Python提取Word文档中各种数据的详细方法(基于python-docx库)

pip install python-docx

from docx import Document
# 加载Word文档，假设文件名为"example.docx"
doc = Document("example.docx")

# 遍历所有段落，提取文本
all_text = []
for paragraph in doc.paragraphs:
    all_text.append(paragraph.text)
# 打印提取结果
print("文档全文：")
for text in all_text:
    print(text)

headings = []
for paragraph in doc.paragraphs:
    if paragraph.style.name.startswith('Heading'):  # 检查样式名以"Heading"开头
        headings.append(paragraph.text)
print("文档标题：")
for heading in headings:
    print(heading)

# 假设文档中有至少一个表格
table = doc.tables[0]  # 获取第一个表格
table_data = []
for row in table.rows:
    row_data = []
    for cell in row.cells:
        row_data.append(cell.text)  # 提取单元格文本
    table_data.append(row_data)
print("表格数据：")
for row in table_data:
    print(row)

import csv
for i, table in enumerate(doc.tables):
    table_data = []
    for row in table.rows:
        row_data = [cell.text for cell in row.cells]
        table_data.append(row_data)
    # 保存到CSV文件
    with open(f"table_{i}.csv", "w", newline="", encoding="utf-8") as f:
        writer = csv.writer(f)
        writer.writerows(table_data)
print(f"已提取并保存{len(doc.tables)}个表格到CSV文件。")

from docx.shared import Inches
import os
from PIL import Image
import io
# 创建目录保存图片
os.makedirs("extracted_images", exist_ok=True)
for rel in doc.part.rels.values():
    if "image" in rel.reltype:  # 检查关系类型是否为图片
        image_data = rel.target_part.blob  # 获取图片二进制数据
        img = Image.open(io.BytesIO(image_data))
        img.save(f"extracted_images/image_{rel.rId}.png")  # 保存为PNG
print(f"已提取并保存{len([rel for rel in doc.part.rels.values() if 'image' in rel.reltype])}张图片。")

lists = []
for paragraph in doc.paragraphs:
    if paragraph.style.name == "List Paragraph":  # 检查列表样式
        lists.append(paragraph.text)
print("列表内容：")
for item in lists:
    print(f"- {item}")

hyperlinks = []
for paragraph in doc.paragraphs:
    for run in paragraph.runs:  # 遍历段落中的文本块
        if run.hyperlink:
            hyperlinks.append((run.text, run.hyperlink.target))  # 保存链接文本和目标URL
print("超链接：")
for text, url in hyperlinks:
    print(f"文本: '{text}', URL: {url}")

header_text = []
footer_text = []
for section in doc.sections:
    header = section.header
    for paragraph in header.paragraphs:
        header_text.append(paragraph.text)
    footer = section.footer
    for paragraph in footer.paragraphs:
        footer_text.append(paragraph.text)
print("页眉内容:", header_text)
print("页脚内容:", footer_text)

import sqlite3
conn = sqlite3.connect("data.db")
cursor = conn.cursor()
cursor.execute("CREATE TABLE IF NOT EXISTS extracted_text (id INTEGER PRIMARY KEY, content TEXT)")
for text in all_text:
    cursor.execute("INSERT INTO extracted_text (content) VALUES (?)", (text,))
conn.commit()