Skip to content

DataflowAcademy-010 : Serverless Data Processing with Dataflow - Writing an ETL Pipeline using Apache Beam and Dataflow (Python) (Notebook Updates)) #3148

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
WorkingGitHubUser merged 1 commit into from
May 19, 2026
+5 −0
Merged

DataflowAcademy-010 : Serverless Data Processing with Dataflow - Writing an ETL Pipeline using Apache Beam and Dataflow (Python) (Notebook Updates)) #3148

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions quests/dataflow_python/1_Basic_ETL/lab/my_pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ def run():
parser.add_argument('--stagingLocation', required=True, help='Specify Cloud Storage bucket for staging')
parser.add_argument('--tempLocation', required=True, help='Specify Cloud Storage bucket for temp')
parser.add_argument('--runner', required=True, help='Specify Apache Beam Runner')
parser.add_argument('--machine_type', required=False, help='Specify machine type')

opts = parser.parse_args()

Expand All @@ -26,6 +27,7 @@ def run():
options.view_as(GoogleCloudOptions).temp_location = opts.tempLocation
options.view_as(GoogleCloudOptions).job_name = '{0}{1}'.format('my-pipeline-',time.time_ns())
options.view_as(StandardOptions).runner = opts.runner
options.view_as(WorkerOptions).machine_type = opts.machine_type

# TODO: Add static input and output strings

Expand Down
3 changes: 3 additions & 0 deletions quests/dataflow_python/1_Basic_ETL/solution/my_pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@
from apache_beam.options.pipeline_options import PipelineOptions
from apache_beam.options.pipeline_options import StandardOptions
from apache_beam.runners import DataflowRunner, DirectRunner
from apache_beam.options.pipeline_options import WorkerOptions

# ### main

Expand All @@ -18,6 +19,7 @@ def run():
parser.add_argument('--stagingLocation', required=True, help='Specify Cloud Storage bucket for staging')
parser.add_argument('--tempLocation', required=True, help='Specify Cloud Storage bucket for temp')
parser.add_argument('--runner', required=True, help='Specify Apache Beam Runner')
parser.add_argument('--machine_type', required=False, help='Specify machine type')

opts = parser.parse_args()

Expand All @@ -29,6 +31,7 @@ def run():
options.view_as(GoogleCloudOptions).temp_location = opts.tempLocation
options.view_as(GoogleCloudOptions).job_name = '{0}{1}'.format('my-pipeline-',time.time_ns())
options.view_as(StandardOptions).runner = opts.runner
options.view_as(WorkerOptions).machine_type = opts.machine_type

# Static input and output
input = 'gs://{0}/events.json'.format(opts.project)
Expand Down