feat: 优化 Skills URL 自动识别
- 新增 /api/fetch-skill-info 接口识别 GitHub skills 仓库 - 解析 skill markdown 的简介、应用场景和包含内容 - Skills 创建页支持一键自动填充标题、简介、来源链接 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Jowe
51
app.py
51
app.py
@@ -1909,6 +1909,56 @@ def create_app(config_name='default'):
|
||||
'message': f'抓取失败: {str(e)}'
|
||||
}), 500
|
||||
|
||||
@app.route('/api/fetch-skill-info', methods=['POST'])
|
||||
@login_required
|
||||
def fetch_skill_info():
|
||||
"""抓取 Skill 信息（GitHub 仓库）"""
|
||||
# 只允许管理员访问
|
||||
if not isinstance(current_user, AdminModel):
|
||||
return jsonify({'success': False, 'message': '无权访问'}), 403
|
||||
|
||||
try:
|
||||
data = request.get_json()
|
||||
url = data.get('url', '').strip()
|
||||
|
||||
if not url:
|
||||
return jsonify({
|
||||
'success': False,
|
||||
'message': '请提供 GitHub 仓库URL'
|
||||
}), 400
|
||||
|
||||
# 创建抓取器
|
||||
fetcher = WebsiteFetcher(timeout=15)
|
||||
|
||||
# 抓取 Skill 信息
|
||||
info = fetcher.fetch_skill_info(url)
|
||||
|
||||
if not info:
|
||||
return jsonify({
|
||||
'success': False,
|
||||
'message': '无法获取 Skill 信息，请检查 URL 是否为有效的 GitHub 仓库'
|
||||
})
|
||||
|
||||
return jsonify({
|
||||
'success': True,
|
||||
'data': {
|
||||
'name': info.get('name', ''),
|
||||
'short_desc': info.get('short_desc', ''),
|
||||
'description': info.get('description', ''),
|
||||
'github_url': info.get('github_url', ''),
|
||||
'source_repo': info.get('source_repo', ''),
|
||||
'source_type': 'github',
|
||||
'usage': info.get('usage', ''),
|
||||
'examples': info.get('examples', '')
|
||||
}
|
||||
})
|
||||
|
||||
except Exception as e:
|
||||
return jsonify({
|
||||
'success': False,
|
||||
'message': f'抓取失败: {str(e)}'
|
||||
}), 500
|
||||
|
||||
@app.route('/api/upload-logo', methods=['POST'])
|
||||
@login_required
|
||||
def upload_logo():
|
||||
@@ -3417,6 +3467,7 @@ Sitemap: {}sitemap.xml
|
||||
|
||||
# Skills管理视图
|
||||
class SkillAdmin(SecureModelView):
|
||||
create_template = 'admin/skill/create.html'
|
||||
can_edit = True
|
||||
can_delete = True
|
||||
can_create = True
|
||||
|
||||
224
templates/admin/skill/create.html
Normal file
224
templates/admin/skill/create.html
Normal file
@@ -0,0 +1,224 @@
|
||||
{% extends 'admin/model/create.html' %}
|
||||
|
||||
{% block tail %}
|
||||
{{ super() }}
|
||||
<style>
|
||||
.auto-fetch-btn {
|
||||
margin-top: 10px;
|
||||
margin-bottom: 15px;
|
||||
}
|
||||
.fetch-status {
|
||||
margin-top: 10px;
|
||||
padding: 10px;
|
||||
border-radius: 8px;
|
||||
display: none;
|
||||
}
|
||||
.fetch-status.success {
|
||||
background-color: rgba(34, 197, 94, 0.1);
|
||||
border: 1px solid rgba(34, 197, 94, 0.3);
|
||||
color: #4ade80;
|
||||
}
|
||||
.fetch-status.error {
|
||||
background-color: rgba(239, 68, 68, 0.1);
|
||||
border: 1px solid rgba(239, 68, 68, 0.3);
|
||||
color: #f87171;
|
||||
}
|
||||
.logo-preview {
|
||||
margin-top: 10px;
|
||||
max-width: 100px;
|
||||
max-height: 100px;
|
||||
display: none;
|
||||
}
|
||||
.logo-preview img {
|
||||
max-width: 100%;
|
||||
max-height: 80px;
|
||||
object-fit: contain;
|
||||
border-radius: 8px;
|
||||
border: 1px solid #ddd;
|
||||
}
|
||||
</style>
|
||||
{% endblock %}
|
||||
|
||||
{% block header %}
|
||||
<h2>添加 Skill</h2>
|
||||
{% endblock %}
|
||||
|
||||
{% block form %}
|
||||
