Append to dataset avatar

Append to dataset

Try for free

No credit card required

Go to Store
Append to dataset

Append to dataset

valek.josef/append-to-dataset
Try for free

No credit card required

Utility actor that allows you to build a single large dataset from individual default datasets of other actor runs.

.editorconfig

1root = true
2
3[*]
4indent_style = space
5indent_size = 4
6charset = utf-8
7trim_trailing_whitespace = true
8insert_final_newline = true
9end_of_line = lf

.eslintrc

1{
2    "extends": "@apify"
3}

.gitignore

1# This file tells Git which files shouldn't be added to source control
2
3.idea
4node_modules

Dockerfile

1# First, specify the base Docker image. You can read more about
2# the available images at https://sdk.apify.com/docs/guides/docker-images
3# You can also use any other image from Docker Hub.
4FROM apify/actor-node:16
5
6# Second, copy just package.json and package-lock.json since it should be
7# the only file that affects "npm install" in the next step, to speed up the build
8COPY package*.json ./
9
10# Install NPM packages, skip optional and development dependencies to
11# keep the image small. Avoid logging too much and print the dependency
12# tree for debugging
13RUN npm --quiet set progress=false \
14 && npm install --only=prod --no-optional \
15 && echo "Installed NPM packages:" \
16 && (npm list --only=prod --no-optional --all || true) \
17 && echo "Node.js version:" \
18 && node --version \
19 && echo "NPM version:" \
20 && npm --version
21
22# Next, copy the remaining files and directories with the source code.
23# Since we do this after NPM install, quick build will be really fast
24# for most source file changes.
25COPY . ./
26
27# Optionally, specify how to launch the source code of your actor.
28# By default, Apify's base Docker images define the CMD instruction
29# that runs the Node.js source code using the command specified
30# in the "scripts.start" section of the package.json file.
31# In short, the instruction looks something like this:
32#
33# CMD npm start

INPUT_SCHEMA.json

1{
2    "title": "Input schema for the append-to-dataset actor.",
3    "type": "object",
4    "schemaVersion": 1,
5    "properties": {
6        "datasetIdOrName": {
7            "title": "Target Dataset (id or name)",
8            "type": "string",
9            "description": "Dataset that should be appended to",
10            "editor": "textfield"
11        },
12        "sourceDatasetId": {
13            "sectionCaption": "Advanced settings",
14            "title": "Source Dataset (id or name)",
15            "description": "In one-time usecase, fill in the dataset to be appended",
16            "type": "string",
17            "editor": "textfield"
18        },
19        "eventData":{
20            "title": "Event Data",
21            "description": "If the actor is run via webhook, eventData.actorRunId will be deterimined from webhook payload and it's default dataset will be appended",
22            "type": "object",
23            "editor": "json"
24        }
25    },
26    "required": ["datasetIdOrName"]
27}

apify.json

1{
2    "env": { "npm_config_loglevel": "silent" }
3}

main.js

1const Apify = require('apify');
2
3Apify.main(async () => {
4    const {eventData, datasetIdOrName, sourceDatasetId, pageSize = 100 } = await Apify.getInput();
5    // Check that input really contains sufficient identification of source dataset
6    if (!eventData?.actorRunId && !sourceDatasetId) {
7        throw new Error('Missing source dataset id or actor run id in event data');
8    }
9
10    const client = Apify.newClient();
11
12    // Prepare target dataset id
13    const targetDataset = await Apify.openDataset(datasetIdOrName);
14
15    // Prepare source dataset client
16    const sourceDatasetClient = sourceDatasetId
17        ? client.dataset(sourceDatasetId)
18        : client.run(eventData.actorRunId).dataset();
19
20    let currentOffset = 0;
21    // eslint-disable-next-line no-constant-condition
22    while(true) {
23        // Get items from source dataset
24        const {items, total, offset} = await sourceDatasetClient.listItems({
25            clean: true,
26            limit: pageSize,
27            offset: currentOffset,
28        });
29
30        // Push the items to target dataset
31        await targetDataset.pushData(items);
32
33        Apify.utils.log.info('Transfered items', {
34            count: items.length,
35            total,
36            offset
37        });
38
39        // Increase offset to go to the next page
40        currentOffset += pageSize;
41
42        // If we got all the items, we can stop
43        if (offset + items.length >= total) {
44            Apify.utils.log.info('All items were transfered');
45            break;
46        }
47    }
48
49});

package.json

1{
2    "name": "project-empty",
3    "version": "0.0.1",
4    "description": "This is a boilerplate of an Apify actor.",
5    "dependencies": {
6        "apify": "^2.3.2"
7    },
8    "devDependencies": {
9        "@apify/eslint-config": "^0.1.3",
10        "eslint": "^7.0.0"
11    },
12    "scripts": {
13        "start": "node main.js",
14        "lint": "./node_modules/.bin/eslint ./src --ext .js,.jsx",
15        "lint:fix": "./node_modules/.bin/eslint ./src --ext .js,.jsx --fix",
16        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
17    },
18    "author": "It's not you it's me",
19    "license": "ISC"
20}
Developer
Maintained by Community

Actor Metrics

  • 5 monthly users

  • 2 stars

  • 99% runs succeeded

  • Created in Jun 2022

  • Modified 8 months ago