## 功能特性 - 建立统一的项目结构,包含 core/、readers/、utils/、tests/ 模块 - 迁移 lyxy-reader-office 的所有解析器(docx、xlsx、pptx、pdf) - 迁移 lyxy-reader-html 的所有解析器(html、url 下载) - 统一 CLI 入口为 lyxy_document_reader.py - 统一 Markdown 后处理逻辑 - 按文件类型组织 readers,每个解析器独立文件 - 依赖分组按文件类型细分(docx、xlsx、pptx、pdf、html、http) - PDF OCR 解析器优先,无参数控制 - 使用 logging 模块替代简单 print - 设计完整的单元测试结构 - 重写项目文档 ## 新增目录/文件 - core/ - 核心模块(异常体系、Markdown 工具、解析调度器) - readers/ - 格式阅读器(base.py + docx/xlsx/pptx/pdf/html) - utils/ - 工具函数(文件类型检测) - tests/ - 测试(conftest.py + test_core/ + test_readers/ + test_utils/) - lyxy_document_reader.py - 统一 CLI 入口 ## 依赖分组 - docx - DOCX 文档解析支持 - xlsx - XLSX 文档解析支持 - pptx - PPTX 文档解析支持 - pdf - PDF 文档解析支持(含 OCR) - html - HTML/URL 解析支持 - http - HTTP/URL 下载支持 - office - Office 格式组合(docx/xlsx/pptx/pdf) - web - Web 格式组合(html/http) - full - 完整功能 - dev - 开发依赖
90 lines
2.6 KiB
Python
90 lines
2.6 KiB
Python
"""HTML/URL 文件阅读器,支持多种解析方法。"""
|
|
|
|
import os
|
|
from typing import List, Optional, Tuple
|
|
|
|
from readers.base import BaseReader
|
|
from utils import is_html_file, is_url
|
|
|
|
from . import cleaner
|
|
from . import downloader
|
|
from . import trafilatura
|
|
from . import domscribe
|
|
from . import markitdown
|
|
from . import html2text
|
|
|
|
|
|
PARSERS = [
|
|
("trafilatura", lambda c, t: trafilatura.parse(c)),
|
|
("domscribe", lambda c, t: domscribe.parse(c)),
|
|
("MarkItDown", lambda c, t: markitdown.parse(c, t)),
|
|
("html2text", lambda c, t: html2text.parse(c)),
|
|
]
|
|
|
|
|
|
class HtmlReader(BaseReader):
|
|
"""HTML/URL 文件阅读器"""
|
|
|
|
@property
|
|
def supported_extensions(self) -> List[str]:
|
|
return [".html", ".htm"]
|
|
|
|
def supports(self, file_path: str) -> bool:
|
|
return is_url(file_path) or is_html_file(file_path)
|
|
|
|
def download_and_parse(self, url: str) -> Tuple[Optional[str], List[str]]:
|
|
"""下载 URL 并解析"""
|
|
all_failures = []
|
|
|
|
# 下载 HTML
|
|
html_content, download_failures = downloader.download_html(url)
|
|
all_failures.extend(download_failures)
|
|
|
|
if html_content is None:
|
|
return None, all_failures
|
|
|
|
# 清理 HTML
|
|
html_content = cleaner.clean_html_content(html_content)
|
|
|
|
# 解析 HTML
|
|
content, parse_failures = self._parse_html_content(html_content, None)
|
|
all_failures.extend(parse_failures)
|
|
|
|
return content, all_failures
|
|
|
|
def _parse_html_content(self, html_content: str, temp_file_path: Optional[str]) -> Tuple[Optional[str], List[str]]:
|
|
"""解析 HTML 内容"""
|
|
failures = []
|
|
content = None
|
|
|
|
for parser_name, parser_func in PARSERS:
|
|
content, error = parser_func(html_content, temp_file_path)
|
|
if content is not None:
|
|
return content, failures
|
|
else:
|
|
failures.append(f"- {parser_name}: {error}")
|
|
|
|
return None, failures
|
|
|
|
def parse(self, file_path: str) -> Tuple[Optional[str], List[str]]:
|
|
all_failures = []
|
|
|
|
if is_url(file_path):
|
|
return self.download_and_parse(file_path)
|
|
|
|
# 读取 HTML 文件
|
|
try:
|
|
with open(file_path, 'r', encoding='utf-8') as f:
|
|
html_content = f.read()
|
|
except Exception as e:
|
|
return None, [f"- 读取文件失败: {str(e)}"]
|
|
|
|
# 清理 HTML
|
|
html_content = cleaner.clean_html_content(html_content)
|
|
|
|
# 解析 HTML
|
|
content, parse_failures = self._parse_html_content(html_content, file_path)
|
|
all_failures.extend(parse_failures)
|
|
|
|
return content, all_failures
|