-
Notifications
You must be signed in to change notification settings - Fork 62
/
pipeline.yaml
125 lines (116 loc) · 5.54 KB
/
pipeline.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
# Copyright 2021 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
---
resources:
- type: bigquery_table
table_id: state_screenshots
dag:
airflow_version: 1
initialize:
dag_id: "state_screenshots"
default_args:
owner: "Google"
# When set to True, keeps a task from getting triggered if the previous schedule for the task hasn’t succeeded
depends_on_past: False
start_date: '2021-03-01'
max_active_runs: 1
schedule_interval: "@once" # run once a week at Sunday 12am
catchup: False
default_view: graph
tasks:
- operator: "BashOperator"
description: "Run the custom/generate_csv.py script to scrape the webpage and generate a CSV file of the state screenshots"
args:
task_id: "generate_csv_data_from_web_scraping"
bash_command: |
mkdir -p $airflow_home/data/$dataset/$pipeline/run_date={{ ds }}
SOURCE_URL=$source_url CSV_OUTPUT_PATH=$airflow_home/data/$dataset/$pipeline/run_date={{ ds }}/data.csv GCS_PATH_PREFIX="gs://$destination_bucket/datasets/$dataset/$pipeline/run_date={{ ds }}/screenshots" python $airflow_home/dags/$dataset/$pipeline/custom/web_scrape_and_generate_csv.py
env:
airflow_home: "{{ var.json.shared.airflow_home }}"
destination_bucket: "{{ var.json.covid19_tracking.destination_bucket }}"
source_url: "https://screenshots.covidtracking.com"
dataset: "covid19_tracking"
pipeline: "state_screenshots"
- operator: "BashOperator"
description: "Run the custom/download_screenshots.py script to download all the screenshots to the local file system (mounted GCS)"
args:
task_id: "download_screenshots"
bash_command: |
CSV_PATH=$airflow_home/data/$dataset/$pipeline/run_date={{ ds }}/data.csv \
SOURCE_COLUMN="source_url" \
DOWNLOAD_PREFIX=$airflow_home/data/$dataset/$pipeline/run_date={{ ds }} \
python $airflow_home/dags/$dataset/$pipeline/custom/download_screenshots.py
env:
airflow_home: "{{ var.json.shared.airflow_home }}"
dataset: "covid19_tracking"
pipeline: "state_screenshots"
- operator: "GoogleCloudStorageToGoogleCloudStorageOperator"
description: "Upload all downloaded screenshots to the destination bucket"
args:
task_id: "upload_screenshots_to_destination_bucket"
source_bucket: "{{ var.json.shared.composer_bucket }}"
source_object: "data/covid19_tracking/state_screenshots/run_date={{ ds }}/*"
destination_bucket: "{{ var.json.covid19_tracking.destination_bucket }}"
destination_object: "datasets/covid19_tracking/state_screenshots/run_date={{ ds }}/"
move_object: False
- operator: "GoogleCloudStorageToBigQueryOperator"
description: "Task to load the data from Airflow data folder to BigQuery"
args:
task_id: "load_screenshots_to_bq_table"
bucket: "{{ var.json.shared.composer_bucket }}"
source_objects: ["data/covid19_tracking/state_screenshots/run_date={{ ds }}/data.csv"]
source_format: "CSV"
destination_project_dataset_table: "covid19_tracking.state_screenshots"
skip_leading_rows: 1
write_disposition: "WRITE_TRUNCATE"
schema_fields:
- name: "state"
type: "STRING"
mode: "REQUIRED"
description: "2-letter postal abbreviation for the state"
- name: "state_name"
type: "STRING"
mode: "REQUIRED"
description: "The full state name"
- name: "date"
type: "DATE"
mode: "REQUIRED"
description: "Date of the observations"
- name: "source_type"
type: "STRING"
mode: "REQUIRED"
description: "How far from the original event or phenomenon the information source is created. Can be one of primary, secondary, tertiary, quaternary"
- name: "time_of_day"
type: "STRING"
mode: "REQUIRED"
description: "The time of day, based on a 12-hour clock in Eastern Time"
- name: "source_url"
type: "STRING"
mode: "REQUIRED"
description: "The URL where the screenshot or file was originally found"
- name: "google_cloud_storage_uri"
type: "STRING"
mode: "REQUIRED"
description: "The GCS location where the screenshot or file was copied to"
- operator: "GoogleCloudStorageDeleteOperator"
description: "Delete downloaded screenshots from the Cloud Composer bucket"
args:
task_id: "delete_screenshots_from_composer_bucket"
bucket_name: "{{ var.json.shared.composer_bucket }}"
prefix: "data/covid19_tracking/state_screenshots/run_date={{ ds }}"
graph_paths:
- "generate_csv_data_from_web_scraping >> download_screenshots"
- "download_screenshots >> upload_screenshots_to_destination_bucket"
- "upload_screenshots_to_destination_bucket >> load_screenshots_to_bq_table"
- "load_screenshots_to_bq_table >> delete_screenshots_from_composer_bucket"