Communitygithub.com

pdf

Utilisez cette compétence dès que l'utilisateur souhaite effectuer une opération sur des fichiers PDF : lecture, extraction de texte/tableaux, fusion, division, rotation, ajout de filigrane, création, remplissage de formulaires, chiffrement/déchiffrement, extraction d'images ou OCR.

Qu'est-ce que pdf ?

Cette compétence fournit un guide complet pour le traitement de fichiers PDF en Python et en ligne de commande. Elle couvre les bibliothèques Python essentielles telles que `pypdf` pour les opérations de base (fusion, division, rotation, métadonnées), `pdfplumber` pour l'extraction avancée de texte et de tableaux, et `reportlab` pour la création de nouveaux PDF. Elle inclut également des outils en ligne de commande comme `qpdf`, `pdftotext` et `pdftk` pour des tâches rapides. Les cas d'usage spécifiques — extraction de texte de PDF scannés via OCR (Tesseract), ajout de filigrane, extraction d'images, protection par mot de passe — sont détaillés avec des exemples concrets. La compétence est conçue pour les développeurs et les utilisateurs d'agents IA sur les plateformes Claude Code, Cursor et Codex, et renvoie vers des fichiers `forms.md` et `reference.md` pour les formulaires et fonctionnalités avancées.

Compatible avec✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/pdf

Demander à votre IA préférée

Ouvre une nouvelle conversation avec cette compétence d'agent déjà préchargée.

Documentation

Guide de traitement PDF

Présentation

Ce guide couvre les opérations essentielles de traitement PDF à l'aide de bibliothèques Python et d'outils en ligne de commande. Pour les fonctionnalités avancées, les bibliothèques JavaScript et des exemples détaillés, consultez le fichier reference.md. Si vous devez remplir un formulaire PDF, lisez le fichier forms.md et suivez ses instructions.

Démarrage rapide

from pypdf import PdfReader, PdfWriter

# Lire un PDF
reader = PdfReader("document.pdf")
print(f"Pages : {len(reader.pages)}")

# Extraire le texte
text = ""
for page in reader.pages:
    text += page.extract_text()

Bibliothèques Python

pypdf - Opérations de base

Fusionner des PDF

from pypdf import PdfWriter, PdfReader

writer = PdfWriter()
for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
    reader = PdfReader(pdf_file)
    for page in reader.pages:
        writer.add_page(page)

with open("merged.pdf", "wb") as output:
    writer.write(output)

Diviser un PDF

reader = PdfReader("input.pdf")
for i, page in enumerate(reader.pages):
    writer = PdfWriter()
    writer.add_page(page)
    with open(f"page_{i+1}.pdf", "wb") as output:
        writer.write(output)

Extraire les métadonnées

reader = PdfReader("document.pdf")
meta = reader.metadata
print(f"Titre : {meta.title}")
print(f"Auteur : {meta.author}")
print(f"Sujet : {meta.subject}")
print(f"Créateur : {meta.creator}")

Rotation des pages

reader = PdfReader("input.pdf")
writer = PdfWriter()

page = reader.pages[0]
page.rotate(90)  # Rotation de 90 degrés dans le sens horaire
writer.add_page(page)

with open("rotated.pdf", "wb") as output:
    writer.write(output)

pdfplumber - Extraction de texte et de tableaux

Extraire le texte avec la mise en page

import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        print(text)

Extraire les tableaux

with pdfplumber.open("document.pdf") as pdf:
    for i, page in enumerate(pdf.pages):
        tables = page.extract_tables()
        for j, table in enumerate(tables):
            print(f"Tableau {j+1} à la page {i+1} :")
            for row in table:
                print(row)

Extraction avancée de tableaux

import pandas as pd

with pdfplumber.open("document.pdf") as pdf:
    all_tables = []
    for page in pdf.pages:
        tables = page.extract_tables()
        for table in tables:
            if table:  # Vérifier que le tableau n'est pas vide
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)

