No credit card required
This Actor may be unreliable while under maintenance. Would you like to try a similar Actor instead?
See alternative Actors
Yash Agarwal
1# Specify the base Docker image. You can read more about
2# the available images at https://crawlee.dev/docs/guides/docker-images
3# You can also use any other image from Docker Hub.
4FROM apify/actor-node-playwright-chrome:18
5
6# Copy just package.json and package-lock.json
7# to speed up the build using Docker layer cache.
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 --omit=dev --omit=optional \
15 && echo "Installed NPM packages:" \
16 && (npm list --omit=dev --all || true) \
17 && echo "Node.js version:" \
18 && node --version \
19 && echo "NPM version:" \
20 && npm --version \
21 && rm -r ~/.npm
22
23# Next, copy the remaining files and directories with the source code.
24# Since we do this after NPM install, quick build will be really fast
25# for most source file changes.
26COPY . ./
27
28
29# Run the image. If you know you won't need headful browsers,
30# you can remove the XVFB start script for a micro perf gain.
31CMD ./start_xvfb_and_run_cmd.sh && npm start --silent1{
2 "actorSpecification": 1,
3 "name": "RBI-latest",
4 "title": "Project Playwright Crawler JavaScript",
5 "description": "Crawlee and Playwright project in JavaScript.",
6 "version": "0.0",
7 "meta": {
8 "templateId": "js-crawlee-playwright-chrome"
9 },
10 "input": "./input_schema.json",
11 "dockerfile": "./Dockerfile"
12}1{
2 "title": "PlaywrightCrawler Template",
3 "type": "object",
4 "schemaVersion": 1,
5 "properties": {
6 "startUrls": {
7 "title": "Start URLs",
8 "type": "array",
9 "description": "URLs to start with.",
10 "editor": "requestListSources",
11 "prefill": [
12 {
13 "url": "https://apify.com"
14 }
15 ]
16 }
17 }
18}1const { Actor, Dataset } = require("apify");
2const { PlaywrightCrawler } = require("crawlee");
3const PdfParse = require("pdf-parse");
4
5async function extractText(page) {
6 const data = {
7 heading: [], // Array to hold heading data
8 mainContent: [], // Array for main content data
9 tableData: [], // Array for table data
10 pdfLinks: [], // PDF link URLs
11 PdfData: [], // Extracted data from PDFs
12 };
13
14 // Heading
15 data.heading = await page.$$eval("td b", (headers) => headers.map((header) => header.textContent.trim()));
16
17 // Main content
18 data.mainContent = await page.$$eval("td p", (paragraphs) => paragraphs.map((paragraph) => paragraph.textContent.trim()));
19
20 // Table data
21 data.tableData = await page.$$eval("table tbody .tablebg tr", (rows) => rows.map((row) => row.textContent.trim()));
22
23 // PDF links
24 data.pdfLinks = await page.$$eval("a", (links) => links.filter((link) => link.href.toLowerCase().endsWith(".pdf")).map((link) => link.href));
25
26 // Fetch and parse PDFs
27 const { default: fetch } = await import("node-fetch");
28 const pdfPromises = data.pdfLinks.map(async (pdfLink) => {
29 try {
30 const response = await fetch(pdfLink);
31 const buffer = await response.arrayBuffer();
32 const pdfText = await PdfParse(buffer);
33 return { pdfLink, text: pdfText.text };
34 } catch (error) {
35 return { pdfLink, error: error.message || true };
36 }
37 });
38
39 data.PdfData = await Promise.all(pdfPromises);
40
41 return data;
42}
43
44Actor.main(async () => {
45 const year = 2024;
46
47 const crawler = new PlaywrightCrawler({
48
49 async requestHandler({ request, page, log, enqueueLinks }) {
50 log.info(`Processing ${request.url} for year ${year}`);
51
52 if (request.url === "https://rbi.org.in/Scripts/NotificationUser.aspx") {
53 await page.goto("https://rbi.org.in/Scripts/NotificationUser.aspx");
54
55 // Navigate based on year
56 if (year < 2015) {
57 await page.getByText("Archives").click();
58 await page.waitForTimeout(2000);
59 }
60 await page.locator(`#btn${year}`).click();
61 await page.locator(`//*[@id="${year}0"]`).click();
62
63 await page.waitForTimeout(2000);
64
65 await enqueueLinks({
66 selector: "a.link2",
67 transformRequestFunction: (reqs) => {
68 return reqs.url === "https://rbi.org.in/Scripts/NotificationUser.aspx" ? false : reqs;
69 },
70 });
71
72 } else {
73 // Extract content from the current page
74 const extractedData = await extractText(page);
75
76 await Dataset.pushData({
77 Year: year,
78 URL: request.url,
79 Data: extractedData,
80 });
81 }
82 },
83 });
84
85 await crawler.run(["https://rbi.org.in/Scripts/NotificationUser.aspx"]);
86});1# configurations
2.idea
3
4# crawlee and apify storage folders
5apify_storage
6crawlee_storage
7storage
8
9# installed files
10node_modules
11
12# git folder
13.git1root = true
2
3[*]
4indent_style = space
5indent_size = 4
6charset = utf-8
7trim_trailing_whitespace = true
8insert_final_newline = true
9end_of_line = lf1{
2 "extends": "@apify",
3 "root": true
4}1# This file tells Git which files shouldn't be added to source control
2
3.DS_Store
4.idea
5dist
6node_modules
7apify_storage
8storage
9
10# Added by Apify CLI
11.venv1# Specify the base Docker image. You can read more about
2# the available images at https://crawlee.dev/docs/guides/docker-images
3# You can also use any other image from Docker Hub.
4FROM apify/actor-node-playwright-chrome:20
5
6# Copy just package.json and package-lock.json
7# to speed up the build using Docker layer cache.
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 --omit=dev --omit=optional \
15 && echo "Installed NPM packages:" \
16 && (npm list --omit=dev --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
28# Run the image. If you know you won't need headful browsers,
29# you can remove the XVFB start script for a micro perf gain.
30CMD ./start_xvfb_and_run_cmd.sh && npm start --silent1{
2 "purgeOnStart": false
3}1{
2 "name": "consumerfinance",
3 "version": "0.0.1",
4 "type": "commonjs",
5 "description": "consumerfinance rules extractor",
6 "dependencies": {
7 "22": "^0.0.0",
8 "apify": "^3.1.10",
9 "crawlee": "^3.5.4",
10 "fs": "^0.0.1-security",
11 "node-fetch": "^3.3.2",
12 "path": "^0.12.7",
13 "pdf-parse": "^1.1.1",
14 "playwright": "^1.44.0"
15 },
16 "devDependencies": {
17 "@apify/eslint-config": "^0.4.0",
18 "@playwright/test": "^1.43.1",
19 "@types/pdf-parse": "^1.1.4",
20 "eslint": "^8.50.0"
21 },
22 "scripts": {
23 "start": "node src/main.js",
24 "lint": "eslint ./src --ext .js,.jsx",
25 "lint:fix": "eslint ./src --ext .js,.jsx --fix",
26 "test": "echo \"Error: oops, the no tests yet, sad!\" && exit 1",
27 "postinstall": "npx crawlee install-playwright-browsers"
28 },
29 "author": "Moazzam Malek"
30}