Powerful Web Scraping - Scalable, Multiple Page Crawling API for LLM Apps and AI Workflows

Sdílet
Vložit
  • čas přidán 29. 08. 2024

Komentáře • 11

  • @Dreysimmons
    @Dreysimmons Před měsícem

    Wow! buildship just keeps getting better and better and better!! My goodness!. If there was a no-code/low-code tool that gives its users, even those who don't really understand too much code SUPER POWERS, its gotta be BUILDSHIP!!! Wow and the tutorials just keep getting better and more explanatory, even for non-technical minds! Awesome Job guys!.............This dynamic scraping method is exactly what a client needed to solve a problem, thanks for giving me the solution!😁

  • @FelixI-js6yk
    @FelixI-js6yk Před 2 měsíci

    LLM extraction option looks insanely useful, thank you guys!
    I have one question regarding the process. 11:20 - should I specify the exact names of fields to parse?
    For example, I want to crawl & scrape 100 sites (collected by Google SERP scraping, with different sitemaps, structure and complexity, various JS selectors and fields naming), containing info about marketing agencies, to get the list of all agencies (name+link). Since there are many naming options for the same fields for each website, is there any possibility to give less accurate instructions like "marketing agecy name" + "marketing agecy link", instead of "name"+"link"?
    If there is such option and performance won't suffer - you can't imagine how happy would I be :) Thanks in advance!

  • @MrLaretos
    @MrLaretos Před 2 měsíci

    Awesome!
    How can I add a referral code to the product links to provide them to my clients?

  • @estefanocampoverde3660
    @estefanocampoverde3660 Před 2 měsíci

    I need tutorials on how to create flows with AI

  • @theadaloguy
    @theadaloguy Před 2 měsíci +1

    Is it possible to use proxy with LLM scrape? Or send our own scraped data for the LLM to process?

    • @BuildShipApp
      @BuildShipApp  Před 2 měsíci +2

      The LLM Extract node has been updated to take any text input you want instead of a URL. Extracting from URL has been moved to it's own node. So now you can just pass your own scraped content directly to the node.

    • @theadaloguy
      @theadaloguy Před 2 měsíci +1

      @BuildShipApp this is amazing. I'm really impressed with all the templates Buildship are coming out with. Keep up the good work!

  • @estefanocampoverde3660
    @estefanocampoverde3660 Před 2 měsíci

    Can use that for get my bank account info?

    • @BuildShipApp
      @BuildShipApp  Před 2 měsíci +1

      Hi! While BuildShip can be a powerful tool for web scraping, it's important to note that accessing bank account information through unauthorized means can be illegal and unsafe. Instead, many banks offer official APIs for accessing account data securely.

    • @estefanocampoverde3660
      @estefanocampoverde3660 Před 2 měsíci

      @@BuildShipApp in Ecuador and other countries in iberoameric that API dont exist

    • @estefanocampoverde3660
      @estefanocampoverde3660 Před 2 měsíci

      @@BuildShipApp In Ibero-American countries, banks do not have APIs, so it is necessary and many companies use their RPA precisely for this thing that banks have not solved and will not do so until perhaps several decades later.