Fixed download of files with invalid char in name, correctly set file…

… ending for google doc file types, don't enable abuse flag by default allow it to be passed as a parameter. (#7)

closes #5

.gitignore

@@ -5,6 +5,8 @@ tokens/
 drivedl.egg-info/
 dist/
 build/
+venv/
+.idea/
 
 credentials.json
 config.json

README.md

@@ -30,6 +30,12 @@ Note that on the first run, you will have to authorize the scope of the applicat
 Adding an argument `--skip` to your command will skip existing files and not redownload them.
 - By default the behaviour is to download everything without skipping.
 
+## File Abuse
+
+Adding an argument `--abuse` allows for downloading files which have been marked as "abused" from google.
+This acknowledges that you will download a file which google has marked that it could be malware or spam.
+An example error can be found on [this](https://github.com/prasmussen/gdrive/issues/182).
+
 ## Assigning extra processes:
 
 Adding an argument `--proc` followed by an integer of processes to assign the application will spawn the specified processes to do the download. Default process count is 5 processes

drivedl/drivedl.py

@@ -83,6 +83,7 @@ def main(console_call=True):
     search = False
     skip = False
     noiter = False
+    abuse = False
 
     # File Listing
     if len(sys.argv) < 2:
@@ -102,6 +103,9 @@ def main(console_call=True):
         if '--skip' in sys.argv:
             skip = True
             sys.argv.remove('--skip')
+        if '--abuse' in sys.argv:
+            abuse = True
+            sys.argv.remove('--abuse')
         if '--debug' in sys.argv:
             util.DEBUG = True
             sys.argv.remove('--debug')
@@ -134,15 +138,16 @@ def build_files():
                 path = ["".join([c for c in dirname if c.isalpha() or c.isdigit() or c in [' ', '-', '_', '.', '(', ')', '[', ']']]).rstrip() for dirname in path]
                 for f in files:
                     dest = os.path.join(destination, os.path.join(*path))
-                    file_dest.append((service, f, dest, skip))
+                    f['name'] = "".join([c for c in f['name'] if c.isalpha() or c.isdigit() or c in [' ', '-', '_', '.', '(', ')', '[', ']']]).rstrip()
+                    file_dest.append((service, f, dest, skip, abuse))
             if file_dest != []:
                 # First valid account found, break to prevent further searches
                 return True
         except ValueError: # mimetype is not a folder
             dlfile = service.files().get(fileId=folderid, supportsAllDrives=True).execute()
             print(f"\nNot a valid folder ID. \nDownloading the file : {dlfile['name']}")
             # Only use a single process for downloading 1 file
-            util.download(service, dlfile, destination, skip)
+            util.download(service, dlfile, destination, skip, abuse)
             sys.exit(0)
         except HttpError:
             print(f"{Fore.RED}File not found in account: {acc}{Style.RESET_ALL}")
@@ -171,7 +176,8 @@ def build_files():
 
     if service == None:
         # No accounts found with access to the drive link, exit gracefully
-        print("No valid accounts with access to the file/folder. Exiting...")
+        print("No valid accounts with access to the file/folder.")
+        print("Have you run the drivedl --add command? Exiting...")
         sys.exit(1)
     try:
         p = Pool(PROCESS_COUNT)

drivedl/util.py

@@ -88,11 +88,25 @@ def querysearch(service, name=None, drive_id=None, is_folder=None, parent=None,
             break
     return items
 
-def download(service, file, destination, skip=False, noiter=False):
+def download(service, file, destination, skip=False, abuse=False, noiter=False):
+    # add file extension if we don't have one
+    mimeType = file['mimeType']
+    if "application/vnd.google-apps" in mimeType:
+        if "form" in mimeType: return -1
+        elif "document" in mimeType:
+            ext_file = '.docx'
+        elif "spreadsheet" in mimeType:
+            ext_file = '.xlsx'
+        elif "presentation" in mimeType:
+            ext_file = '.pptx'
+        else:
+            ext_file = '.pdf'
+        root, ext = os.path.splitext(file['name'])
+        if not ext:
+            file['name'] = file['name'] + ext_file
     # file is a dictionary with file id as well as name
     if skip and os.path.exists(os.path.join(destination, file['name'])):
         return -1
-    mimeType = file['mimeType']
     if "application/vnd.google-apps" in mimeType:
         if "form" in mimeType: return -1
         elif "document" in mimeType:
@@ -104,7 +118,7 @@ def download(service, file, destination, skip=False, noiter=False):
         else:
             dlfile = service.files().export_media(fileId=file['id'], mimeType='application/pdf')
     else:
-        dlfile = service.files().get_media(fileId=file['id'], supportsAllDrives=True, acknowledgeAbuse=True)
+        dlfile = service.files().get_media(fileId=file['id'], supportsAllDrives=True, acknowledgeAbuse=abuse)
     rand_id = str(uuid.uuid4())
     os.makedirs('buffer', exist_ok=True)
     fh = io.FileIO(os.path.join('buffer', rand_id), 'wb')
@@ -116,6 +130,10 @@ def download(service, file, destination, skip=False, noiter=False):
         try:
             status, done = downloader.next_chunk()
         except Exception as ex:
+            if "abuse" in str(ex).lower():
+                if not noiter: print()
+                print(f"{Fore.RED}Abuse error for file{Style.RESET_ALL} {file['name']} ...")
+                rate_limit_count = 21
             DEBUG_STATEMENTS.append(f'File Name: {file["name"]}, File ID: {file["id"]}, Exception: {ex}')
             rate_limit_count += 1
     fh.close()