def main():
"""Uses the Docs API to print out the text of a document."""
credentials = get_credentials()
http = credentials.authorize(Http())
docs_service = discovery.build(
'docs', 'v1', http=http, discoveryServiceUrl=DISCOVERY_DOC)
drive_service = discovery.build('drive', 'v3', credentials=credentials)
doc = docs_service.documents().get(documentId=DOCUMENT_ID).execute()
doc_content = doc.get('body').get('content')
requests = [
{
"replaceAllText" : {
"replaceText" : sys.argv[3],
"containsText" : {
"text" : sys.argv[2],
"matchCase" : True
}
}
}
]
result = docs_service.documents().batchUpdate(
documentId=DOCUMENT_ID, body={'requests' : requests}).execute()
download_request = drive_service.files().export(fileId=DOCUMENT_ID,
mimeType='application/pdf')
fh = io.BytesIO()
downloader = driveHttp.MediaIoBaseDownload(fh, download_request)
done = False
while done is False:
status, done = downloader.next_chunk()
print("Downloaded %d%%." % int(status.progress() * 100))
if done is True:
with open(sys.argv[4], 'wb') as f:
f.write(fh.getvalue())
def download_file(service, file_id, name, size, path):
print("Download: " + "['" + file_id + "'" + ", '" + name + "']")
dir = os.path.join(path, name)
# filesize =
# print(str(filesize) + '....' + size)
if os.path.exists(dir) == True and str(os.path.getsize(dir)) == size:
print('File alreay exist, skipping...')
return 0
file_io_base = open(dir, 'wb')
request = service.files().get_media(fileId=file_id)
media_request = http.MediaIoBaseDownload(file_io_base, request)
while True:
try:
status, done = media_request.next_chunk()
except errors.HttpError as error:
print('An error occurred: %s' % error)
return
if status:
print("... %d%%." % int(status.progress() * 100))
if done:
print('Download Complete')
file_io_base.close()
return 0
def download_file(service, file_id, filename):
"""Download a Drive file's content to the local filesystem.
Args:
service : Drive API Service instance.
file_id : ID of the Drive file that will downloaded.
local_fd : io.Base or file object, the stream that the Drive file's contents will be written to.
"""
fh = io.FileIO(filename, 'wb')
request = service.files().get_media(fileId=file_id)
media_request = http.MediaIoBaseDownload(fh, request)
while True:
try:
download_progress, done = media_request.next_chunk()
except Exception as e:
print(f"An error occurred: {e}")
if download_progress:
print(
f"Download Progress: {int(download_progress.progress() * 100)}"
)
if done:
print("Download Complete")
break
def download_file(service, file_id, destination):
""" Function to download a file stored in Google Drive
Args:
service (Google Drive API): object to interact with the content
file_id (str): Google Drive ID for the file to retrieve
destination (str): local path to save the file
Returns:
Dictionary with the metadata from the downloaded file
"""
info = service.files().get(fileId=file_id).execute()
# Google Docs files
if info["mimeType"] == "application/vnd.google-apps.document":
request = service.files().export_media(fileId=info['id'],
mimeType="application/vnd"
".oasis.opendocument"
".text")
# Files stored in Google Drive
else:
request = service.files().get_media(fileId=info['id'])
fh = io.BytesIO()
downloader = http.MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
# print("Download %d%%." % int(status.progress() * 100))
write_bytesio_to_file(destination, fh)
return info
def download_file(self, where_to_download, query, onProgress=None):
files = self.search_service.find(**query)
if len(files) == 0:
print("File not found! '{}'".format(query))
return
if len(files) > 1:
print("There are multiple files! Select only one: {}".format(
[x['name'] for x in files]))
return
file = files[0]
print("File found! '{}'".format(file['name']))
print("Downloading File...")
fullpath = os.path.join(where_to_download, file['name'])
print("Saving in {}".format(fullpath))
file_stream = open(fullpath, "wb")
request = self.service.files().get_media(fileId=file['id'])
media_request = http.MediaIoBaseDownload(file_stream, request)
done = False
while done is False:
status, done = media_request.next_chunk()
if onProgress:
onProgress(int((status.progress() if status else 1) * 100))
print("Download Complete!")
def download_file(self, __id: str, __path: Path) -> None:
""" Download the file by ID.
