pdf-read-file-fallback
Extract text from PDFs using pdftotext when read_file returns binary data
- License 许可
- MIT
- 所属仓库
- HKUDS/AgentPilot
- 最近更新
- 2026-11-12
- Stars
- ★ 8.0k
- Forks
- 944
01 前言 Front Matter
- name
- pdf-read-file-fallback
- description
- Extract text from PDFs using pdftotext when read_file returns binary data
02 资源文件 1
- 其他.skill_id36 B
03 SKILL.md 正文
PDF Text Extraction Fallback
When to Use
Use this pattern when read_file with filetype="pdf" returns binary image data instead of extractable text content. This commonly occurs with PDFs that contain scanned images or complex formatting.
Steps
1. Attempt Primary Extraction
First, try using read_file:
result = read_file(file_path="document.pdf", filetype="pdf")
Important: Use filetype (not file_type) - incorrect parameter naming will cause execution failures.
2. Detect Binary/Image Data
Check if the result contains unusable content:
# Indicators of binary/image data:
# - Contains null bytes: '\x00'
# - Very short or empty
# - Contains image markers (PNG/JPEG headers)
# - Unreadable character sequences
if not result or len(result) < 50 or '\x00' in str(result):
# Proceed to fallback
3. Use pdftotext via run_shell
Extract text using the pdftotext command-line tool:
shell_result = run_shell(command="pdftotext -layout document.pdf -")
text_content = shell_result.stdout
The - flag outputs to stdout for easy capture. The -layout flag preserves original formatting.
4. Handle pdftotext Unavailable
If pdftotext is not installed, try Python-based extraction:
result = execute_code_sandbox(code="""
import pdfplumber
text = ''
with pdfplumber.open('document.pdf') as pdf:
for page in pdf.pages:
extracted = page.extract_text()
if extracted:
text += extracted + '\\n'
print(text)
""")
Complete Example
file_path = "report.pdf"
# Primary attempt
result = read_file(file_path=file_path, filetype="pdf")
# Validate and fallback if needed
if not result or len(str(result)) < 100 or '\x00' in str(result):
# Fallback to pdftotext
shell_result = run_shell(command=f"pdftotext -layout {file_path} -")
text_content = shell_result.stdout
# If pdftotext fails, try Python extraction
if not text_content or len(text_content) < 50:
code_result = execute_code_sandbox(code=f"""
import pdfplumber
text = ''
with pdfplumber.open('{file_path}') as pdf:
for page in pdf.pages:
extracted = page.extract_text()
if extracted:
text += extracted + '\\n'
print(text)
""")
text_content = code_result
Notes
pdftotextis part of thepoppler-utilspackage on most Linux systems- For scanned/image-only PDFs, consider OCR tools (tesseract) instead
- Always validate parameter names against tool documentation (
filetypevsfile_type)
04 同仓库更多 Skills
agentpilot
Set up AgentPilot and use its single entry to prepare missing inputs and run configured RSI experiments. Use when the user requests AgentPilot installation or work with AgentPilot.
remember
Review auto-memory entries and propose promotions to OPENSPACE.md, OPENSPACE.local.md, or retained auto-memory topics; detect duplicates, stale facts, conflicts, and ambiguous entries before making changes.
skill-discovery
Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.
delegate-task
Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library. Skills auto-improve through use, reducing token consumption over time. A cloud community lets agents share and collectively evolve reusable skills.
write-special-chars-ts-check
Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, plus a reliable TypeScript type-checking step that filters output to only the newly-written files to avoid being misled by pre-existing errors.
write-special-chars-readback
Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, with mandatory post-write verification via read_file and cleanup of /tmp helper scripts.