205 lines
6.9 KiB
Python
205 lines
6.9 KiB
Python
|
"""OneNav/Chrome书签HTML文件解析工具"""
|
|||
|
|
from bs4 import BeautifulSoup
|
|||
|
|
from typing import List, Dict
|
|||
|
|
import re
|
|||
|
|
|
|||
|
|
|
|||
|
|
class BookmarkParser:
|
|||
|
|
"""解析OneNav/Chrome导出的书签HTML文件"""
|
|||
|
|
|
|||
|
|
def parse_html_file(self, html_content: str, debug=False) -> Dict[str, any]:
|
|||
|
|
"""
|
|||
|
|
解析OneNav/Chrome书签HTML文件
|
|||
|
|
|
|||
|
|
Args:
|
|||
|
|
html_content: HTML文件内容
|
|||
|
|
debug: 是否打印调试信息
|
|||
|
|
|
|||
|
|
Returns:
|
|||
|
|
Dict: 包含 categories(标签列表) 和 sites(网站列表)
|
|||
|
|
"""
|
|||
|
|
soup = BeautifulSoup(html_content, 'html.parser')
|
|||
|
|
categories = set() # 使用set去重
|
|||
|
|
sites = []
|
|||
|
|
|
|||
|
|
# 找到第一个DL标签作为起点
|
|||
|
|
first_dl = soup.find('dl')
|
|||
|
|
if first_dl:
|
|||
|
|
# 递归解析书签，收集分类和网站
|
|||
|
|
self._parse_dl_tag(first_dl, categories, sites, current_category=None, debug=debug)
|
|||
|
|
|
|||
|
|
return {
|
|||
|
|
'categories': sorted(list(categories)), # 转为排序的列表
|
|||
|
|
'sites': sites
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
def parse_html_file_legacy(self, html_content: str) -> List[Dict[str, str]]:
|
|||
|
|
"""
|
|||
|
|
解析Chrome书签HTML文件（旧版格式）
|
|||
|
|
|
|||
|
|
Args:
|
|||
|
|
html_content: HTML文件内容
|
|||
|
|
|
|||
|
|
Returns:
|
|||
|
|
List[Dict]: 书签列表，每个书签包含 name, url, folder
|
|||
|
|
"""
|
|||
|
|
soup = BeautifulSoup(html_content, 'html.parser')
|
|||
|
|
bookmarks = []
|
|||
|
|
|
|||
|
|
# 递归解析书签
|
|||
|
|
self._parse_dl_tag_legacy(soup, bookmarks, folder_path="")
|
|||
|
|
|
|||
|
|
return bookmarks
|
|||
|
|
|
|||
|
|
def _parse_dl_tag(self, element, categories: set, sites: List[Dict], current_category: str, debug=False):
|
|||
|
|
"""递归解析DL标签（OneNav格式）"""
|
|||
|
|
# 查找所有DT标签（不限制为直接子元素，因为可能在p标签内）
|
|||
|
|
dt_list = element.find_all('dt')
|
|||
|
|
if debug and dt_list:
|
|||
|
|
print(f"Found {len(dt_list)} DT tags total")
|
|||
|
|
|
|||
|
|
for dt in dt_list:
|
|||
|
|
# 检查是否是文件夹/分类
|
|||
|
|
h3 = dt.find('h3', recursive=False)
|
|||
|
|
if h3:
|
|||
|
|
category_name = h3.get_text(strip=True)
|
|||
|
|
|
|||
|
|
# 跳过根节点和默认分类
|
|||
|
|
if category_name not in ['OneNav', 'OneNav默认分类']:
|
|||
|
|
categories.add(category_name)
|
|||
|
|
if debug:
|
|||
|
|
print(f" Category: {category_name}")
|
|||
|
|
|
|||
|
|
# 检查是否是书签链接（并且不在子分类的DL中）
|
|||
|
|
a = dt.find('a', recursive=False)
|
|||
|
|
if a and a.get('href'):
|
|||
|
|
# 找到这个DT所属的最近的H3分类
|
|||
|
|
parent_category = None
|
|||
|
|
# 向上查找同级或父级的H3
|
|||
|
|
prev = dt.find_previous('h3')
|
|||
|
|
if prev:
|
|||
|
|
parent_category = prev.get_text(strip=True)
|
|||
|
|
# 跳过根节点和默认分类
|
|||
|
|
if parent_category in ['OneNav', 'OneNav默认分类']:
|
|||
|
|
parent_category = None
|
|||
|
|
|
|||
|
|
if parent_category:
|
|||
|
|
url = a['href']
|
|||
|
|
title = a.get_text(strip=True)
|
|||
|
|
|
|||
|
|
sites.append({
|
|||
|
|
'title': title,
|
|||
|
|
'url': url,
|
|||
|
|
'category': parent_category,
|
|||
|
|
'add_date': a.get('add_date', '')
|
|||
|
|
})
|
|||
|
|
if debug:
|
|||
|
|
print(f" Site: {title} -> {parent_category}")
|
|||
|
|
|
|||
|
|
def _parse_dl_tag_legacy(self, element, bookmarks: List[Dict], folder_path: str):