:param __id: string, file ID.
:param __path: Path, path to download the file.
:return: None.
"""
# m_type = mime_type(__path)
_request = self.__drive.files().get_media(fileId=__id)
_fh = io.BytesIO()
_downloader = http.MediaIoBaseDownload(_fh, _request)
_done = False
while _done is False:
try:
status, _done = _downloader.next_chunk()
except Exception as e:
print(f"{e}\nwhile downloading file: {__path}",
file=sys.stderr)
return
print(f"Download {int(status.progress() * 100)}%")
with io.open(str(__path), 'wb') as f:
_fh.seek(10)
f.write(_fh.read())
def download_file(service, file_id, local_fd):
"""
This will actually download the file from Google Drive.
:param service:
:param file_id:
:param local_fd:
:return:
"""
download_progress = None
request = service.files().get_media(fileId=file_id)
media_request = http.MediaIoBaseDownload(local_fd, request)
while True:
try:
download_progress, done = media_request.next_chunk()
except errors.HttpError as error:
#print('An error occurred: %s' % error)
break
if download_progress:
#print('Download Progress: %d%%' % int(download_progress.progress() * 100))
pass
if done:
#print('Download Complete')
pass
if download_progress and download_progress.progress() >= 1.0:
return True
def download_file(service, file_id, local_fd):
"""Download a Drive file's content to the local filesystem.
Args:
service: Drive API Service instance.
file_id: ID of the Drive file that will downloaded.
local_fd: io.Base or file object, the stream that the Drive file's
contents will be written to.
"""
request = service.files().get_media(fileId=file_id)
media_request = http.MediaIoBaseDownload(local_fd, request)
while True:
try:
download_progress, done = media_request.next_chunk()
except errors.HttpError, error:
print 'An error occurred: %s' % error
return
if download_progress:
print 'Download Progress: %d%%' % int(
download_progress.progress() * 100)
if done:
print 'Download Complete'
return
def download_file(service, file_id, local_fd):
"""Download a Drive file's content to the local filesystem.
Args:
service: Drive API Service instance.
file_id: ID of the Drive file that will downloaded.
local_fd: io.Base or file object, the stream that the Drive file's
contents will be written to.
"""
request = service.files().get_media(fileId=file_id)
print('req-i' + str(request.headers))
media_request = http.MediaIoBaseDownload(local_fd, request)
while True:
try:
download_progress, done = media_request.next_chunk()
except errors.HttpError, error:
print('An error occurred: %s' % error)
# print(type(errors.HttpError))
# print(json.loads(errors.HttpError.content.decode('utf-8'))['error']['message']) # works
return
if download_progress:
print('Download Progress: %d%%' %
int(download_progress.progress() * 100))
if done:
print('Download Complete')
return
def download_file(file_id, filename='myfile'):
request = drive_service.files().get_media(fileId=file_id)
fh = io.FileIO(filename, 'wb')
downloader = http.MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
print "Download %d%%." % int(status.progress() * 100)
def download_file(self, file_id, file_type, export_path):
request = self.files.export_media(fileId=file_id, mimeType=file_type)
fh = io.FileIO(export_path, 'wb')
downloader = http.MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
return export_path
def pull(self, name):
file_id = self.exists(name)['id']
request = self.files.get_media(fileId=file_id)
fh = io.FileIO(name, 'wb')
downloader = http.MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
def downoad_file_and_store(service, file_id):
try:
file_info = get_file_info(service, file_id)
if (file_info == -1):
return -1, -1
download_dir = os.path.join(settings.TEMP_DOWNLOAD_PATH, file_id)
path_download = os.path.join(download_dir, str(file_info["name"]))
