Run any Skill in Manus with one click

web-scraping

Stars2

Forks3

UpdatedJune 26, 2026 at 17:11

Scrapes webpages for text and images using a headless browser (JS-rendered) or static HTML. Downloads images and files from the web.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

Rotoslider

Rotoslider/Choom

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

3 files

SKILL.md

readonly

name	web-scraping
description	Scrapes webpages for text and images using a headless browser (JS-rendered) or static HTML. Downloads images and files from the web.
version	2.0.0
author	system
tools	["scrape_page_content","scrape_page_images","download_web_image","download_web_file"]
dependencies	[]

Web Scraping & Downloads

When to Use

Scrape page text + images (JS-rendered) -> scrape_page_content (best for modern sites, SPAs, product pages)
Find images on a simple page -> scrape_page_images (faster, static HTML only)
Download image -> download_web_image (after scraping for real URLs)
Download file (PDF, doc, etc.) -> download_web_file

scrape_page_content vs scrape_page_images

scrape_page_content: Uses headless Chromium, renders JavaScript, extracts text AND images. Use for product pages, SPAs, dynamic content. Returns text + sorted images (largest first).
scrape_page_images: Static HTML fetch, faster but misses JS-loaded content. Use for simple pages with standard img tags.

Important

NEVER guess CDN URLs -- always scrape first
WebP images auto-converted to PNG on download
Browser User-Agent headers used to avoid 403 blocks
Image download: 10MB limit, File download: 50MB limit
scrape_page_content text capped at 15K chars to avoid context bloat

More from this repository

same repository

home-assistant

Rotoslider/Choom

Controls smart home devices and reads sensor data via Home Assistant

2026-06-262

self-scheduling

Rotoslider/Choom

Lets a Choom queue its OWN future followup. The Choom writes a short prompt to itself; the bridge fires it as a one-shot heartbeat at the scheduled time. Use to self-trigger proactive check-ins, reminders to revisit an unfinished thread, or to wake up after an expected interval.

2026-06-262

group-chat

Rotoslider/Choom

Start a live group conversation with one or more sister Chooms — a real back-and-forth chat (not a task hand-off). Use to check in, think together, plan, or connect. The user can see and join.

2026-06-222

workspace-files

Rotoslider/Choom

Sandboxed file operations in project workspace — create projects, write, read, list, create folders, delete files, and rename projects. Use for saving reports, code, notes, or managing project files.

2026-06-152

image-generation

Rotoslider/Choom

Generates images using Stable Diffusion with checkpoint switching, LoRA support, and self-portrait mode. Use when the user requests pictures, artwork, selfies, or portraits.

2026-06-152

google-docs

Rotoslider/Choom

Manages Google Documents — list, create, read, and append text. Use for reports, letters, notes, and documents.

2026-06-142

name	web-scraping
description	Scrapes webpages for text and images using a headless browser (JS-rendered) or static HTML. Downloads images and files from the web.
version	2.0.0
author	system
tools	["scrape_page_content","scrape_page_images","download_web_image","download_web_file"]
dependencies	[]

Web Scraping & Downloads

When to Use

Scrape page text + images (JS-rendered) -> scrape_page_content (best for modern sites, SPAs, product pages)
Find images on a simple page -> scrape_page_images (faster, static HTML only)
Download image -> download_web_image (after scraping for real URLs)
Download file (PDF, doc, etc.) -> download_web_file

scrape_page_content vs scrape_page_images

scrape_page_content: Uses headless Chromium, renders JavaScript, extracts text AND images. Use for product pages, SPAs, dynamic content. Returns text + sorted images (largest first).
scrape_page_images: Static HTML fetch, faster but misses JS-loaded content. Use for simple pages with standard img tags.

Important

NEVER guess CDN URLs -- always scrape first
WebP images auto-converted to PNG on download
Browser User-Agent headers used to avoid 403 blocks
Image download: 10MB limit, File download: 50MB limit
scrape_page_content text capped at 15K chars to avoid context bloat