stvlynn/dingtalk-wukong-skills/pdf

用户需求 → 判断任务类型 → 选择工具 → 执行操作 → 验证输出
User request → Task type classification → Tool selection → Execute → Validate

# Best practice for table extraction
import pdfplumber
import pandas as pd
all_tables = []
with pdfplumber.open("document.pdf") as pdf:
    for page in pdf.pages:
        tables = page.extract_tables()
        for table in tables:
            if table:  # Check not empty
                df = pd.DataFrame(table[1:], columns=table[0])  # First row as header
                all_tables.append(df)
# Combine and clean
combined = pd.concat(all_tables, ignore_index=True)
combined.to_excel("output.xlsx", index=False)

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

import pdfplumber
import pandas as pd
all_tables = []
with pdfplumber.open("document.pdf") as pdf:
    for page in pdf.pages:
        tables = page.extract_tables()
        for table in tables:
            if table:
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)
combined = pd.concat(all_tables, ignore_index=True)
combined.to_excel("extracted_tables.xlsx", index=False)

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)

from pypdf import PdfReader, PdfWriter
reader = PdfReader("large_document.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)

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter
c.drawString(100, height - 100, "Hello World!")
c.save()

from pypdf import PdfReader
reader = PdfReader("document.pdf")
meta = reader.metadata
print(f"Title: {meta.title}")
print(f"Author: {meta.author}")
print(f"Pages: {len(reader.pages)}")

pip install -r requirements.txt
# Includes: pypdf, pdfplumber, reportlab, pandas, openpyxl

import pdfplumber
import pandas as pd
import glob
all_data = []
for pdf_file in glob.glob("invoices/*.pdf"):
    with pdfplumber.open(pdf_file) as pdf:
        for page in pdf.pages:
            tables = page.extract_tables()
            for table in tables:
                if table:
                    df = pd.DataFrame(table[1:], columns=table[0])
                    df['source_file'] = pdf_file
                    all_data.append(df)
combined = pd.concat(all_data, ignore_index=True)
combined.to_excel("all_invoices.xlsx", index=False)

from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Table, TableStyle, Paragraph
from reportlab.lib.styles import getSampleStyleSheet
doc = SimpleDocTemplate("report.pdf", pagesize=letter)
styles = getSampleStyleSheet()
story = []
# Title
story.append(Paragraph("Sales Report", styles['Title']))
# Table
data = [
    ['Product', 'Q1', 'Q2', 'Q3', 'Q4'],
    ['Product A', '1000', '1200', '1100', '1300'],
    ['Product B', '800', '900', '950', '1000']
]
t = Table(data)
t.setStyle(TableStyle([
    ('BACKGROUND', (0, 0), (-1, 0), 'grey'),
    ('TEXTCOLOR', (0, 0), (-1, 0), 'white'),
    ('ALIGN', (0, 0), (-1, -1), 'CENTER'),
    ('GRID', (0, 0), (-1, -1), 1, 'black')
]))
story.append(t)
doc.build(story)