# Combiner tous les tableaux
if all_tables:
    combined_df = pd.concat(all_tables, ignore_index=True)
    combined_df.to_excel("extracted_tables.xlsx", index=False)

reportlab - Créer des PDF

Création basique d'un PDF

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter

# Ajouter du texte
c.drawString(100, height - 100, "Bonjour le monde !")
c.drawString(100, height - 120, "Ceci est un PDF créé avec reportlab")

# Ajouter une ligne
c.line(100, height - 140, 400, height - 140)

# Enregistrer
c.save()

Créer un PDF avec plusieurs pages

from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
from reportlab.lib.styles import getSampleStyleSheet

doc = SimpleDocTemplate("report.pdf", pagesize=letter)
styles = getSampleStyleSheet()
story = []

# Ajouter du contenu
title = Paragraph("Titre du rapport", styles['Title'])
story.append(title)
story.append(Spacer(1, 12))

body = Paragraph("Ceci est le corps du rapport. " * 20, styles['Normal'])
story.append(body)
story.append(PageBreak())

# Page 2
story.append(Paragraph("Page 2", styles['Heading1']))
story.append(Paragraph("Contenu de la page 2", styles['Normal']))

# Construire le PDF
doc.build(story)

Indices et exposants

IMPORTANT : N'utilisez jamais les caractères Unicode d'indice/exposant (₀₁₂₃₄₅₆₇₈₉, ⁰¹²³⁴⁵⁶⁷⁸⁹) dans les PDF reportlab. Les polices intégrées ne contiennent pas ces glyphes, ce qui les rendrait comme des cases noires pleines.

Utilisez plutôt les balises XML de reportlab dans les objets Paragraph :

from reportlab.platypus import Paragraph
from reportlab.lib.styles import getSampleStyleSheet

styles = getSampleStyleSheet()

# Indices : utilisez la balise <sub>
chemical = Paragraph("H<sub>2</sub>O", styles['Normal'])

# Exposants : utilisez la balise <super>
squared = Paragraph("x<super>2</super> + y<super>2</super>", styles['Normal'])

Pour le texte dessiné par canvas (pas les objets Paragraph), ajustez manuellement la taille et la position de la police au lieu d'utiliser les indices/exposants Unicode.

Outils en ligne de commande

pdftotext (poppler-utils)

# Extraire le texte
pdftotext input.pdf output.txt

# Extraire le texte en conservant la mise en page
pdftotext -layout input.pdf output.txt

# Extraire des pages spécifiques
pdftotext -f 1 -l 5 input.pdf output.txt  # Pages 1 à 5

qpdf

# Fusionner des PDF
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf

# Diviser des pages
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf
qpdf input.pdf --pages . 6-10 -- pages6-10.pdf

# Rotation des pages
qpdf input.pdf output.pdf --rotate=+90:1  # Rotation de 90 degrés page 1

# Supprimer le mot de passe
qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf

pdftk (si disponible)

# Fusionner
pdftk file1.pdf file2.pdf cat output merged.pdf

# Diviser
pdftk input.pdf burst

# Rotation
pdftk input.pdf rotate 1east output rotated.pdf

Tâches courantes

Extraire le texte de PDF scannés

# Nécessite : uv pip install pytesseract pdf2image
import pytesseract
from pdf2image import convert_from_path

# Convertir le PDF en images
images = convert_from_path('scanned.pdf')

# OCR de chaque page
text = ""
for i, image in enumerate(images):
    text += f"Page {i+1} :\n"
    text += pytesseract.image_to_string(image)
    text += "\n\n"

print(text)

Ajouter un filigrane

from pypdf import PdfReader, PdfWriter

# Créer un filigrane (ou charger un existant)
watermark = PdfReader("watermark.pdf").pages[0]

# Appliquer à toutes les pages
reader = PdfReader("document.pdf")
writer = PdfWriter()

for page in reader.pages:
    page.merge_page(watermark)
    writer.add_page(page)

with open("watermarked.pdf", "wb") as output:
    writer.write(output)

