{"version":"2.1.323","anchor":"pdf-page-text-extraction-via-pdftotext-added","canonical_anchor":"pdf-page-text-extraction-via-pdftotext-added","heading":"Claude Code can pull page-by-page text out of PDFs with pdftotext","tier":"notice","area":"PDF Reading","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323\/e\/pdf-page-text-extraction-via-pdftotext-added","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323","markdown":"### Claude Code can pull page-by-page text out of PDFs with `pdftotext`\n\nClaude Code can now use the `pdftotext` program to pull text from a range of PDF pages, one block of text per page\n\n**Unclear.** It is not clear whether reading a PDF uses this yet, or whether `pdftotext` has to be installed for it to work.\n\n**What**\n\nClaude Code can now use `pdftotext`, a separate program that reads the text out of PDF files. It asks for a range of pages, keeps the page layout, and splits the result into one block of text per page. It gives up after 10 seconds, and it also gives up when the number of text blocks does not match the number of pages.\n\n**Why**\n\nReading a PDF may now give Claude the text of each page as well.\n\n- Area: PDF Reading\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}