pip install pdfplumber

import pdfplumber

with pdfplumber.open("example.pdf") as pdf:
    first_page = pdf.pages[0]
    print(first_page.extract_text())

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

with pdfplumber.open("formatted.pdf") as pdf:
    page = pdf.pages[0]
    words = page.extract_words()
    for word in words:
        print(f"文本: {word['text']}, 位置: {word['x0'], word['top']}, 字體: {word['fontname']}")

with pdfplumber.open("document.pdf") as pdf:
    page = pdf.pages[0]
    # 定義區(qū)域(x0, top, x1, bottom)
    area = (50, 100, 400, 300)  
    cropped = page.crop(area)
    print(cropped.extract_text())

with pdfplumber.open("data.pdf") as pdf:
    page = pdf.pages[0]
    table = page.extract_table()
    for row in table:
        print(row)

with pdfplumber.open("complex_table.pdf") as pdf:
    page = pdf.pages[0]
    # 自定義表格設(shè)置
    table_settings = {
        "vertical_strategy": "text", 
        "horizontal_strategy": "text",
        "intersection_y_tolerance": 10
    }
    table = page.extract_table(table_settings)

with pdfplumber.open("multi_page_table.pdf") as pdf:
    full_table = []
    for page in pdf.pages:
        table = page.extract_table()
        if table:
            # 跳過(guò)表頭（假設(shè)第一頁(yè)已經(jīng)有表頭）
            if page.page_number > 1:
                table = table[1:]
            full_table.extend(table)
    
    for row in full_table:
        print(row)

with pdfplumber.open("debug.pdf") as pdf:
    page = pdf.pages[0]
    im = page.to_image()
    im.debug_tablefinder().show()

with pdfplumber.open("drawing.pdf") as pdf:
    page = pdf.pages[0]
    lines = page.lines
    curves = page.curves
    rects = page.rects
    
    print(f"找到 {len(lines)} 條直線")
    print(f"找到 {len(curves)} 條曲線")
    print(f"找到 {len(rects)} 個(gè)矩形")

def custom_extract_method(page):
    # 獲取所有字符對(duì)象
    chars = page.chars
    # 按y坐標(biāo)分組（行）
    lines = {}
    for char in chars:
        line_key = round(char["top"])
        if line_key not in lines:
            lines[line_key] = []
        lines[line_key].append(char)
    
    # 按x坐標(biāo)排序并拼接文本
    result = []
    for y in sorted(lines.keys()):
        line_chars = sorted(lines[y], key=lambda c: c["x0"])
        line_text = "".join([c["text"] for c in line_chars])
        result.append(line_text)
    
    return "\n".join(result)

???????with pdfplumber.open("custom.pdf") as pdf:
    page = pdf.pages[0]
    print(custom_extract_method(page))

with pdfplumber.open("large.pdf") as pdf:
    # 只處理前5頁(yè)
    for page in pdf.pages[:5]:
        process(page.extract_text())

from concurrent.futures import ThreadPoolExecutor

def process_page(page):
    return page.extract_text()

with pdfplumber.open("big_file.pdf") as pdf:
    with ThreadPoolExecutor(max_workers=4) as executor:
        results = list(executor.map(process_page, pdf.pages))

import pickle

def extract_and_cache(pdf_path, cache_path):
    try:
        with open(cache_path, "rb") as f:
            return pickle.load(f)
    except FileNotFoundError:
        with pdfplumber.open(pdf_path) as pdf:
            data = [page.extract_text() for page in pdf.pages]
            with open(cache_path, "wb") as f:
                pickle.dump(data, f)
            return data

text_data = extract_and_cache("report.pdf", "report_cache.pkl")

def extract_invoice_info(pdf_path):
    invoice_data = {
        "invoice_no": None,
        "date": None,
        "total": None
    }
    
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            text = page.extract_text()
            lines = text.split("\n")
            
            for line in lines:
                if "發(fā)票號(hào)碼" in line:
                    invoice_data["invoice_no"] = line.split(":")[1].strip()
                elif "日期" in line:
                    invoice_data["date"] = line.split(":")[1].strip()
                elif "合計(jì)" in line:
                    invoice_data["total"] = line.split()[-1]
    
    return invoice_data

def analyze_paper(pdf_path):
    sections = {
        "abstract": "",
        "introduction": "",
        "conclusion": ""
    }
    
    with pdfplumber.open(pdf_path) as pdf:
        current_section = None
        for page in pdf.pages:
            text = page.extract_text()
            for line in text.split("\n"):
                line = line.strip()
                if line.lower() == "abstract":
                    current_section = "abstract"
                elif line.lower().startswith("1. introduction"):
                    current_section = "introduction"
                elif line.lower().startswith("conclusion"):
                    current_section = "conclusion"
                elif current_section:
                    sections[current_section] += line + "\n"
    
    return sections

import csv

def convert_pdf_to_csv(pdf_path, csv_path):
    with pdfplumber.open(pdf_path) as pdf:
        with open(csv_path, "w", newline="") as f:
            writer = csv.writer(f)
            for page in pdf.pages:
                table = page.extract_table()
                if table:
                    writer.writerows(table)

with pdfplumber.open("chinese.pdf") as pdf:
    page = pdf.pages[0]
    # 確保系統(tǒng)安裝了中文字體
    text = page.extract_text()
    print(text.encode("utf-8").decode("utf-8"))

table_settings = {
    "vertical_strategy": "lines",
    "horizontal_strategy": "lines",
    "explicit_vertical_lines": page.lines,
    "explicit_horizontal_lines": page.lines,
    "intersection_x_tolerance": 15,
    "intersection_y_tolerance": 15
}
table = page.extract_table(table_settings)

# 逐頁(yè)處理并立即釋放內(nèi)存
with pdfplumber.open("huge.pdf") as pdf:
    for i, page in enumerate(pdf.pages):
        process(page.extract_text())
        # 手動(dòng)釋放頁(yè)面資源
        pdf.release_resources()
        if i % 10 == 0:
            print(f"已處理 {i+1} 頁(yè)")

# 使用Ghostscript優(yōu)化PDF
import subprocess
subprocess.run(["gs", "-sDEVICE=pdfwrite", "-dNOPAUSE", "-dBATCH", 
               "-dSAFER", "-sOutputFile=optimized.pdf", "original.pdf"])

# 結(jié)合PyMuPDF獲取更精確的文本位置
import fitz
doc = fitz.open("combined.pdf")

def safe_extract(pdf_path):
    try:
        with pdfplumber.open(pdf_path) as pdf:
            return pdf.pages[0].extract_text()
    except Exception as e:
        print(f"處理{pdf_path}時(shí)出錯(cuò): {str(e)}")
        return None

import time
start = time.time()
# pdf處理操作
print(f"處理耗時(shí): {time.time()-start:.2f}秒")