<div class="form-group">
|
||||
<label for="github_url">GitHub 仓库 URL <span style="color: #999; font-weight: normal;">(可选，填写后自动获取信息)</span></label>
|
||||
<div style="display: flex; gap: 10px; align-items: flex-start;">
|
||||
<input type="text" class="form-control" id="github_url" placeholder="例如: https://github.com/anthropics/claude-code" style="flex: 1;">
|
||||
<button type="button" class="auto-fetch-btn btn btn-info" id="fetchSkillBtn">
|
||||
<span class="material-symbols-outlined" style="vertical-align: middle;">auto_awesome</span>
|
||||
自动识别
|
||||
</button>
|
||||
</div>
|
||||
<div class="fetch-status" id="fetchStatus"></div>
|
||||
</div>
|
||||
|
||||
<div class="form-group">
|
||||
<label for="name">Skill 名称 <span style="color: #e74c3c;">*</span></label>
|
||||
<input type="text" class="form-control" name="name" id="name" required placeholder="例如: PDF Helper">
|
||||
</div>
|
||||
|
||||
<div class="form-group">
|
||||
<label for="short_desc">简短描述</label>
|
||||
<input type="text" class="form-control" name="short_desc" id="short_desc" placeholder="一句话描述这个 Skill 的用途">
|
||||
</div>
|
||||
|
||||
<div class="form-group">
|
||||
<label for="description">详细介绍</label>
|
||||
<textarea class="form-control" name="description" id="description" rows="4" placeholder="详细介绍这个 Skill 的功能和使用场景"></textarea>
|
||||
</div>
|
||||
|
||||
<div class="form-group">
|
||||
<label for="logo">Logo 图片路径</label>
|
||||
<input type="text" class="form-control" name="logo" id="logo" placeholder="/static/logos/xxx.png">
|
||||
<div class="logo-preview" id="logoPreview">
|
||||
<img id="logoImg" src="" alt="Logo预览">
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="form-group">
|
||||
<label for="github_url_field">GitHub 链接</label>
|
||||
<input type="text" class="form-control" name="github_url" id="github_url_field" placeholder="https://github.com/...">
|
||||
</div>
|
||||
|
||||
<div class="form-group">
|
||||
<label for="source_type">来源类型</label>
|
||||
<select class="form-control" name="source_type" id="source_type">
|
||||
<option value="manual" selected>手动添加</option>
|
||||
<option value="github">GitHub</option>
|
||||
</select>
|
||||
</div>
|
||||
|
||||
<div class="form-group">
|
||||
<label for="source_repo">来源仓库</label>
|
||||
<input type="text" class="form-control" name="source_repo" id="source_repo" placeholder="owner/repo">
|
||||
</div>
|
||||
|
||||
<div class="form-group">
|
||||
<label for="usage">包含内容 / 应用场景</label>
|
||||
<textarea class="form-control" name="usage" id="usage" rows="4" placeholder="这个 skills 仓库主要包含哪些内容、适合什么场景"></textarea>
|
||||
</div>
|
||||
|
||||
<div class="form-group">
|
||||
<label for="examples">来源链接 / 示例</label>
|
||||
<textarea class="form-control" name="examples" id="examples" rows="4" placeholder="主要来源链接或示例链接"></textarea>
|
||||
</div>
|
||||
|
||||
<div class="form-group">
|
||||
<div class="form-check">
|
||||
<input type="checkbox" class="form-check-input" name="is_active" id="is_active" checked>
|
||||
<label class="form-check-label" for="is_active">启用</label>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="form-group">
|
||||
<div class="form-check">
|
||||
<input type="checkbox" class="form-check-input" name="is_featured" id="is_featured">
|
||||
