Created a new Crawlee + PlaywrightCrawler + TypeScript project.

This commit is contained in:
David Ball 2024-06-04 21:34:46 -04:00
commit 5adac13cf7
9 changed files with 3922 additions and 0 deletions

10
.dockerignore Normal file
View File

@ -0,0 +1,10 @@
# configurations
.idea
# crawlee and apify storage folders
apify_storage
crawlee_storage
storage
# installed files
node_modules

8
.gitignore vendored Normal file
View File

@ -0,0 +1,8 @@
# This file tells Git which files shouldn't be added to source control
.idea
dist
node_modules
apify_storage
crawlee_storage
storage

51
Dockerfile Normal file
View File

@ -0,0 +1,51 @@
# 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 AS builder
# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY --chown=myuser package*.json ./
# Install all dependencies. Don't audit to speed up the installation.
RUN npm install --include=dev --audit=false
# Next, copy the source files using the user set
# in the base image.
COPY --chown=myuser . ./
# Install all dependencies and build the project.
# Don't audit to speed up the installation.
RUN npm run build
# Create final image
FROM apify/actor-node-playwright-chrome:20
# Copy only built JS files from builder image
COPY --from=builder --chown=myuser /home/myuser/dist ./dist
# 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 run start:prod --silent

8
README.md Normal file
View File

@ -0,0 +1,8 @@
# Crawlee + PlaywrightCrawler + TypeScript project
This template is a production ready boilerplate for developing with `PlaywrightCrawler`. Use this to bootstrap your projects using the most up-to-date code.
If you're looking for examples or want to learn more visit:
- [Documentation](https://crawlee.dev/api/playwright-crawler/class/PlaywrightCrawler)
- [Examples](https://crawlee.dev/docs/examples/playwright-crawler)

3771
package-lock.json generated Normal file

File diff suppressed because it is too large Load Diff

26
package.json Normal file
View File

@ -0,0 +1,26 @@
{
"name": "crawlee-russellcountyva.us",
"version": "0.0.1",
"type": "module",
"description": "This is an example of a Crawlee project.",
"dependencies": {
"crawlee": "^3.0.0",
"playwright": "*"
},
"devDependencies": {
"@apify/tsconfig": "^0.1.0",
"tsx": "^4.4.0",
"typescript": "~5.4.0",
"@types/node": "^20.0.0"
},
"scripts": {
"start": "npm run start:dev",
"start:prod": "node dist/main.js",
"start:dev": "tsx src/main.ts",
"build": "tsc",
"test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1",
"postinstall": "npx crawlee install-playwright-browsers"
},
"author": "It's not you it's me",
"license": "ISC"
}

15
src/main.ts Normal file
View File

@ -0,0 +1,15 @@
// For more information, see https://crawlee.dev/
import { PlaywrightCrawler, ProxyConfiguration } from 'crawlee';
import { router } from './routes.js';
const startUrls = ['https://crawlee.dev'];
const crawler = new PlaywrightCrawler({
// proxyConfiguration: new ProxyConfiguration({ proxyUrls: ['...'] }),
requestHandler: router,
// Comment this option to scrape the full website.
maxRequestsPerCrawl: 20,
});
await crawler.run(startUrls);

21
src/routes.ts Normal file
View File

@ -0,0 +1,21 @@
import { createPlaywrightRouter } from 'crawlee';
export const router = createPlaywrightRouter();
router.addDefaultHandler(async ({ enqueueLinks, log }) => {
log.info(`enqueueing new URLs`);
await enqueueLinks({
globs: ['https://crawlee.dev/**'],
label: 'detail',
});
});
router.addHandler('detail', async ({ request, page, log, pushData }) => {
const title = await page.title();
log.info(`${title}`, { url: request.loadedUrl });
await pushData({
url: request.loadedUrl,
title,
});
});

12
tsconfig.json Normal file
View File

@ -0,0 +1,12 @@
{
"extends": "@apify/tsconfig",
"compilerOptions": {
"module": "NodeNext",
"moduleResolution": "NodeNext",
"target": "ES2022",
"outDir": "dist",
"noUnusedLocals": false,
"lib": ["DOM"]
},
"include": ["./src/**/*"]
}