使用 Python 中的 PDFMiner 从 PDF 中提取文本

pip install pdfminer.six

python -m venv venv
source venv/bin/activate  # 在 Windows 上：venv\Scripts\activate
pip install pdfminer.six

pdf2txt.py --version

from pdfminer.high_level import extract_text

# 从 PDF 中提取所有文本
text = extract_text('document.pdf')
print(text)

from pdfminer.high_level import extract_text

# 从页面 2-5 提取文本（0 索引）
text = extract_text('document.pdf', page_numbers=[1, 2, 3, 4])
print(text)

from pdfminer.high_level import extract_pages
from pdfminer.layout import LTTextContainer

for page_layout in extract_pages('document.pdf'):
    for element in page_layout:
        if isinstance(element, LTTextContainer):
            print(element.get_text())

from pdfminer.high_level import extract_text
from pdfminer.layout import LAParams

# 创建自定义 LAParams
laparams = LAParams(
    line_overlap=0.5,      # 文本行的最小重叠
    char_margin=2.0,       # 字符边距
    line_margin=0.5,       # 行边距
    word_margin=0.1,       # 单词间距
    boxes_flow=0.5,        # 文本框流阈值
    detect_vertical=True,  # 检测垂直文本
    all_texts=False        # 仅提取文本框中的文本
)

text = extract_text('document.pdf', laparams=laparams)

from pdfminer.high_level import extract_pages
from pdfminer.layout import LTTextBox, LTTextLine, LTChar

for page_layout in extract_pages('document.pdf'):
    for element in page_layout:
        if isinstance(element, LTTextBox):
            # 获取边界框坐标
            x0, y0, x1, y1 = element.bbox
            print(f"文本位于 ({x0}, {y0})：{element.get_text()}")
            
            # 遍历行
            for text_line in element:
                if isinstance(text_line, LTTextLine):
                    # 获取字符级别的细节
                    for char in text_line:
                        if isinstance(char, LTChar):
                            print(f"字符：{char.get_text()}, "
                                  f"字体：{char.fontname}, "
                                  f"大小：{char.height}")

from pdfminer.high_level import extract_text

# 从受密码保护的 PDF 提取
text = extract_text('encrypted.pdf', password='your_password')

from pdfminer.high_level import extract_text
from pdfminer.layout import LAParams

# 优化多栏布局
laparams = LAParams(
    detect_vertical=False,
    line_margin=0.3,
    word_margin=0.1,
    boxes_flow=0.3  # 更低值有助于更好地检测列
)

text = extract_text('multi_column.pdf', laparams=laparams)

from pdfminer.high_level import extract_text

# 使用 Unicode 支持提取文本
text = extract_text('multilingual.pdf', codec='utf-8')

# 以 UTF-8 编码保存到文件
with open('output.txt', 'w', encoding='utf-8') as f:
    f.write(text)

from pdfminer.high_level import extract_text
from pdfminer.high_level import extract_pages
from pdfminer.layout import LTFigure, LTImage

def is_scanned_pdf(pdf_path):
    """检查 PDF 是否为扫描（主要是图像）"""
    text_count = 0
    image_count = 0
    
    for page_layout in extract_pages(pdf_path):
        for element in page_layout:
            if isinstance(element, (LTFigure, LTImage)):
                image_count += 1
            elif hasattr(element, 'get_text'):
                if element.get_text().strip():
                    text_count += 1
    
    # 如果主要是图像且文本很少，可能是扫描的
    return image_count > text_count * 2

if is_scanned_pdf('document.pdf'):
    print("此 PDF 看起来是扫描的 - 使用 OCR")
else:
    text = extract_text('document.pdf')
    print(text)

# 提取文本到标准输出
pdf2txt.py document.pdf

# 保存到文件
pdf2txt.py -o output.txt document.pdf

# 提取特定页面
pdf2txt.py -p 1,2,3 document.pdf

# 以 HTML 格式提取
pdf2txt.py -t html -o output.html document.pdf

# 自定义布局参数
pdf2txt.py -L 0.3 -W 0.1 document.pdf

# 提取详细布局（XML）
pdf2txt.py -t xml -o layout.xml document.pdf

# 设置加密 PDF 的密码
pdf2txt.py -P mypassword encrypted.pdf

from pdfminer.high_level import extract_pages
from pdfminer.layout import LAParams

