lanyuanxiaoyao
7eab1dcef1
- 测试数量从 83 个增加到 193 个 (+132%) - 代码覆盖率从 48% 提升到 69% (+44%) - 为每种文档格式的所有 Reader 实现创建独立测试 - 添加跨 Reader 的一致性验证测试 - 新增 4 个测试规范 (cli-testing, exception-testing, reader-testing, test-fixtures) - 更新 README 测试统计信息 测试覆盖: - DOCX: python-docx, markitdown, docling, native-xml, pypandoc, unstructured - PDF: pypdf, markitdown, docling, docling-ocr, unstructured, unstructured-ocr - HTML: html2text, markitdown, trafilatura, domscribe - PPTX: python-pptx, markitdown, docling, native-xml, unstructured - XLSX: pandas, markitdown, docling, native-xml, unstructured - CLI: 所有命令行选项和错误处理 所有 193 个测试通过。
94 lines
2.8 KiB
Python
94 lines
2.8 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 scripts.readers.base import BaseReader
|
|
from scripts.utils import is_url
|
|
from scripts.utils import encoding_detection
|
|
|
|
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 file_path.lower().endswith(('.html', '.htm'))
|
|
|
|
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 = []
|
|
|
|
# 判断输入类型
|
|
if is_url(file_path):
|
|
return self.download_and_parse(file_path)
|
|
|
|
# 检查文件是否存在
|
|
if not os.path.exists(file_path):
|
|
return None, ["文件不存在"]
|
|
|
|
# 读取本地 HTML 文件，使用编码检测
|
|
html_content, error = encoding_detection.read_text_file(file_path)
|
|
if error:
|
|
return None, [f"- {error}"]
|
|
|
|
# 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
|