Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
3 changes: 0 additions & 3 deletions components/webscraping_ai/.gitignore

This file was deleted.

126 changes: 126 additions & 0 deletions components/webscraping_ai/actions/ask-question/ask-question.mjs
Original file line number Diff line number Diff line change
@@ -0,0 +1,126 @@
import webscrapingAI from "../../webscraping_ai.app.mjs";
import utils from "../../common/utils.mjs";

export default {
key: "webscraping_ai-ask-question",
name: "Ask Question about Webpage",
description: "Gets an answer to a question about a given webpage. [See the documentation](https://webscraping.ai/docs#tag/AI/operation/getQuestion)",
version: "0.0.1",
type: "action",
props: {
webscrapingAI,
targetUrl: {
propDefinition: [
webscrapingAI,
"targetUrl",
],
},
question: {
type: "string",
label: "Question",
description: "The question to ask about the given webpage. E.g. `What is the summary of this page content?`",
},
headers: {
propDefinition: [
webscrapingAI,
"headers",
],
},
timeout: {
propDefinition: [
webscrapingAI,
"timeout",
],
},
js: {
propDefinition: [
webscrapingAI,
"js",
],
},
jsTimeout: {
propDefinition: [
webscrapingAI,
"jsTimeout",
],
},
waitFor: {
propDefinition: [
webscrapingAI,
"waitFor",
],
},
proxy: {
propDefinition: [
webscrapingAI,
"proxy",
],
},
country: {
propDefinition: [
webscrapingAI,
"country",
],
},
customProxy: {
propDefinition: [
webscrapingAI,
"customProxy",
],
},
device: {
propDefinition: [
webscrapingAI,
"device",
],
},
errorOn404: {
propDefinition: [
webscrapingAI,
"errorOn404",
],
},
errorOnRedirect: {
propDefinition: [
webscrapingAI,
"errorOnRedirect",
],
},
jsScript: {
propDefinition: [
webscrapingAI,
"jsScript",
],
},
format: {
propDefinition: [
webscrapingAI,
"format",
],
},
},
async run({ $ }) {
const response = await this.webscrapingAI.getAnswerToQuestion({
$,
params: {
url: this.targetUrl,
question: this.question,
headers: utils.stringifyHeaders(this.headers),
timeout: this.timeout,
js: this.js,
js_timeout: this.jsTimeout,
wait_for: this.waitFor,
proxy: this.proxy,
country: this.country,
custom_proxy: this.customProxy,
device: this.device,
error_on_404: this.errorOn404,
error_on_redirect: this.errorOnRedirect,
js_script: this.jsScript,
format: this.format,
},
});
$.export("$summary", "Successfully retrieved answer to question");
return response;
},
};
Original file line number Diff line number Diff line change
@@ -0,0 +1,127 @@
import webscrapingAI from "../../webscraping_ai.app.mjs";
import utils from "../../common/utils.mjs";