<label class="form-check-label" for="is_featured">推荐</label>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="form-group">
|
||||
<label for="sort_order">排序权重</label>
|
||||
<input type="number" class="form-control" name="sort_order" id="sort_order" value="0" placeholder="数字越大越靠前">
|
||||
</div>
|
||||
|
||||
<div class="form-group">
|
||||
<button type="submit" class="btn btn-primary">保存</button>
|
||||
<a href="{{ url_for('skills.index_view') }}" class="btn btn-secondary">取消</a>
|
||||
</div>
|
||||
{% endblock %}
|
||||
|
||||
{% block tail2 %}
|
||||
<script>
|
||||
document.addEventListener('DOMContentLoaded', function() {
|
||||
const fetchBtn = document.getElementById('fetchSkillBtn');
|
||||
const urlInput = document.getElementById('github_url');
|
||||
const statusDiv = document.getElementById('fetchStatus');
|
||||
const logoInput = document.getElementById('logo');
|
||||
const logoPreview = document.getElementById('logoPreview');
|
||||
const logoImg = document.getElementById('logoImg');
|
||||
|
||||
function showStatus(message, type) {
|
||||
statusDiv.textContent = message;
|
||||
statusDiv.className = 'fetch-status ' + type;
|
||||
statusDiv.style.display = 'block';
|
||||
}
|
||||
|
||||
if (logoInput) {
|
||||
logoInput.addEventListener('input', function() {
|
||||
if (this.value) {
|
||||
logoImg.src = this.value;
|
||||
logoPreview.style.display = 'block';
|
||||
} else {
|
||||
logoPreview.style.display = 'none';
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
if (fetchBtn && urlInput) {
|
||||
fetchBtn.addEventListener('click', function() {
|
||||
const url = urlInput.value.trim();
|
||||
|
||||
if (!url) {
|
||||
showStatus('请先输入 GitHub 仓库 URL', 'error');
|
||||
return;
|
||||
}
|
||||
|
||||
if (!url.includes('github.com')) {
|
||||
showStatus('请输入有效的 GitHub 仓库 URL', 'error');
|
||||
return;
|
||||
}
|
||||
|
||||
fetchBtn.disabled = true;
|
||||
statusDiv.style.display = 'none';
|
||||
|
||||
fetch('/api/fetch-skill-info', {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({ url: url })
|
||||
})
|
||||
.then(response => response.json())
|
||||
.then(data => {
|
||||
if (!data.success) {
|
||||
showStatus('✗ ' + (data.message || '获取失败，请手动填写'), 'error');
|
||||
return;
|
||||
}
|
||||
|
||||
const nameField = document.querySelector('input[name="name"]');
|
||||
const shortDescField = document.querySelector('input[name="short_desc"]');
|
||||
const descriptionField = document.querySelector('textarea[name="description"]');
|
||||
const githubUrlField = document.querySelector('input[name="github_url"]');
|
||||
const sourceRepoField = document.querySelector('input[name="source_repo"]');
|
||||
const sourceTypeField = document.querySelector('select[name="source_type"]');
|
||||
const usageField = document.querySelector('textarea[name="usage"]');
|
||||
const examplesField = document.querySelector('textarea[name="examples"]');
|
||||
|
||||
if (nameField && data.data.name) nameField.value = data.data.name;
|
||||
if (shortDescField && data.data.short_desc) shortDescField.value = data.data.short_desc.substring(0, 100);
|
||||
if (descriptionField && data.data.description) descriptionField.value = data.data.description;
|
||||
if (githubUrlField && data.data.github_url) githubUrlField.value = data.data.github_url;
|
||||
