第 07 章：文档解析

from pypdf import PdfReader

def read_pdf(path: str):
    reader = PdfReader(path)
    pages = []
    for i, page in enumerate(reader.pages, start=1):
        text = page.extract_text() or ""
        pages.append({"page": i, "text": text.strip()})
    return pages

from docx import Document

def read_docx(path: str):
    doc = Document(path)
    blocks = []
    for p in doc.paragraphs:
        if not p.text.strip():
            continue
        blocks.append({
            "type": "paragraph",
            "style": p.style.name,
            "text": p.text.strip(),
        })

    for table in doc.tables:
        rows = [[cell.text.strip() for cell in row.cells] for row in table.rows]
        blocks.append({"type": "table", "rows": rows})
    return blocks

import requests
from bs4 import BeautifulSoup

def read_html(url: str):
    html = requests.get(url, timeout=10).text
    soup = BeautifulSoup(html, "html.parser")

    for tag in soup(["script", "style", "nav", "footer"]):
        tag.decompose()

    title = soup.title.get_text(strip=True) if soup.title else ""
    text = "\n".join(
        p.get_text(" ", strip=True)
        for p in soup.find_all(["h1", "h2", "h3", "p", "li"])
        if p.get_text(strip=True)
    )
    return {"title": title, "text": text}