export default {
key: "webscraping_ai-scrape-website-html",
name: "Scrape Website HTML",
description: "Returns the full HTML content of a webpage specified by the URL. [See the documentation](https://webscraping.ai/docs#tag/HTML/operation/getHTML):",
version: "0.0.1",
type: "action",
props: {
webscrapingAI,
targetUrl: {
propDefinition: [
webscrapingAI,
"targetUrl",
],
},
headers: {
propDefinition: [
webscrapingAI,
"headers",
],
},
timeout: {
propDefinition: [
webscrapingAI,
"timeout",
],
},
js: {
propDefinition: [
webscrapingAI,
"js",
],
},
jsTimeout: {
propDefinition: [
webscrapingAI,
"jsTimeout",
],
},
waitFor: {
propDefinition: [
webscrapingAI,
"waitFor",
],
},
proxy: {
propDefinition: [
webscrapingAI,
"proxy",
],
},
country: {
propDefinition: [
webscrapingAI,
"country",
],
},
customProxy: {
propDefinition: [
webscrapingAI,
"customProxy",
],
},
device: {
propDefinition: [
webscrapingAI,
"device",
],
},
errorOn404: {
propDefinition: [
webscrapingAI,
"errorOn404",
],
},
errorOnRedirect: {
propDefinition: [
webscrapingAI,
"errorOnRedirect",
],
},
jsScript: {
propDefinition: [
webscrapingAI,
"jsScript",
],
},
format: {
propDefinition: [
webscrapingAI,
"format",
],
},
returnScriptResult: {
type: "boolean",
label: "Return Script Result",
description: "Return result of the custom JavaScript code (`js_script` parameter) execution on the target page (`false` by default, page HTML will be returned).",
optional: true,
},
},
async run({ $ }) {
const response = await this.webscrapingAI.pageHtmlByUrl({
$,
params: {
url: this.targetUrl,
headers: utils.stringifyHeaders(this.headers),
timeout: this.timeout,
js: this.js,
js_timeout: this.jsTimeout,
wait_for: this.waitFor,
proxy: this.proxy,
country: this.country,
custom_proxy: this.customProxy,
device: this.device,
error_on_404: this.errorOn404,
error_on_redirect: this.errorOnRedirect,
js_script: this.jsScript,
format: this.format,
return_script_result: this.returnScriptResult,
},
});
$.export("$summary", `Successfully scraped HTML of URL ${this.targetUrl}`);
return response;
},
};
Original file line number Diff line number Diff line change
@@ -0,0 +1,133 @@
import webscrapingAI from "../../webscraping_ai.app.mjs";
import utils from "../../common/utils.mjs";

export default {
key: "webscraping_ai-scrape-website-text",
name: "Scrape Website Text",
description: "Returns the visible text content of a webpage specified by the URL. [See the documentation](https://webscraping.ai/docs#tag/Text/operation/getText).",
version: "0.0.1",
type: "action",
props: {
webscrapingAI,
targetUrl: {
propDefinition: [
webscrapingAI,
"targetUrl",
],
},
headers: {
propDefinition: [
webscrapingAI,
"headers",
],
},
timeout: {
propDefinition: [
webscrapingAI,
"timeout",
],
},
js: {
propDefinition: [
webscrapingAI,
"js",
],
},
jsTimeout: {
propDefinition: [
webscrapingAI,
"jsTimeout",
],
},
waitFor: {
propDefinition: [
webscrapingAI,
"waitFor",
],
},
proxy: {
propDefinition: [
webscrapingAI,
"proxy",
],
},
country: {
propDefinition: [
webscrapingAI,
"country",
],
},
customProxy: {
propDefinition: [
webscrapingAI,
"customProxy",
],
},
device: {
propDefinition: [
webscrapingAI,
"device",
],
},
errorOn404: {
propDefinition: [
webscrapingAI,
"errorOn404",
],
},
errorOnRedirect: {
propDefinition: [
webscrapingAI,
"errorOnRedirect",
],
},
jsScript: {
propDefinition: [
webscrapingAI,
"jsScript",
],
},
textFormat: {
type: "string",
label: "Text Format",
description: "The format of the returned text content. Default: `json`",
options: [
"plain",
"xml",
"json",
],
default: "json",
optional: true,
},
returnLinks: {
type: "boolean",
label: "Return Links",
description: "Whether to include links in the returned text content. Works only when Text Format is `json`.",
optional: true,
},
},
async run({ $ }) {
const response = await this.webscrapingAI.pageTextByUrl({
$,
params: {
url: this.targetUrl,
headers: utils.stringifyHeaders(this.headers),
timeout: this.timeout,
js: this.js,
js_timeout: this.jsTimeout,
wait_for: this.waitFor,
proxy: this.proxy,
country: this.country,
custom_proxy: this.customProxy,
device: this.device,
error_on_404: this.errorOn404,
error_on_redirect: this.errorOnRedirect,
js_script: this.jsScript,
text_format: this.textFormat,
return_links: this.returnLinks,
},
});
$.export("$summary", `Successfully scraped text from ${this.targetUrl}`);
return response;
},
};
Loading
Loading