LD+JSON Schema scraper avatar

LD+JSON Schema scraper

Try for free

No credit card required

Go to Store
LD+JSON Schema scraper

LD+JSON Schema scraper

pocesar/json-ld-schema
Try for free

No credit card required

Extract all LD+JSON tags from the given URLs.

.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": "LD JSON Schema scraper",
3    "type": "object",
4    "schemaVersion": 1,
5    "properties": {
6        "startUrls": {
7            "title": "Start Urls",
8            "type": "array",
9            "description": "The URLs to extract all LD+JSON data",
10            "default": [],
11            "prefill": [{
12                "url": "https://blog.apify.com/"
13            }],
14            "editor": "requestListSources"
15        },
16        "proxyConfiguration": {
17            "title": "Proxy configuration",
18            "description": "A proxy required for scraping",
19            "type": "object",
20            "default": { "useApifyProxy": true },
21            "prefill": { "useApifyProxy": true },
22            "editor": "proxy"
23        },
24        "customData": {
25            "title": "Custom data",
26            "description": "Provide some custom data to output",
27            "type": "object",
28            "default": {},
29            "prefill": {},
30            "editor": "json"
31        }
32    },
33    "required": [
34        "startUrls",
35        "proxyConfiguration"
36    ]
37}

apify.json

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

main.js

1const Apify = require('apify');
2
3const pageFunction = async (context) => {
4    const { request, $, log, customData } = context;
5
6    const { url } = request;
7
8    const lds = $('script[type="application/ld+json"]');
9
10    if (!lds.length) {
11        log.warning('No LD+JSON found on page', { url });
12        return {
13            data: {},
14            url,
15            customData,
16        };
17    }
18
19    return lds
20        .map((_, el) => $(el).html().trim())
21        .get()
22        .map((html) => {
23            try {
24                return JSON.parse(html);
25            } catch (e) {
26                log.exception(e, 'Invalid JSON', { url });
27            }
28        })
29        .filter(Boolean)
30        .map((data) => {
31            return {
32                data,
33                url,
34                customData,
35            }
36        });
37};
38
39Apify.main(async () => {
40    const { proxyConfiguration, startUrls, customData } = await Apify.getInput();
41
42    if (!proxyConfiguration) {
43        throw new Error('You require a proxy to run');
44    }
45
46    // test proxy
47    const proxy = await Apify.createProxyConfiguration(proxyConfiguration);
48
49    if (!proxy) {
50        throw new Error('Invalid proxy configuration');
51    }
52
53    if (!startUrls?.length) {
54        throw new Error('Provide a RequestList sources array on "startUrls" input'); 
55    }
56
57    await Apify.metamorph('apify/cheerio-scraper', {
58        startUrls,
59        pageFunction: pageFunction.toString(),  
60        proxyConfiguration,  
61        customData,
62        ignoreSslErrors: true,
63    });
64});

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": "^2.2.1"
7    },
8    "scripts": {
9        "start": "node main.js",
10        "lint": "./node_modules/.bin/eslint ./src --ext .js,.jsx",
11        "lint:fix": "./node_modules/.bin/eslint ./src --ext .js,.jsx --fix",
12        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
13    },
14    "author": "It's not you it's me",
15    "license": "ISC"
16}
Developer
Maintained by Community

Actor Metrics

  • 13 monthly users

  • 5 stars

  • >99% runs succeeded

  • Created in Feb 2022

  • Modified 3 years ago