Knowledgator Docs
GitHubDiscord
  • 🛎️Welcome
  • ⚙️Models
    • 🧮Comprehend-it
      • Comprehend_it-base
      • Comprehend_it-multilingual-t5-base
    • 🦎UTC
  • 👷Frameworks
    • 💧LiqFit
      • Quick Start
      • Benchmarks
      • API Reference
        • Collators
          • NLICollator
          • Creating custom collator
        • Datasets
          • NLIDataset
        • Losses
          • Focal Loss
          • Binary Cross Entropy
          • Cross Entropy Loss
        • Modeling
          • LiqFitBackbone
          • LiqFitModel
        • Downstream Heads
          • LiqFitHead
          • LabelClassificationHead
          • ClassClassificationHead
          • ClassificationHead
        • Pooling
          • GlobalMaxPooling1D
          • GlobalAbsAvgPooling1D
          • GlobalAbsMaxPooling1D
          • GlobalRMSPooling1D
          • GlobalSumPooling1D
          • GlobalAvgPooling1D
          • FirstTokenPooling1D
        • Models
          • Deberta
          • T5
        • Pipelines
          • ZeroShotClassificationPipeline
  • 📚Datasets
    • Biotech news dataset
  • 👩‍🔧Support
  • API Reference
    • Comprehend-it API
    • Entity extraction
      • /fast
      • /deterministic
      • /advanced
    • Token searcher
    • Web2Meaning
    • Web2Meaning2
    • Relation extraction
    • Text2Table
      • /web2text
      • /text_preprocessing
      • /text2table
      • /merge_tables
Powered by GitBook
On this page
  1. API Reference
  2. Text2Table

/web2text

PreviousText2TableNext/text_preprocessing

Last updated 1 year ago

Scrape web information and prepare it for processing by the Text2Table API

POST https://text2table.p.rapidapi.com/t2t/web2text

The Web2Text API serves as an alternative to the endpoint, with the added capability of extracting text directly from a web page.

Headers

Name
Type
Description

X-RapidAPI-Key*

String

Your API key.

X-RapidAPI-Host*

String

text2table.p.rapidapi.com

content-type*

String

application/json

Request Body

Name
Type
Description

url*

String

A URL of the web page from which text needs to be extracted.

columns

Strings list

Column names for the result table. Check out more .

split

int

Determines the token count for each text chunk in the preprocessing phase. Check out more .

Indicates that your request has been successfully processed, and the response will include a table with the data from the given text. Check out more details on the .

This may be due to missing or improperly formatted parameters. Check for parameter type mismatches, Invalid characters or bad code formatting. Refer to this for guidance.

Your request lacks proper authorization. Ensure your RapidAPI key is correct and included in the request headers. See authorization guidelines.

Check for parameter type mismatches, Invalid characters or bad code formatting. The required header might be wrong, such as X-RapidAPI-Host. Refer to this for guidance.

You've gone over the 30 KB limit with your submitted data. Please see our limits page for proper API request sizes. If you need to increase your limit, our support team is here to help.

An unexpected issue occurred on our end. We are notified and investigating. If this issue persists or follows a pattern, please contact our support. Join our for support.

text_preprocessing
response
example request
example request
Discord
Where can I get it?
details
details