if (sourceRepoField && data.data.source_repo) sourceRepoField.value = data.data.source_repo;
|
||||
if (sourceTypeField && data.data.source_type) sourceTypeField.value = data.data.source_type;
|
||||
if (usageField && data.data.usage) usageField.value = data.data.usage;
|
||||
if (examplesField && data.data.examples) examplesField.value = data.data.examples;
|
||||
|
||||
showStatus('✓ Skill 信息获取成功！已自动填充标题、简介、应用场景和来源链接', 'success');
|
||||
})
|
||||
.catch(error => {
|
||||
console.error('Error:', error);
|
||||
showStatus('✗ 网络请求失败，请手动填写', 'error');
|
||||
})
|
||||
.finally(() => {
|
||||
fetchBtn.disabled = false;
|
||||
});
|
||||
});
|
||||
}
|
||||
});
|
||||
</script>
|
||||
{% endblock %}
|
||||
@@ -6,6 +6,7 @@ import requests
|
||||
from bs4 import BeautifulSoup
|
||||
from urllib.parse import urljoin, urlparse
|
||||
import os
|
||||
import re
|
||||
from PIL import Image
|
||||
from io import BytesIO
|
||||
|
||||
@@ -54,6 +55,243 @@ class WebsiteFetcher:
|
||||
print(f"抓取网站信息失败: {str(e)}")
|
||||
return None
|
||||
|
||||
def fetch_skill_info(self, url):
|
||||
"""
|
||||
抓取 Skill 信息（GitHub 仓库）
|
||||
|
||||
Args:
|
||||
url: GitHub 仓库URL
|
||||
|
||||
Returns:
|
||||
dict: 包含name, short_desc, github_url, source_repo的字典
|
||||
"""
|
||||
try:
|
||||
# 解析 GitHub URL
|
||||
# 支持格式: https://github.com/user/repo 或 https://github.com/user/repo/tree/main
|
||||
parsed = urlparse(url)
|
||||
if 'github.com' not in parsed.netloc:
|
||||
return None
|
||||
|
||||
path_parts = [p for p in parsed.path.split('/') if p]
|
||||
if len(path_parts) < 2:
|
||||
return None
|
||||
|
||||
owner = path_parts[0]
|
||||
repo = path_parts[1].replace('.git', '')
|
||||
|
||||
# 获取仓库信息
|
||||
api_url = f"https://api.github.com/repos/{owner}/{repo}"
|
||||
response = requests.get(api_url, headers=self.headers, timeout=self.timeout)
|
||||
if response.status_code != 200:
|
||||
return None
|
||||
|
||||
repo_info = response.json()
|
||||
|
||||
# 获取 .claude 目录下的 skills
|
||||
skills_url = f"https://api.github.com/repos/{owner}/{repo}/contents/.claude/skills"
|
||||
skills_response = requests.get(skills_url, headers=self.headers, timeout=self.timeout)
|
||||
|
||||
skills = []
|
||||
if skills_response.status_code == 200:
|
||||
skills_data = skills_response.json()
|
||||
for item in skills_data:
|
||||
if item.get('type') == 'file' and item['name'].endswith('.md'):
|
||||
# 获取 skill 文件内容
|
||||
skill_content = requests.get(item['download_url'], headers=self.headers, timeout=self.timeout)
|
||||
if skill_content.status_code == 200:
|
||||
skill_info = self._parse_skill_file(
|
||||
item['name'],
|
||||
skill_content.text,
|
||||
item.get('html_url') or item.get('download_url') or ''
|
||||
)
|
||||
if skill_info:
|
||||
skills.append(skill_info)
|
||||
|
||||
summary = self._summarize_skills(repo_info, skills)
|
||||
|
||||
return {
|
||||
'name': summary.get('name') or repo_info.get('name', ''),
|
||||
'short_desc': summary.get('short_desc') or repo_info.get('description', ''),
|
||||
'description': summary.get('description', ''),
|
||||
'github_url': url,
|
||||
'source_repo': f"{owner}/{repo}",
|
||||
'usage': summary.get('usage', ''),
|
||||
'examples': summary.get('examples', ''),
|
||||
'skills': skills
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
print(f"抓取 Skill 信息失败: {str(e)}")
