Pay $9.00 for 1,000 pages

GPT Scraper

drobnikj/gpt-scraper

Pay $9.00 for 1,000 pages

Extract data from any website and feed it into GPT via the OpenAI API. Use ChatGPT to proofread content, analyze sentiment, summarize reviews, extract contact details, and much more.

Do you want to learn more about this Actor?

Get a demo

Back to issues Create new issue

Not able to scrape filmot.com

Closed

jen_brown_done opened this issue

When I try to scrape based on a specific url, i get 3 total results but the page is a full grid of text.

Sviatozar Petrenko (svpetrenko)

Hi! This is because this scraper uses GPT-4o mini. It has limited context length. The max context allowed is around 8k tokens, while the length required to scrape your page is 70+k tokens. I'd recommend using Extended GPT Scraper where you'd select GPT-4o (without mini) model. Here is an example run with more results https://console.apify.com/view/runs/nOYNHy1su3IGo72Bo (it also has json schema for output, you may find it helpful).

As an alternative, you may reduce content being sent to GPT by adding additional elements to "Remove HTML elements (CSS selector)" input, until log messages no longer say that the content is trimmed.

Let me know if this helps

jen_brown_done

Hello! This worked! thank you!

Lukáš Průša (lukas.prusa)

That’s great! We are happy to hear that!

Add comment

Developer

Jakub Drobník

Actor Metrics

155 monthly users
64 stars
>99% runs succeeded
2 days response time
Created in Mar 2023
Modified 4 days ago

Categories

Lead generation

Other

Extended GPT Scraper

drobnikj/extended-gpt-scraper

Extract data from any website and feed it into GPT via the OpenAI API. Use ChatGPT to proofread content, analyze sentiment, summarize reviews, extract contact details, and much more.

Jakub Drobník

1.2k

Free GPTs Scraper

seadapp/free-gpts-scraper

Gets you GPT data from Openai. Download your data as JSON, HTML Table, CSV, Execl, RSS Feed

Seadapp

Twitter Tweets and Profiles Scraper

web.harvester/twitter-scraper

Easily search and extract tweets from profiles or directly using a URL with our tool. Scrape tweets and replies effortlessly. Download data in formats like JSON, CSV, XML, RSS, or HTML Table, perfect for integration with various applications, databases, and social media analytics tools.

Web Harvester

2.2k

Easy Twitter Search Scraper

web.harvester/easy-twitter-search-scraper

Easily Scrape tweets with our Twitter Search Scraper. Export data in formats like JSON and Excel perfect for integration with various applications, databases, and data analysis tools.

Web Harvester

3.4k

Get ChatGPT GPT info

manageable_yager/get-chatgpt-gpt-info

Scrape public information about a GPT in the ChatGPT store using it's link.

GPTEEZY Official

Indeed job scraper

curious_coder/indeed-scraper

This is an actively maintained scraper which can extract job postings and hiring company details at scale from any indeed search results page for a fixed monthly rental price. Well documented with examples and demos

Curious Coder

722

Text Scraper (Free)

karamelo/text-scraper-free

Website Text Extractor. Extract Text from Webpages and Feed Your LLMs

karamelo

117

Pinecone GPT Chatbot

tri_angle/pinecone-gpt-chatbot

Pinecone GPT Chatbot combines OpenAI's GPT models with Pinecone's database to generate insightful responses. Its interactive chatbot interface presents precise and comprehensive answers to user queries. Benefit from semantic understanding, efficient workflows, and enriched knowledge integration!

Tri⟁angle

LinkedIn People Profile Scraper

pratikdani/linkedin-people-profile-scraper

Retrieve LinkedIn profile URLs and extract comprehensive profile details. This includes basic information, employment history, skills, company information, biography, location, and more.

Pratik Dani

225

Youtube Channel Scraper

powerful_bachelor/Youtube-Channel-Scraper

The YouTube Channel Scraper is a powerful tool for extracting detailed info from YT channels. It retrieves video count 📹, subscribers count 📊, description 📝, verification status ✅, keywords 🏷️, tags 🔖, view count 👁️, and social media links 🔗. Ideal for researchers, marketers, and creators!!