|
|||
|
|
"""递归解析DL标签（Chrome旧格式）"""
|
|||
|
|
# 查找所有DT标签（书签项）
|
|||
|
|
for dt in element.find_all('dt', recursive=False):
|
|||
|
|
# 检查是否是文件夹
|
|||
|
|
h3 = dt.find('h3', recursive=False)
|
|||
|
|
if h3:
|
|||
|
|
folder_name = h3.get_text(strip=True)
|
|||
|
|
new_folder_path = f"{folder_path}/{folder_name}" if folder_path else folder_name
|
|||
|
|
|
|||
|
|
# 递归解析子文件夹
|
|||
|
|
dl = dt.find('dl', recursive=False)
|
|||
|
|
if dl:
|
|||
|
|
self._parse_dl_tag_legacy(dl, bookmarks, new_folder_path)
|
|||
|
|
|
|||
|
|
# 检查是否是书签链接
|
|||
|
|
a = dt.find('a', recursive=False)
|
|||
|
|
if a and a.get('href'):
|
|||
|
|
url = a['href']
|
|||
|
|
name = a.get_text(strip=True)
|
|||
|
|
|
|||
|
|
bookmarks.append({
|
|||
|
|
'name': name,
|
|||
|
|
'url': url,
|
|||
|
|
'folder': folder_path
|
|||
|
|
})
|
|||
|
|
|
|||
|
|
def parse_url_list(self, text: str) -> List[Dict[str, str]]:
|
|||
|
|
"""
|
|||
|
|
解析纯文本URL列表
|
|||
|
|
|
|||
|
|
Args:
|
|||
|
|
text: 文本内容，每行一个URL
|
|||
|
|
|
|||
|
|
Returns:
|
|||
|
|
List[Dict]: URL列表
|
|||
|
|
"""
|
|||
|
|
urls = []
|
|||
|
|
lines = text.strip().split('\n')
|
|||
|
|
|
|||
|
|
for line in lines:
|
|||
|
|
line = line.strip()
|
|||
|
|
if not line or line.startswith('#'):
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
# 简单的URL验证
|
|||
|
|
if re.match(r'^https?://', line):
|
|||
|
|
urls.append({
|
|||
|
|
'url': line,
|
|||
|
|
'name': '', # 名称留空，后续自动获取
|
|||
|
|
'folder': ''
|
|||
|
|
})
|
|||
|
|
|
|||
|
|
return urls
|
|||
|
|
|
|||
|
|
@staticmethod
|
|||
|
|
def clean_title(title: str) -> str:
|
|||
|
|
"""清理网站标题，提取网站名称"""
|
|||
|
|
if not title:
|
|||
|
|
return ''
|
|||
|
|
|
|||
|
|
# 去除HTML实体
|
|||
|
|
title = re.sub(r'&', '&', title)
|
|||
|
|
title = re.sub(r'<', '<', title)
|
|||
|
|
title = re.sub(r'>', '>', title)
|
|||
|
|
title = re.sub(r'"', '"', title)
|
|||
|
|
|
|||
|
|
# 常见的分隔符
|
|||
|
|
separators = [' - ', ' | ', ' · ', '·', '｜', ' — ']
|
|||
|
|
for sep in separators:
|
|||
|
|
if sep in title:
|
|||
|
|
parts = title.split(sep)
|
|||
|
|
# 过滤掉常见的无用部分
|
|||
|
|
filtered_parts = []
|
|||
|
|
skip_keywords = ['官网', '首页', 'official', 'home', 'page', 'website']
|
|||
|
|
|
|||
|
|
for part in parts:
|
|||
|
|
part = part.strip()
|
|||
|
|
if part and not any(kw in part.lower() for kw in skip_keywords):
|
|||
|
|
filtered_parts.append(part)
|
|||
|
|
|
|||
|
|
if filtered_parts:
|
|||
|
|
# 返回最短的部分（通常是网站名）
|
|||
|
|
return min(filtered_parts, key=len)
|
|||
|
|
|
|||
|
|
# 去除一些常见的后缀词
|
|||
|
|
suffixes = [
|
|||
|
|
r'\s*官网\s*$', r'\s*首页\s*$',
|
|||
|
|
r'\s*Official Site\s*$', r'\s*Home Page\s*$',
|
|||
|
|
r'\s*Homepage\s*$', r'\s*Website\s*$'
|
|||
|
|
]
|
|||
|
|
for suffix in suffixes:
|
|||
|
|
title = re.sub(suffix, '', title, flags=re.IGNORECASE)
|
|||
|
|
|
|||
|
|
return title.strip()
|
|||
|
|
|
|||
|
|
@staticmethod
|
|||
|
|
def extract_domain(url: str) -> str:
|
|||
|
|
"""从URL提取域名"""
|
|||
|
|
match = re.search(r'https?://([^/]+)', url)
|
|||
|
|
if match:
|
|||
|
|
domain = match.group(1)
|
|||
|
|
# 去除www前缀
|
|||
|
|
domain = re.sub(r'^www\.', '', domain)
|
|||
|
|
return domain
|
|||
|
|
return url
|