|
||||
return None
|
||||
|
||||
def _parse_skill_file(self, filename, content, source_url=''):
|
||||
"""解析 skill 文件内容"""
|
||||
try:
|
||||
lines = [line.rstrip() for line in content.strip().split('\n')]
|
||||
fallback_name = filename.replace('.md', '')
|
||||
title = fallback_name
|
||||
|
||||
for line in lines:
|
||||
if line.startswith('# '):
|
||||
title = line[2:].strip()
|
||||
break
|
||||
|
||||
sections = self._extract_markdown_sections(lines)
|
||||
|
||||
desc = self._pick_section(
|
||||
sections,
|
||||
['描述', '简介', 'description', 'overview', 'summary', 'what it does']
|
||||
)
|
||||
use_cases = self._pick_section(
|
||||
sections,
|
||||
['应用场景', '适用场景', '使用场景', 'use cases', 'when to use', 'use case']
|
||||
)
|
||||
usage = self._pick_section(
|
||||
sections,
|
||||
['使用方法', '用法', 'usage', 'how to use', 'quick start']
|
||||
)
|
||||
examples = self._pick_section(
|
||||
sections,
|
||||
['示例', 'examples', 'example']
|
||||
)
|
||||
|
||||
if not desc:
|
||||
desc = self._first_paragraph(lines)
|
||||
|
||||
content_outline = self._extract_outline(sections)
|
||||
|
||||
return {
|
||||
'name': title,
|
||||
'description': self._clean_text(desc)[:240],
|
||||
'use_cases': self._clean_text(use_cases)[:240],
|
||||
'usage': self._clean_text(usage)[:600],
|
||||
'examples': self._clean_text(examples)[:600],
|
||||
'content_outline': content_outline,
|
||||
'source_url': source_url
|
||||
}
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
def _extract_markdown_sections(self, lines):
|
||||
sections = {}
|
||||
current = '__intro__'
|
||||
buffer = []
|
||||
|
||||
for raw_line in lines:
|
||||
line = raw_line.strip()
|
||||
if line.startswith('##'):
|
||||
sections[current] = '\n'.join(buffer).strip()
|
||||
current = re.sub(r'^#+\s*', '', line).strip().lower()
|
||||
buffer = []
|
||||
else:
|
||||
buffer.append(raw_line)
|
||||
|
||||
sections[current] = '\n'.join(buffer).strip()
|
||||
return sections
|
||||
|
||||
def _pick_section(self, sections, keywords):
|
||||
for key, value in sections.items():
|
||||
low = key.lower()
|
||||
for keyword in keywords:
|
||||
if keyword.lower() in low and value.strip():
|
||||
return value.strip()
|
||||
return ''
|
||||
|
||||
def _first_paragraph(self, lines):
|
||||
paragraph = []
|
||||
for line in lines:
|
||||
stripped = line.strip()
|
||||
if not stripped or stripped.startswith('#'):
|
||||
if paragraph:
|
||||
break
|
||||
continue
|
||||
if stripped.startswith('- ') or stripped.startswith('* ') or stripped.startswith('```'):
|
||||
continue
|
||||
paragraph.append(stripped)
|
||||
if len(' '.join(paragraph)) > 220:
|
||||
break
|
||||
return ' '.join(paragraph)
|
||||
|
||||
def _extract_outline(self, sections):
|
||||
outlines = []
|
||||
for key in sections.keys():
|
||||
if key != '__intro__':
|
||||
clean_key = key.strip()
|
||||
if clean_key:
|
||||
outlines.append(clean_key)
|
||||
return outlines[:8]
|
||||
|
||||
def _clean_text(self, text):
|
||||
if not text:
|
||||
return ''
|
||||
text = re.sub(r'```.*?```', '', text, flags=re.S)
|
||||
text = re.sub(r'`([^`]+)`', r'\1', text)
|
||||
text = re.sub(r'\[(.*?)\]\((.*?)\)', r'\1', text)
|
||||
text = re.sub(r'^[-*]\s+', '', text, flags=re.M)
|
||||
text = re.sub(r'\n{2,}', '\n', text)
|
||||
text = re.sub(r'\s+', ' ', text)
