PDF Processing with Python

import pdfplumber

with pdfplumber.open("in.pdf") as pdf:
    for i, page in enumerate(pdf.pages, 1):
        print(f"--- page {i} ---")
        print(page.extract_text() or "")  # layout-aware text
        for t in page.extract_tables():  # list of tables; each is list[row]
            for row in t:
                print(row)

import pdfplumber
from openpyxl import Workbook

workbook = Workbook()
workbook.remove(workbook.active)
table_number = 0
with pdfplumber.open("in.pdf") as pdf:
    for page_number, page in enumerate(pdf.pages, 1):
        for table in page.extract_tables():
            if not table:
                continue
            table_number += 1
            sheet = workbook.create_sheet(f"p{page_number}_table{table_number}"[:31])
            for row in table:
                sheet.append([cell or "" for cell in row])
if table_number:
    workbook.save("tables.xlsx")

ts = {
    "vertical_strategy": "lines",
    "horizontal_strategy": "lines",
    "snap_tolerance": 3,
    "intersection_tolerance": 15,
}
page.extract_tables(ts)

from pypdf import PdfReader, PdfWriter

# Merge
w = PdfWriter()
for f in ["a.pdf", "b.pdf"]:
    for p in PdfReader(f).pages:
        w.add_page(p)
w.write("merged.pdf")

# Split: one file per page
r = PdfReader("in.pdf")
for i, p in enumerate(r.pages, 1):
    w = PdfWriter()
    w.add_page(p)
    w.write(f"page_{i}.pdf")

# Rotate page 0 by 90 degrees clockwise
r = PdfReader("in.pdf")
w = PdfWriter()
r.pages[0].rotate(90)
w.add_page(r.pages[0])
w.write("rotated.pdf")

from pypdf import PdfReader, PdfWriter

wm = PdfReader("stamp.pdf").pages[0]
r = PdfReader("in.pdf")
w = PdfWriter()
for p in r.pages:
    p.merge_page(wm)
    w.add_page(p)
w.write("stamped.pdf")

from reportlab.lib.pagesizes import letter
from reportlab.lib.styles import getSampleStyleSheet
from reportlab.lib import colors
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Table, TableStyle

styles = getSampleStyleSheet()
story = [
    Paragraph("Report Title", styles["Title"]),
    Spacer(1, 12),
    Paragraph("Body text. " * 20, styles["Normal"]),
]
data = [["Product", "Q1", "Q2"], ["Widgets", "120", "135"]]
tbl = Table(data)
tbl.setStyle(
    TableStyle(
        [
            ("BACKGROUND", (0, 0), (-1, 0), colors.grey),
            ("TEXTCOLOR", (0, 0), (-1, 0), colors.whitesmoke),
            ("GRID", (0, 0), (-1, -1), 0.5, colors.black),
        ]
    )
)
story += [Spacer(1, 12), tbl]
SimpleDocTemplate("out.pdf", pagesize=letter).build(story)

import os
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont


def register_cjk_font(name="CJK"):
    # TrueType ONLY — reportlab cannot embed CFF/OpenType outlines, so a .otf
    # like Noto Sans CJK fails with "postscript outlines are not supported".
    for path in [
        "/usr/share/fonts/truetype/wqy/wqy-zenhei.ttc",  # Linux sandbox (fonts-wqy-zenhei)
        "/usr/share/fonts/truetype/wqy/wqy-microhei.ttc",
        "/System/Library/Fonts/STHeiti Light.ttc",  # macOS
        "/System/Library/Fonts/Hiragino Sans GB.ttc",
        "/System/Library/Fonts/Supplemental/Songti.ttc",
        "/System/Library/Fonts/Supplemental/Arial Unicode.ttf",
        "C:/Windows/Fonts/msyh.ttc",  # Windows
    ]:
        if os.path.exists(path):
            try:
                pdfmetrics.registerFont(TTFont(name, path, subfontIndex=0))
                return name
            except Exception:
                continue
    raise RuntimeError("No CJK-capable TrueType font found — do not emit tofu; say so.")


font = register_cjk_font()
styles = getSampleStyleSheet()
for s in styles.byName.values():  # make the CJK font the default everywhere
    s.fontName = font
# Tables don't read the stylesheet — set the font in the TableStyle too:
#   ("FONTNAME", (0, 0), (-1, -1), font)
# Canvas: c.setFont(font, size) before every drawString.