with WebScraper.IO and Alibaba Cloud?
Emit new event when a page scraping job has completed. See the docs here
Creates a scraping job (scrapes a sitemap). See the docs here
Creates a sitemap for the selected website. See the docs here
Retrieves a list of scraping jobs for a sitemap. See the docs here
The WebScraper.IO API allows you to programmatically perform web scraping tasks, extracting structured data from websites. With the API, you can automate the gathering of web content for analysis, monitoring, and integration with other data sources. In Pipedream, you can leverage this API to build workflows that process, analyze, and act on the data you scrape without writing code for backend infrastructure.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
webscraper_io: {
type: "app",
app: "webscraper_io",
}
},
async run({steps, $}) {
return await axios($, {
url: `https://api.webscraper.io/api/v1/sitemaps`,
params: {
api_token: `${this.webscraper_io.$auth.api_key}`,
},
})
},
})
import Ecs20140526, * as $Ecs20140526 from '@alicloud/ecs20140526';
import OpenApi, * as $OpenApi from '@alicloud/openapi-client';
import Util, * as $Util from '@alicloud/tea-util';
export default defineComponent({
props: {
alibaba_cloud: {
type: "app",
app: "alibaba_cloud",
}
},
async run({ steps, $ }) {
//Creates a new Alibaba Cloud SDK client
let config = new OpenApi.Config({
accessKeyId: this.alibaba_cloud.$auth.access_key_id,
accessKeySecret: this.alibaba_cloud.$auth.access_key_secret,
});
config.endpoint = this.alibaba_cloud.$auth.endpoint;
//Creates and executes a request
let client = new Ecs20140526.default(config);
let describeRegionsRequest = new $Ecs20140526.DescribeRegionsRequest({});
let runtime = new $Util.RuntimeOptions({});
return await client.describeRegionsWithOptions(describeRegionsRequest, runtime);
},
})