|
||||
return text.strip()
|
||||
|
||||
def _summarize_skills(self, repo_info, skills):
|
||||
if not skills:
|
||||
return {
|
||||
'name': repo_info.get('name', ''),
|
||||
'short_desc': repo_info.get('description', ''),
|
||||
'description': repo_info.get('description', ''),
|
||||
'usage': '',
|
||||
'examples': ''
|
||||
}
|
||||
|
||||
skill_names = [s['name'] for s in skills if s.get('name')]
|
||||
use_cases = [s['use_cases'] for s in skills if s.get('use_cases')]
|
||||
descs = [s['description'] for s in skills if s.get('description')]
|
||||
outlines = []
|
||||
for s in skills:
|
||||
outlines.extend(s.get('content_outline', []))
|
||||
|
||||
repo_desc = (repo_info.get('description') or '').strip()
|
||||
short_desc = repo_desc or (descs[0] if descs else '')
|
||||
|
||||
parts = []
|
||||
if repo_desc:
|
||||
parts.append(f"仓库简介：{repo_desc}")
|
||||
if skill_names:
|
||||
shown = '、'.join(skill_names[:5])
|
||||
more = f" 等 {len(skill_names)} 个 skill" if len(skill_names) > 5 else ''
|
||||
parts.append(f"包含内容：{shown}{more}")
|
||||
if use_cases:
|
||||
parts.append(f"应用场景：{use_cases[0]}")
|
||||
elif descs:
|
||||
parts.append(f"应用场景：{descs[0]}")
|
||||
if outlines:
|
||||
uniq = []
|
||||
for item in outlines:
|
||||
if item not in uniq:
|
||||
uniq.append(item)
|
||||
parts.append(f"文档涵盖：{'、'.join(uniq[:6])}")
|
||||
|
||||
usage_lines = []
|
||||
for s in skills[:5]:
|
||||
line = f"- {s['name']}"
|
||||
if s.get('use_cases'):
|
||||
line += f"：{s['use_cases']}"
|
||||
elif s.get('description'):
|
||||
line += f"：{s['description']}"
|
||||
usage_lines.append(line)
|
||||
|
||||
examples_lines = []
|
||||
for s in skills[:3]:
|
||||
if s.get('source_url'):
|
||||
examples_lines.append(f"{s['name']}：{s['source_url']}")
|
||||
|
||||
return {
|
||||
'name': repo_info.get('name', ''),
|
||||
'short_desc': short_desc[:180],
|
||||
'description': '\n'.join(parts)[:1200],
|
||||
'usage': '\n'.join(usage_lines)[:1200],
|
||||
'examples': '\n'.join(examples_lines)[:1200]
|
||||
}
|
||||
|
||||
def _extract_title(self, soup):
|
||||
"""提取网站标题"""
|
||||
# 优先使用 og:title
|
||||
@@ -80,89 +318,83 @@ class WebsiteFetcher:
|
||||
if meta_desc and meta_desc.get('content'):
|
||||
return meta_desc['content'].strip()
|
||||
|
||||
# 使用 meta keywords 作为fallback
|
||||
meta_keywords = soup.find('meta', attrs={'name': 'keywords'})
|
||||
if meta_keywords and meta_keywords.get('content'):
|
||||
return meta_keywords['content'].strip()
|
||||
|
||||
return ''
|
||||
|
||||
def _extract_logo(self, soup, base_url):
|
||||
"""提取网站Logo"""
|
||||
logo_url = None
|
||||
"""提取网站 Logo URL"""
|
||||
# 优先查找 favicon
|
||||
favicon = soup.find('link', rel='icon') or soup.find('link', rel='shortcut icon')
|
||||
if favicon and favicon.get('href'):
|
||||
return urljoin(base_url, favicon['href'])
|
||||
|
||||
# 1. 尝试 og:image
|
||||
og_image = soup.find('meta', property='og:image')
|
||||
if og_image and og_image.get('content'):
|
||||
logo_url = og_image['content']
|
||||
# 查找 apple-touch-icon
|
||||
apple_icon = soup.find('link', rel='apple-touch-icon')
|
||||
if apple_icon and apple_icon.get('href'):
|
||||
return urljoin(base_url, apple_icon['href'])
|
||||
|
||||
# 2. 尝试 link rel="icon" 或 "shortcut icon"
|
||||
if not logo_url:
|
||||
