will need to use PIP (https://pip.readthedoc
 
 Exact command is "pip install -r requirements.txt"
 
+Next, edit cloudlink.py to do the following:
+* Set your JWT and USER ID
+* Set the destination path for the downloads
+* Set the desired range of years to check
+
 Then run "python cloudlink.py"
 
 That will download all the recordings wherever you specify. 

diff --git a/cloudlink.py b/cloudlink.py
index c8d485f940aeef0e1fb0733baac4f6d0ea5ce315..c41b5a7d0ebedb58345da63531012dc2fd3b5d75 100644 (file)
--- a/cloudlink.py
+++ b/cloudlink.py
@@ -17,12 +17,12 @@ headers = {
        }
 
 # Put your own download path here, I used an external hard drive so mine will differ from yours
-PATH = '/Volumes/Ext3/Zoom/'
+PATH = '/media/rhett/Seagate Portable Drive/VAM_2021/'
 
 
 
 def main():
-       for year in range(2018,2022):
+       for year in range(2021,2022):
                for month in range(1,13):
                        next_month = month + 1
                        next_year = year
@@ -61,12 +61,13 @@ def get_recording(start_date, next_date):
        # print(data['to'])
 
        for meeting in data['meetings']:
-               os.mkdir('{}{}'.format(PATH, meeting['id']))
+               if not os.path.isdir('{}{}'.format(PATH, meeting['id'])):
+                       os.mkdir('{}{}'.format(PATH, meeting['id']))
                for record in meeting['recording_files']:
                        if 'status' in record and record['status'] != 'completed':
                                continue
 
-                       download_recording(
+               download_recording(
                                record['download_url'], 
                                record['recording_start'].replace(':','-'),
                                record['file_type'],
@@ -88,13 +89,15 @@ def download_recording(download_url, filename, filetype, meeting_id):
                suffix = 'JSON'
        suffix = suffix.lower()
        local_filename = '{}/{}/{}_{}.{}'.format(PATH, meeting_id, filename, filetype, suffix)
+       if os.path.isfile(local_filename):
+               print ('file {} exists, skipping download!'.format(local_filename))
+       else:
+               with open(local_filename, 'wb') as f:
+                       for chunk in response.iter_content(chunk_size=8192):
+                               print (len(chunk))
+                               f.write(chunk)
 
-       with open(local_filename, 'wb') as f:
-               for chunk in response.iter_content(chunk_size=8192):
-                       print (len(chunk))
-                       f.write(chunk)
 
-          
 if __name__ == '__main__':
        main()