path_fileinfo = os.path.join(download_dir, "fileinfo")
if not os.path.exists(download_dir):
os.makedirs(download_dir)
else:
try:
if os.path.exists(path_fileinfo):
json_data = json.load(open(path_fileinfo))
if "modifiedTime" in json_data:
modified_time = json_data["modifiedTime"]
else:
modified_time = ""
if "createdTime" in json_data:
created_time = json_data["createdTime"]
else:
created_time = ""
if (created_time == file_info["createdTime"]
and modified_time == file_info["modifiedTime"]
and os.path.exists(path_download)
and os.path.getsize(path_download) == long(
file_info["size"])):
return str(path_download), str(file_info["name"])
else:
pass
else:
pass
except:
pass
if file_info["mimeType"] in array_google_mimeType:
mimeTypeExport = ""
for mime in list_google_mimeType:
if mime[0] == file_info["mimeType"]:
mimeTypeExport = mime[2]
break
request = service.files().export_media(fileId=file_id,
mimeType=mimeTypeExport)
else:
request = service.files().get_media(fileId=file_id)
fh = open(path_download, 'wb')
downloader = http.MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
print("Downloaded " + str(file_info["name"]) + " " +
str(int(status.progress() * 100)) + "%")
fh.close()
json.dump(file_info, open(path_fileinfo, 'w+'))
return str(path_download), str(file_info["name"])
except Exception as e:
print(e)
return -1, -1
def table2sql(request, id=0):
bucket_name = ''
if id:
storage = Storage(CredentialsModel, 'id', request.user, 'credential')
credential = storage.get()
http1 = httplib2.Http()
http2 = credential.authorize(http1)
service = build("drive", "v2", http=http2)
# files = service.files().list().execute()
# request = service.files().get_media(fileId=id)
# local_fd = open('workfile', 'w');
# media_request = http.MediaIoBaseDownload(local_fd, request)
# close f;
# Retry transport and file IO errors.
RETRYABLE_ERRORS = (httplib2.HttpLib2Error, IOError)
# Number of times to retry failed downloads.
NUM_RETRIES = 5
# Number of bytes to send/receive in each request.
CHUNKSIZE = 2 * 1024 * 1024
# Mimetype to use if one can't be guessed from the file extension.
DEFAULT_MIMETYPE = 'application/octet-stream'
print 'Building download request...'
filename = 'xxx'
f = file(filename, 'w')
request = service.files().get_media(fileId=id)
media = http.MediaIoBaseDownload(f, request, chunksize=CHUNKSIZE)
print 'Downloading bucket: %s object: %s to file: %s' % (bucket_name,
id, filename)
progressless_iters = 0
done = False
while not done:
error = None
try:
progress, done = media.next_chunk()
if progress:
print_with_carriage_return('Download %d%%.' %
int(progress.progress() * 100))
except HttpError, err:
error = err
if err.resp.status < 500:
raise
except RETRYABLE_ERRORS, err:
error = err
if error:
progressless_iters += 1
handle_progressless_iter(error, progressless_iters)
else:
progressless_iters = 0
def download(service=None, file_id=None, file_name='download.jpg'):
request = service.files().get_media(fileId=file_id)
with open(file_name, 'wb') as f:
downloader = http.MediaIoBaseDownload(f, request)
done = False
while not done:
status, done = downloader.next_chunk()
print("Download %d%%." % int(status.progress() * 100))
def export(self, spreadsheet_id, fformat):
request = self.driveService.files().export(fileId=spreadsheet_id, mimeType=fformat.value.split(':')[0])
import io
fh = io.FileIO(spreadsheet_id+fformat.value.split(':')[1], 'wb')
downloader = ghttp.MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
print("Download %d%%." % int(status.progress() * 100))
def download_to(self, path):
resource = service.files().get_media(fileId=self.id)
file = open(path + self.properties['name'], "wb")
media_request = http.MediaIoBaseDownload(file, resource)
try:
done = False
while not done:
download_progress, done = media_request.next_chunk()