icon_link = soup.find('link', rel=lambda x: x and ('icon' in x.lower() if isinstance(x, str) else 'icon' in ' '.join(x).lower()))
|
||||
if icon_link and icon_link.get('href'):
|
||||
logo_url = icon_link['href']
|
||||
# 使用 /favicon.ico
|
||||
parsed = urlparse(base_url)
|
||||
return f"{parsed.scheme}://{parsed.netloc}/favicon.ico"
|
||||
|
||||
# 3. 尝试 apple-touch-icon
|
||||
if not logo_url:
|
||||
apple_icon = soup.find('link', rel='apple-touch-icon')
|
||||
if apple_icon and apple_icon.get('href'):
|
||||
logo_url = apple_icon['href']
|
||||
|
||||
# 4. 默认使用 /favicon.ico
|
||||
if not logo_url:
|
||||
logo_url = '/favicon.ico'
|
||||
|
||||
# 转换为绝对URL
|
||||
if logo_url:
|
||||
logo_url = urljoin(base_url, logo_url)
|
||||
|
||||
return logo_url
|
||||
|
||||
def download_logo(self, logo_url, save_dir='static/uploads'):
|
||||
def download_logo(self, logo_url, save_dir='static/logos'):
|
||||
"""
|
||||
下载并保存Logo
|
||||
下载 Logo 到本地
|
||||
|
||||
Args:
|
||||
logo_url: Logo的URL
|
||||
logo_url: Logo URL
|
||||
save_dir: 保存目录
|
||||
|
||||
Returns:
|
||||
str: 保存后的相对路径，失败返回None
|
||||
str: 保存后的文件路径，失败返回 None
|
||||
"""
|
||||
if not logo_url:
|
||||
return None
|
||||
|
||||
try:
|
||||
# 创建保存目录
|
||||
# 确保目录存在
|
||||
os.makedirs(save_dir, exist_ok=True)
|
||||
|
||||
# 下载图片
|
||||
response = requests.get(logo_url, headers=self.headers, timeout=self.timeout)
|
||||
response.raise_for_status()
|
||||
response = requests.get(logo_url, headers=self.headers, timeout=10, stream=True)
|
||||
if response.status_code != 200:
|
||||
return None
|
||||
|
||||
# 检查是否是图片
|
||||
content_type = response.headers.get('content-type', '')
|
||||
if not content_type.startswith('image/'):
|
||||
content_type = response.headers.get('Content-Type', '').lower()
|
||||
if 'image' not in content_type:
|
||||
return None
|
||||
|
||||
# 生成文件名
|
||||
parsed_url = urlparse(logo_url)
|
||||
ext = os.path.splitext(parsed_url.path)[1]
|
||||
if not ext or len(ext) > 5:
|
||||
ext = '.png' # 默认扩展名
|
||||
import time
|
||||
import hashlib
|
||||
ext = '.png'
|
||||
if 'jpeg' in content_type or 'jpg' in content_type:
|
||||
ext = '.jpg'
|
||||
elif 'gif' in content_type:
|
||||
ext = '.gif'
|
||||
elif 'svg' in content_type:
|
||||
ext = '.svg'
|
||||
elif 'ico' in content_type:
|
||||
ext = '.ico'
|
||||
|
||||
# 使用域名作为文件名
|
||||
domain = parsed_url.netloc.replace(':', '_').replace('.', '_')
|
||||
filename = f"logo_{domain}{ext}"
|
||||
timestamp = str(int(time.time() * 1000))
|
||||
hash_name = hashlib.md5(f"{logo_url}{timestamp}".encode()).hexdigest()[:16]
|
||||
filename = f"logo_{hash_name}{ext}"
|
||||
filepath = os.path.join(save_dir, filename)
|
||||
|
||||
# 保存图片
|
||||
with open(filepath, 'wb') as f:
|
||||
f.write(response.content)
|
||||
for chunk in response.iter_content(8192):
|
||||
f.write(chunk)
|
||||
|
||||
# 返回相对路径（用于数据库存储）
|
||||
return f'/{filepath.replace(os.sep, "/")}'
|
||||
# 验证图片是否有效
|
||||
try:
|
||||
with Image.open(filepath) as img:
|
||||
img.verify()
|
||||
return filepath
|
||||
except:
|
||||
# 图片无效，删除文件
|
||||
if os.path.exists(filepath):
|
||||
os.remove(filepath)
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
print(f"下载Logo失败: {str(e)}")
|
||||
print(f"下载 Logo 失败: {str(e)}")
|
||||
return None
|
||||
Reference in New Issue
Block a user