Extraire des images

# Avec pdfimages (poppler-utils)
pdfimages -j input.pdf output_prefix

# Cela extrait toutes les images sous output_prefix-000.jpg, output_prefix-001.jpg, etc.

Protection par mot de passe

from pypdf import PdfReader, PdfWriter

reader = PdfReader("input.pdf")
writer = PdfWriter()

for page in reader.pages:
    writer.add_page(page)

# Ajouter un mot de passe
writer.encrypt("userpassword", "ownerpassword")

with open("encrypted.pdf", "wb") as output:
    writer.write(output)

Référence rapide

TâcheMeilleur outilCommande/Code
Fusionner des PDFpypdfwriter.add_page(page)
Diviser des PDFpypdfUn fichier par page
Extraire le textepdfplumberpage.extract_text()
Extraire les tableauxpdfplumberpage.extract_tables()
Créer des PDFreportlabCanvas ou Platypus
Fusion en ligne de commandeqpdfqpdf --empty --pages ...
OCR de PDF scannéspytesseractConvertir d'abord en image
Remplir des formulaires PDFpdf-lib ou pypdf (voir forms.md)Voir forms.md

Prochaines étapes

  • Pour une utilisation avancée de pypdfium2, consultez reference.md
  • Pour les bibliothèques JavaScript (pdf-lib), consultez reference.md
  • Si vous devez remplir un formulaire PDF, suivez les instructions dans forms.md
  • Pour les guides de dépannage, consultez reference.md

Cette compétence est créée et maintenue par Anthropic. Vendue ici sans modification, hormis les métadonnées de préambule et la casse des liens reference.md/forms.md, qui sont en majuscules en amont ; voir LICENSE.txt pour les conditions.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

adaptyv

How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.

aeon

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

alphagenome

Look up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq, DNase, ATAC, ChIP-TF, ChIP-histone, CAGE, PRO-cap, splicing, polyadenylation and contact-map tracks), score variants or scan windows on demand with the AlphaGenome model for human and mouse (variant scoring, in silico mutagenesis, REF-versus-ALT track prediction), and build Atlas website deep links. Use when the user mentions AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind variant effect prediction, or wants to prioritise or mechanistically interpret non-coding, regulatory, splicing, enhancer, promoter, or chromatin-accessibility effects of SNVs from a VCF, credible set, or region. Research use only; not a clinical tool.

analytical-method-validation

Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP <1220>/<1225>/<1226>, ICH M10 bioanalytical, CLSI EP, or ISO/IEC 17025. Use for HPLC, LC-MS/MS, GC, CE, ICP-MS, dissolution, qNMR, qPCR, NIR, and ligand binding or cell-based assays whenever the question is whether a procedure is fit for its intended purpose. Triggers include

anndata

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

arbor

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g.

arboreto

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

astropy

Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing or debugging astronomical data analysis code with Astropy.

autoskill

Observe the user

benchling-integration

Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. Use when automating lab data with benchling-sdk or the v2 API.

bgpt-paper-search

Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.

bids

>

biopython

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

bioservices

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.

bulk-rnaseq

End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and publication figures (scientific-visualization). Use whenever the user has bulk RNA-seq reads or quant output and wants a complete, reproducible differential-expression workflow — e.g.

cellxgene-census

Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.

cirq

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.

citation-management

Comprehensive citation management for academic research. Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

clinical-decision-support

Prepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts. Use for aggregate or synthetic research documentation and traceability—not patient care or live clinical operation.

clinical-reports

Create safety-bounded draft structures and run local deterministic checks for clinical case, diagnostic, trial, safety, and aggregate research reports. Use only with synthetic, de-identified, or aggregate inputs and verified source-fact manifests; every output requires qualified review.

Skills associés