except errors.HttpError as error:
print('An error occurred: %s' % error)
def do_GET(self):
f = self.send_head()
if f:
media_request = http.MediaIoBaseDownload(self.wfile, f)
done = False
while done is False:
try:
download_progress, done = media_request.next_chunk()
except Exception as e:
print(e)
self.send_error(HTTPStatus.INTERNAL_SERVER_ERROR)
def export_file(file_id, filepath):
request = drive_service.files().export_media(fileId=file_id,
mimeType='text/csv')
fh = io.BytesIO()
downloader = ghttp.MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
print("Download %d%%." % int(status.progress() * 100))
with io.open(filepath, 'wb') as f:
fh.seek(0)
f.write(fh.read())
def start(self, file_handle=None): #, first_process = True):
if file_handle is None:
self.file_handle = io.BytesIO()
else:
self.file_handle = file_handle
self.downloader = http.MediaIoBaseDownload(self.file_handle,
self.request)
self.done = False
self.status = None
self.part = 0
def download_file(self, file_id):
"""
Download a file given it's file id.
:param file_id: File ID of the file to be downloaded.
:return: ByteIO object of the file which can be saved to a file in the local system.
"""
request = self.service.files().get_media(fileId=file_id)
file_handler = io.BytesIO()
downloader = http.MediaIoBaseDownload(file_handler, request)
done = False
while not done:
status, done = downloader.next_chunk()
return file_handler
def save_raw_spreadsheet(self, sheet_id, spreadsheet_file):
request = self.drive_api.files().export_media(
fileId=sheet_id,
mimeType=
'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'
)
with open(spreadsheet_file, 'wb') as fh:
downloader = http.MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
def getFile(service, folderID, fileID, fileName, destPath, verbose=False):
"""Retrieves a File from a google drive Folder. Currently we only
support binary files so you can not get docs,spreadhseets, etc.
Args:
service: google drive service instance to use
folderID: Parent Folder's ID from which to get the file
fileID: Id of the file that needs to be retrieved from google drive
fileName: Name to use for the local file
destPath: destination path to use for the local file
verbose: print debugging information
Returns:
File that was requested or error if error occured
To Do:
Check if File and folder exist
Possible check if File is not 0 length before putting it up on google drive
"""
drive_service = service
os.chdir(destPath)
local_fd = open(fileName, 'w')
if verbose:
print('Received FileID = ' + fileID, file=sys.stderr)
print('Destination received: {0}'.format(destPath), file=sys.stderr)
request = drive_service.files().get_media(fileId=fileID)
alternateLinkFilePath = os.path.join(destPath, 'filelink.txt')
fileUrlRequest = drive_service.files().get(fileId=fileID).execute()
fileDownloadUrl = fileUrlRequest['webContentLink']
if verbose:
print('Headers: {0}'.format(request.headers), file=sys.stderr)
print('URI: {0}'.format(request.uri), file=sys.stderr)
media_request = http.MediaIoBaseDownload(local_fd, request)
while True:
try:
download_progress, done = media_request.next_chunk()
except errors.HttpError, error:
#print 'An error occurred: %s' % error
return error
if download_progress:
print('Download Progress: %d%%' %
int(download_progress.progress() * 100),
file=sys.stderr)
if done:
#print 'Download Complete'
with open(alternateLinkFilePath, 'w') as fh:
fh.write(fileDownloadUrl)
print('Download Artifacts: {0}'.format(fileDownloadUrl),
file=sys.stderr)
return
def download_file(service_download, file_id, local_fd):
request = service_download.files().get_media(fileId=file_id)
media_request = http.MediaIoBaseDownload(local_fd, request)
while True:
try:
download_progress, done = media_request.next_chunk()
except errors.HttpError as error:
