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

prompt gets filled with base64 representation of image

Open

Pepa <b>J</b> (JoseJet) opened this issue

For this input, the Actor returned wrong answer, when we checked the MD generated prompt from KV-store it was overflowed with base64 inline representation from one of the images on the website.

When we remove the img, link tags everything works fine. I do not think that including inline base64 encoded source of image into the prompt should be default behavior.

1{
2  "dynamicContentWaitSecs": 10,
3  "instructions": "Gets the amount of results on the page and return it as single number in JSON format: \njobAmount",
4  "pageFormatInRequest": "Markdown",
5  "proxyConfiguration": {
6    "useApifyProxy": true
7  },
8  "removeElementsCssSelector": "script, style, noscript, path, svg, xlink",
9  "removeLinkUrls": true,
10  "saveSnapshots": true,
11  "schema": {
12    "type": "object",
13    "properties": {
14      "jobAmount": {
15        "type": "number",
16        "description": "results"
17      }
18    },
19    "required": [
20      "jobAmount"
21    ]
22  },
23  "startUrls": [
24    {
25      "url": "https://workforcenow.adp.com/mascsr/default/mdf/recruitment/recruitment.html?cid=e4f6ff38-1bcd-40e3-b778-ec98a30f2192&ccId=19000101_000001&type=MP&lang=en_US&selectedMenuKey=CurrentOpenings",
26      "method": "GET"
27    }
28  ],
29  "useStructureOutput": false,
30  "includeUrlGlobs": [],
31  "excludeUrlGlobs": [],
32  "maxCrawlingDepth": 99999999,
33  "maxPagesPerCrawl": 10,
34  "initialCookies": [],
35  "temperature": "0",
36  "topP": "1",
37  "frequencyPenalty": "0",
38  "presencePenalty": "0"
39}

Lukáš Průša (lukas.prusa)

Thanks for reporting this!

Yeah, this should definitely not be the default, it should get processed out of the page content before it is sent to the GPT. We will investigate and fix this :)

Add comment

Developer

Jakub Drobník

Actor Metrics

150 monthly users
69 stars
>99% runs succeeded
2.6 days response time
Created in Mar 2023
Modified 8 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

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

Linkedin x GPT prompt

anchor/linkedin-gpt-prompt

Extract LinkedIn profiles, and uses ChatGPT magic automatically on each profile ! Your prompt, the answer you need, the way you want.

Anchor

WCC Pinecone Integration

tri_angle/wcc-pinecone-integration

Crawl any website and store its content in your Pinecone vector database. Enhance the accuracy and reliability of your own AI Assistant with facts fetched from external sources or connect this integration to our Pinecone GPT Chatbot assistant available in Apify Store.

Tri⟁angle

Website Content Crawler

apify/website-content-crawler

Crawl websites and extract text content to feed AI models, LLM applications, vector databases, or RAG pipelines. The Actor supports rich formatting using Markdown, cleans the HTML, downloads files, and integrates well with 🦜🔗 LangChain, LlamaIndex, and the wider LLM ecosystem.

Apify

28.5k

718

Google Maps Extractor

compass/google-maps-extractor

Extract data from hundreds of places fast. Scrape Google Maps by keyword, category, location, URLs & other filters. Get addresses, contact info, opening hours, popular times, prices, menus & more. Export scraped data, run the scraper via API, schedule and monitor runs, or integrate with other tools.

Compass

21k

456

Instagram Scraper

apify/instagram-scraper

Scrape and download Instagram posts, profiles, places, hashtags, photos, and comments. Get data from Instagram using one or more Instagram URLs or search queries. Export scraped data, run the scraper via API, schedule and monitor runs or integrate with other tools.

Apify

61.8k

588

Facebook Posts Scraper

apify/facebook-posts-scraper

Extract data from hundreds of Facebook posts from one or multiple Facebook pages and profiles. Get post URL, post text, page or profile URL, timestamp, number of likes, shares, comments, and more. Download the data in JSON, CSV, and Excel and use it in apps, spreadsheets, and reports.

Apify

15.6k

204

Contact Details Scraper

vdrmota/contact-info-scraper

Free email extractor and lead scraper to extract and download emails, phone numbers, Facebook, Twitter, LinkedIn, and Instagram profiles from any website. Extract contact information at scale from lists of URLs and download the data as Excel, CSV, JSON, HTML, and XML.