# 仅处理所需页面
def extract_page_range(pdf_path, start_page, end_page):
    text_content = []
    for i, page_layout in enumerate(extract_pages(pdf_path)):
        if i < start_page:
            continue
        if i >= end_page:
            break
        text_content.append(page_layout)
    return text_content

# 禁用布局分析以提高速度
from pdfminer.high_level import extract_text
text = extract_text('large.pdf', laparams=None)  # 快得多

from multiprocessing import Pool
from pdfminer.high_level import extract_text
import os

def process_pdf(pdf_path):
    """处理单个 PDF 文件"""
    try:
        text = extract_text(pdf_path)
        output_path = pdf_path.replace('.pdf', '.txt')
        with open(output_path, 'w', encoding='utf-8') as f:
            f.write(text)
        return f"已处理: {pdf_path}"
    except Exception as e:
        return f"处理 {pdf_path} 时出错: {str(e)}"

# 并行处理 PDF
def batch_process_pdfs(pdf_directory, num_workers=4):
    pdf_files = [os.path.join(pdf_directory, f) 
                 for f in os.listdir(pdf_directory) 
                 if f.endswith('.pdf')]
    
    with Pool(num_workers) as pool:
        results = pool.map(process_pdf, pdf_files)
    
    for result in results:
        print(result)

# 使用方法
batch_process_pdfs('/path/to/pdfs', num_workers=4)

from pdfminer.layout import LAParams
laparams = LAParams(boxes_flow=0.3)  # 尝试不同值
text = extract_text('document.pdf', laparams=laparams)

laparams = LAParams(word_margin=0.2)  # 从默认值 0.1 增加
text = extract_text('document.pdf', laparams=laparams)

text = extract_text('document.pdf', codec='utf-8')

def extract_text_chunked(pdf_path, chunk_size=10):
    """分块提取文本以减少内存使用"""
    all_text = []
    page_count = 0
    
    for page_layout in extract_pages(pdf_path):
        page_text = []
        for element in page_layout:
            if hasattr(element, 'get_text'):
                page_text.append(element.get_text())
        
        all_text.append(''.join(page_text))
        page_count += 1
        
        # 分块处理
        if page_count % chunk_size == 0:
            yield ''.join(all_text)
            all_text = []
    
    # 输出剩余文本
    if all_text:
        yield ''.join(all_text)

from pdfminer.high_level import extract_pages, extract_text
from pdfminer.layout import LTTextBox, LTChar
from collections import Counter
import re

def analyze_pdf(pdf_path):
    """提取文本并提供文档分析"""
    
    # 提取全文
    full_text = extract_text(pdf_path)
    
    # 统计信息
    stats = {
        'total_chars': len(full_text),
        'total_words': len(full_text.split()),
        'total_lines': full_text.count('\n'),
        'fonts': Counter(),
        'font_sizes': Counter(),
        'pages': 0
    }
    
    # 详细分析
    for page_layout in extract_pages(pdf_path):
        stats['pages'] += 1
        
        for element in page_layout:
            if isinstance(element, LTTextBox):
                for line in element:
                    for char in line:
                        if isinstance(char, LTChar):
                            stats['fonts'][char.fontname] += 1
                            stats['font_sizes'][round(char.height, 1)] += 1
    
    return {
        'text': full_text,
        'stats': stats,
        'most_common_font': stats['fonts'].most_common(1)[0] if stats['fonts'] else None,
        'most_common_size': stats['font_sizes'].most_common(1)[0] if stats['font_sizes'] else None
    }

# 使用方法
result = analyze_pdf('document.pdf')
print(f"页数: {result['stats']['pages']}")
print(f"单词数: {result['stats']['total_words']}")
print(f"主要字体: {result['most_common_font']}")
print(f"主要字号: {result['most_common_size']}")