print('An error occurred: %s' % error)
return
if download_progress:
print('Download Progress: %d%%' % int(download_progress.progress() * 100))
if done:
print('Download Complete')
return
def download_file(self, file_id):
"""
Download a file whose ID is fild_id
:param file_id: File ID
:return: Downloaded bytes
"""
request = self.service.files().get_media(fileId=file_id)
fh = io.BytesIO()
downloader = http.MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
self._logger.info("Download %d%%" % int(status.progress() * 100))
return fh.getvalue()
def download_media_csv(service, fildId, local_fd):
request = service.files().get_media(fileId=fildId, acknowledgeAbuse=True)
print(request), dir(request), dir(request.uri), request.uri
media_request = http.MediaIoBaseDownload(local_fd, request)
while True:
try:
download_progress, done = media_request.next_chunk()
except errors.HttpError as error:
print 'An error occurred: %s' % error
return
if download_progress:
print 'Download Progress: %d%%' % int(
download_progress.progress() * 100)
if done:
print 'Download Complete'
return
def exportFile(DRIVE, fileid, mimetype, filename): ''' Accepts a file ID, mimeType, and filename and attempts to export the file from Google Drive to the given mimeType. ''' # Create a request for the file to export request = DRIVE.files().export_media(fileId=fileid, mimeType=mimetype) # Open a stream up to write bytes to the given filename fh = io.FileIO(filename, 'wb') # Create a downloader from the request to the file stream downloader = http.MediaIoBaseDownload(fh, request) done = False # Download chunks of the file until done while done is False: status, done = downloader.next_chunk()
def get_file(fileId, fileName, year, user):
global FILES_DOWNLOADED
filePath = BACKUP_DIR + "/" + user + "/" + str(year) + "/" + fileName
if (not os.path.exists(filePath)):
request = DRIVE_SERVICE.files().get_media(fileId=fileId)
fh = io.FileIO(filePath + ".inprogress", mode='wb')
downloader = http.MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
print("Download {0}% (file {1} of max {2})".format(
int(status.progress() * 100), (FILES_DOWNLOADED + 1),
MAX_FILES_TO_DOWNLOAD))
fh.close()
os.rename(filePath + ".inprogress", filePath)
FILES_DOWNLOADED += 1
def download_file(service, file_id, local_fd):
"""Download a Drive file's content to the local filesystem.
Args:
service: Drive API Service instance.
file_id: ID of the Drive file that will downloaded.
local_fd: io.Base or file object, the stream that the Drive file's
contents will be written to.
"""
request = service.files().get_media(fileId=file_id)
fh = io.BytesIO()
downloader = http.MediaIoBaseDownload(local_fd, request)
done = False
while done is False:
status, done = downloader.next_chunk()
print("Download %d%%." % int(status.progress() * 100))
def getFile(self, FolderName, FileName):
retObj = ''
fileId = self.getFileID(FolderName, FileName)
fileMeta = self.getFileDetails(FolderName, FileName)
fm = json.dumps(fileMeta)
fd = json.loads(fm)
fileSize = '0'
if 'size' in fd:
fileSize = fd['size']
if fileSize != '0':
try:
print('Download Starting.')
request = self.SERVICE.files().get_media(fileId=fileId)
fh = io.BytesIO()
downloader = http.MediaIoBaseDownload(fh, request)
done = False
while done is False:
status, done = downloader.next_chunk()
print("Download %d%%." % int(status.progress() * 100))
print('Download Finished.')
retObj = fh.getvalue()
except urllib3.exceptions.HTTPError as error:
print('HTTP Error occured!')
if hasattr(error, 'code'):
print('Error Code: ' + str(error.code))
if hasattr(error, 'reason'):
print('Error Code: ' + str(error.reason))
except Exception as error:
print("An error has occured!")
print(error)
exit(409)
else:
print('File ({0}) has a size of 0'.format(FileName))
retObj = ''
return retObj
