Extracting Data
How to use Parseur core features to parse and extract data from emails and documents
30 articles
- AI vs Template Parsing: Pros and ConsUnderstand the benefits and drawbacks of Parseur’s three parsing engines
- Manage Your Mailbox FieldsWhat are fields and how to manage them effectively?
- Extract Metadata From Emails and Documents With Metadata FieldsHow to use Metadata Fields to automatically add document metadata to your parsed result
- Mailbox Options and SettingsAll mailbox settings and what they do
- Fixing Documents With “Process Failed” StatusWhat should you do when Parseur cannot process your document?
- How to Restrict Field Outputs to a List of Allowed ChoicesLimit a Field to Allowed Values
- How to Use Instructions to Improve AI Data ExtractionTips, Best Practices and Examples using Instructions
- Understanding Parseur's AI EnginesLearn how to pick the right AI engine for your use case
- Extract Nested Tables (Table-in-Table) With the AI EngineExtract tables inside tables, like invoices and their line items, in a single pass
- Use Labels to dynamically position fields (Dynamic OCR)How to use the Labels to capture data from fields that can move horizontally or vertically in a document
- Extract PDF Tables With OCRHow to setup your OCR template to extract data from PDFs tables
- Only Process or Ignore Certain PagesHow to use the page processing options to restrict processing to only certain pages or exclude some pages from the processing
- When to Use the Force OCR OptionHow the Force OCR option can help when the text extracted from your PDFs is incorrect
- Extract Tables and Repetitive Structures From EmailsHow to extract variable length tables and repetitive blocks in Parseur
- Use the Source View to Extract Links and Hidden AttributesHow to use the Source view in the Template Editor to capture hidden attributes like links
- Extract text from plain-text documentsTips and best practices to parse plain-text documents
- Understand How the Text Parsing Engine WorksUnderstanding how Parseur works in order to get the most out of your templates
- Working with predefined mailboxesHow to use Parseur ready-made mailboxes to quick start extracting data from documents form a specific domain or industry
- Full Text Content predefined mailboxUse the Full Text mailbox to extract document content and metadata
- Food Orders Predefined MailboxSupported platforms and extracted fields of the Food Orders predefined mailbox
- Real Estate Predefined MailboxSupported platforms and extracted fields of the real estate predefined mailbox
- Property Bookings Predefined Mailbox
- Master and Apprentice MailboxesLet Parseur automatically populate your newly-created mailboxes with fields from a Master mailbox
- Add Custom Values to Extracted Data With Static FieldsHow to use static fields to add custom data not found in the original document
- Download and Parse a Webpage From a Link in a DocumentHow to automatically download a webpage and parse its content
- Advanced Template Actions: Skip Document, Delete Document, Rename, Disable, CopyUnderstand advanced template actions: what they do and how to use them.
- Understand How Parseur Picks a TemplateHow to work with multiple templates and ensure Parseur always picks the right one
- Working With Email AttachmentsHow to extract text from documents attached to emails
- Working With Field ConstraintsAdd field constraints to be more restrictive on the content of a field
- Review Your Parsed Data With the Explore Data TabThe Explore Data feature gives you a powerful way to browse, search, filter, and analyze the data extracted by Parseur — all from a spreadsheet-like interface.