RBI Latest

# Specify the base Docker image. You can read more about
# the available images at https://crawlee.dev/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node-playwright-chrome:18

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY --chown=myuser package*.json ./

# Install NPM packages, skip optional and development dependencies to
# keep the image small. Avoid logging too much and print the dependency
# tree for debugging
RUN npm --quiet set progress=false \
    && npm install --omit=dev --omit=optional \
    && echo "Installed NPM packages:" \
    && (npm list --omit=dev --all || true) \
    && echo "Node.js version:" \
    && node --version \
    && echo "NPM version:" \
    && npm --version \
    && rm -r ~/.npm

# Next, copy the remaining files and directories with the source code.
# Since we do this after NPM install, quick build will be really fast
# for most source file changes.
COPY --chown=myuser . ./


# Run the image. If you know you won't need headful browsers,
# you can remove the XVFB start script for a micro perf gain.
CMD ./start_xvfb_and_run_cmd.sh && npm start --silent

{
	"actorSpecification": 1,
	"name": "RBI-latest",
	"title": "Project Playwright Crawler JavaScript",
	"description": "Crawlee and Playwright project in JavaScript.",
	"version": "0.0",
	"meta": {
		"templateId": "js-crawlee-playwright-chrome"
	},
	"input": "./input_schema.json",
	"dockerfile": "./Dockerfile"
}

{
    "title": "PlaywrightCrawler Template",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "startUrls": {
            "title": "Start URLs",
            "type": "array",
            "description": "URLs to start with.",
            "editor": "requestListSources",
            "prefill": [
                {
                    "url": "https://apify.com"
                }
            ]
        }
    }
}

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});

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git

root = true

[*]
indent_style = space
indent_size = 4
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
end_of_line = lf

{
    "extends": "@apify",
    "root": true
}

# This file tells Git which files shouldn't be added to source control

.DS_Store
.idea
dist
node_modules
apify_storage
storage

# Added by Apify CLI
.venv

# Specify the base Docker image. You can read more about
# the available images at https://crawlee.dev/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node-playwright-chrome:20

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY --chown=myuser package*.json ./

# Install NPM packages, skip optional and development dependencies to
# keep the image small. Avoid logging too much and print the dependency
# tree for debugging
RUN npm --quiet set progress=false \
    && npm install --omit=dev --omit=optional \
    && echo "Installed NPM packages:" \
    && (npm list --omit=dev --all || true) \
    && echo "Node.js version:" \
    && node --version \
    && echo "NPM version:" \
    && npm --version

# Next, copy the remaining files and directories with the source code.
# Since we do this after NPM install, quick build will be really fast
# for most source file changes.
COPY --chown=myuser . ./


# Run the image. If you know you won't need headful browsers,
# you can remove the XVFB start script for a micro perf gain.
CMD ./start_xvfb_and_run_cmd.sh && npm start --silent

{
	"purgeOnStart": false
}

{
	"name": "consumerfinance",
	"version": "0.0.1",
	"type": "commonjs",
	"description": "consumerfinance rules extractor",
	"dependencies": {
		"22": "^0.0.0",
		"apify": "^3.1.10",
		"crawlee": "^3.5.4",
		"fs": "^0.0.1-security",
		"node-fetch": "^3.3.2",
		"path": "^0.12.7",
		"pdf-parse": "^1.1.1",
		"playwright": "^1.44.0"
	},
	"devDependencies": {
		"@apify/eslint-config": "^0.4.0",
		"@playwright/test": "^1.43.1",
		"@types/pdf-parse": "^1.1.4",
		"eslint": "^8.50.0"
	},
	"scripts": {
		"start": "node src/main.js",
		"lint": "eslint ./src --ext .js,.jsx",
		"lint:fix": "eslint ./src --ext .js,.jsx --fix",
		"test": "echo \"Error: oops, the no tests yet, sad!\" && exit 1",
		"postinstall": "npx crawlee install-playwright-browsers"
	},
	"author": "Moazzam Malek"
}