Results for “scrape”

MCP server for scraping Italian rental/sale property listings from multiple real estate portals (Immobiliare.it, Casa.it, and extensible to others) using Camoufox (anti-detection browser) and BeautifulSoup. Plugin architecture — each site is a self-contained adapter with its own URL templates, query param mappings, and CSS selector chains. Use this skill whenever the user wants to search for apartments, houses, or properties in Italy, scrape real estate listings, compare rental prices across Italian cities, or extract property data from Italian portals. Triggers on mentions of immobiliare, casa.it, Italian rentals, affitto, vendita, apartment hunting in Italy, or property scraping.

The English summary is being prepared. Showing the original description.

Control and interact with a live browser session on any scraped page — click buttons, fill forms, navigate flows, and extract data using natural language prompts or code. Use when the user needs to interact with a webpage beyond simple scraping: logging into a site, submitting forms, clicking through pagination, handling infinite scroll, navigating multi-step checkout or wizard flows, or when a regular scrape failed because content is behind JavaScript interaction. Also useful for authenticated scraping via profiles. Triggers on "interact", "click", "fill out the form", "log in to", "sign in", "submit", "paginated", "next page", "infinite scroll", "interact with the page", "navigate to", "open a session", or "scrape failed".

The English summary is being prepared. Showing the original description.

Integrate Firecrawl browser actions into application code to retrieve content that requires clicks, form entry, or pagination. Use it for multi-step page interactions and workflows that need to preserve the browser session after scraping.

• Retrieving content revealed by clicks
• Working with search forms and filters
• Collecting results across multiple pages

Build web search, page content retrieval, structured data extraction, and browser interactions into applications with Firecrawl. The skill guides endpoint selection, credentials, SDK or REST integration, and verification with a real request.

• Adding web search to an application
• Extracting structured data from known URLs
• Building website clicks and form filling into a workflow

Search and export public LinkedIn job postings without a LinkedIn login. Gather available salary, seniority, recruiter and company details, compare hiring activity, and organize results by role, location or posting date.

• Find newly posted jobs in a selected city
• Compare advertised salaries for a role
• Identify companies hiring for specific skills

Research public TikTok videos, creators, hashtags, comments and followers without a TikTok login. Collect viewing and engagement statistics, filter results by date or likes, and export findings for content planning or creator research.

• Compare recent videos from selected creators
• Find popular videos for a hashtag
• Export video comments and replies

Research public Meta Ad Library ads by advertiser or keyword. Export ad copy, image and video links, and running dates, then compare active ads by duration and review reach or spending figures where disclosed.

• Review a competitor's active ads
• Find long-running ads for a product keyword
• Export an advertiser's recent ads

Build Python applications that keep other tasks moving while waiting for network, file, or database operations. The skill guides asyncio patterns, task cancellation, timeouts, workload limits, and testing for asynchronous APIs, scrapers, and background processing.

• Building asynchronous web APIs
• Sending concurrent requests in web scrapers
• Designing background tasks and queues

Build integrations that use Xquik to search X posts, retrieve profiles and followers, monitor accounts, and draw giveaway winners. Includes API authentication, bulk extraction with cost estimates, real-time notifications, and MCP connections for agent access.

• Searching posts and researching user profiles
• Extracting follower lists for CSV export
• Receiving notifications about account activity

Extract web page content as Markdown from a single URL or a site crawl. When access is blocked, progressively switch from basic fetching to Chrome and Bright Data proxy services, which route requests through other IP addresses.

• Converting a single web page to Markdown
• Extracting content from JavaScript-rendered pages
• Retrieving pages blocked by bot detection

Collect posts from an Instagram profile, including captions, image and video URLs, like and comment counts, timestamps, and location tags. Follow successive result pages to assemble the posts accessible to the logged-in account.

• Collect an account’s profile posts
• Review captions and engagement counts
• Compile image and video URLs

Retrieve a Xiaohongshu creator’s profile and published posts using their user ID. Collect their bio, follower counts, tags, and post engagement figures to support creator research and account comparisons.

• Research creator profiles and follower counts
• Review a creator’s published posts and engagement
• Gather information to compare influencer candidates

Extract Google search results into structured data, including organic listings, ads, related searches, and People Also Ask questions. Set language and country parameters, collect result positions, and capture AI Overview text when it appears.

• Checking result positions for a keyword
• Collecting ads shown in search results
• Gathering related searches and common questions

Search Xiaohongshu posts by keyword and filters, then collect body text, tags, image and video URLs, publication times, and engagement counts. Check both titles and body text to find relevant mentions for topic or brand research.

• Find posts mentioning a brand
• Collect recent video posts
• Compare likes and saves across posts

Collect top Instagram posts for a hashtag, including captions, like and comment counts, media URLs, and usernames. Use the results to review topic-related content and compare engagement across the returned posts.

• Collecting top posts for a hashtag
• Comparing like and comment counts
• Reviewing captions and media URLs

Search Douyin videos by keyword and collect structured results with creator details, engagement counts, descriptions, hashtags, covers, and download links. Filter by posting period and sort by relevance, likes, or newest posts.

• Researching Douyin videos about a specific topic
• Comparing videos sorted by likes
• Collecting recent posts and hashtags

Collect posts from public Facebook Pages or personal profile timelines as structured data. Capture text, author details, reactions, comments and share counts, plus media information, with date options and pagination for larger collections.

• Comparing reactions across Facebook posts
• Collecting posts around a specified date range
• Gathering post text, media links and author details

Collect posts from public Facebook Pages with their text, authors, links, hashtags, and engagement counts. Gather reaction breakdowns and multiple batches of posts to review page activity, compare responses, or collect content around a chosen period.

• Collect posts from a public Facebook Page
• Compare reaction types across posts
• Gather posts around a campaign period

Search Meta Ad Library by keyword or Facebook page ID and collect ad text, images, videos, destination links, and publishing platforms. Filter by country and ad status to gather material for competitor advertising research.

• Researching competitors' ad copy and visuals
• Collecting ads from a specific Facebook page
• Comparing ads by country and publishing platform

Collect sold listings from eight eBay marketplaces and organize displayed prices, shipping costs, conditions, sale dates, and seller details. Filter results to research resale values and compare prices across markets, with accepted offers flagged separately.

• Research resale prices for used products
• Compare sold prices across eBay marketplaces
• Collect sales records for collectibles

Extract wholesale product details from 1688.com, including quantity-based prices, product variants with dimensions and weight, seller information, shop scores, promotions, and review summaries. Organize these details to compare sourcing options and supplier metrics.

• Compare wholesale prices by order quantity
• Check dimensions and weight for product variants
• Compare supplier scores and repeat purchase rates

Search LinkedIn jobs by keywords, location, work arrangement, employment type, experience level, posting date, and company. Collect job descriptions, applicant counts, direct links, and salary information when provided to organize potential opportunities.

• Finding remote or hybrid job openings
• Filtering jobs by employment type and experience
• Collecting recently posted jobs from selected companies

Extract details from an open eBay listing into JSON, a structured data format. Collect prices, availability, sales counts, seller feedback, specifications, and image links for product comparisons and catalog checks across regional eBay sites.

• Comparing prices and availability across eBay listings
• Checking seller feedback and item locations
• Collecting product identifiers and specifications

Collect Airbnb accommodation search results for a destination, including listing links, locations, ratings, prices, photos, and badges. Specify dates, guest counts, and budget filters, then retrieve multiple pages of accommodation options.

• Collecting accommodation options for a destination
• Finding listings within a budget for specific dates
• Comparing accommodation ratings and photos