Files
StarPunk/starpunk/webmention_processor.py
T
PhilandClaude Opus 5.5 106495d114 fix: Webmention processing works end to end (v2.6.9)
- Normalise mf2 author values: u-photo with alt text is a dict in mf2py and
  broke the database update for most real senders
- Pass str(response.url) to urljoin during endpoint discovery; the TypeError
  marked every target as having no endpoint. Retry on discovery errors
- Hold a cross-process flock so only one gunicorn process runs the worker
- Keep author URL/photo only if http(s) (XSS via javascript: URLs)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 07:53:19 -07:00

399 lines
13 KiB
Python

"""
Webmention validation and processing utilities
Per background-worker.md and api-contract.md:
- Fetch and validate source URLs
- Parse microformats with mf2py
- Extract author information from h-cards
- Detect mention types (reply, like, repost, etc.)
- Sanitize content with nh3
References:
- Background Worker Design: /docs/design/v1.6.0/background-worker.md
- API Contract: /docs/design/v1.6.0/api-contract.md
- W3C Webmention: https://www.w3.org/TR/webmention/
"""
import logging
import mf2py
import nh3
import httpx
from datetime import datetime
from typing import Dict, Any, Optional
from urllib.parse import urlparse
from starpunk.webmention_ssrf import validate_url_for_fetch, SSRFBlockedError
logger = logging.getLogger(__name__)
class ValidationError(Exception):
"""Raised when webmention validation fails"""
pass
def fetch_source(url: str, site_url: str, timeout: int = 10, max_size: int = 1048576) -> tuple[str, str]:
"""
Fetch source URL content with SSRF protection.
Args:
url: Source URL to fetch
site_url: Site URL for User-Agent header
timeout: Request timeout in seconds (default: 10)
max_size: Maximum content size in bytes (default: 1MB)
Returns:
Tuple of (content, content_type)
Raises:
SSRFBlockedError: If URL points to private IP
ValidationError: If fetch fails or content too large
"""
# SSRF protection
try:
validate_url_for_fetch(url)
except (SSRFBlockedError, ValueError) as e:
logger.warning(f"SSRF protection blocked URL {url}: {e}")
raise ValidationError(f"Blocked request: {e}")
# Fetch URL
try:
# Use streaming to check size before downloading entire content
with httpx.stream(
'GET',
url,
timeout=timeout,
headers={'User-Agent': f'StarPunk/1.6.0 (+{site_url})'},
follow_redirects=True
) as response:
response.raise_for_status()
# Check content length if provided
content_length = response.headers.get('Content-Length')
if content_length and int(content_length) > max_size:
raise ValidationError(f"Source exceeds size limit ({max_size} bytes)")
# Read content with size limit
content = b''
for chunk in response.iter_bytes(chunk_size=8192):
content += chunk
if len(content) > max_size:
raise ValidationError(f"Source exceeds size limit ({max_size} bytes)")
content_type = response.headers.get('Content-Type', '')
return content.decode('utf-8', errors='replace'), content_type
except httpx.TimeoutException:
raise ValidationError("Source fetch timed out")
except httpx.HTTPStatusError as e:
if 400 <= e.response.status_code < 500:
raise ValidationError(f"Source returned {e.response.status_code}")
else:
raise ValidationError(f"Source server error: {e.response.status_code}")
except httpx.HTTPError as e:
raise ValidationError(f"Failed to fetch source: {e}")
except UnicodeDecodeError:
raise ValidationError("Source content encoding is not supported")
def verify_link_presence(content: str, target_url: str, content_type: str) -> bool:
"""
Verify that source content contains a link to target URL.
Args:
content: Source content (HTML or text)
target_url: Target URL to find
content_type: Content type of source
Returns:
True if target link found, False otherwise
"""
# Normalize URLs for comparison (remove fragments, trailing slashes)
target_normalized = urlparse(target_url)._replace(fragment='').geturl().rstrip('/')
# For HTML, parse and check all links
if 'html' in content_type.lower():
try:
from lxml import html as lxml_html
doc = lxml_html.fromstring(content)
links = doc.xpath('//a/@href')
for link in links:
# Make absolute if relative
link_normalized = urlparse(link)._replace(fragment='').geturl().rstrip('/')
if link_normalized == target_normalized:
return True
except Exception as e:
logger.debug(f"HTML parsing failed, falling back to string search: {e}")
# Fallback: simple string search
return target_normalized in content
def detect_mention_type(parsed_mf2: Dict, target_url: str) -> str:
"""
Detect mention type from microformats.
Priority: reply > like > repost > bookmark > mention
Args:
parsed_mf2: Parsed microformats data from mf2py
target_url: Target URL being mentioned
Returns:
Mention type: 'reply', 'like', 'repost', 'bookmark', or 'mention'
"""
target_normalized = urlparse(target_url)._replace(fragment='').geturl().rstrip('/')
# Find h-entry that references target
for item in parsed_mf2.get('items', []):
if 'h-entry' not in item.get('type', []):
continue
props = item.get('properties', {})
# Check in-reply-to (highest priority)
for reply_to in props.get('in-reply-to', []):
url = reply_to if isinstance(reply_to, str) else reply_to.get('value', '')
if urlparse(url)._replace(fragment='').geturl().rstrip('/') == target_normalized:
return 'reply'
# Check like-of
for like in props.get('like-of', []):
url = like if isinstance(like, str) else like.get('value', '')
if urlparse(url)._replace(fragment='').geturl().rstrip('/') == target_normalized:
return 'like'
# Check repost-of
for repost in props.get('repost-of', []):
url = repost if isinstance(repost, str) else repost.get('value', '')
if urlparse(url)._replace(fragment='').geturl().rstrip('/') == target_normalized:
return 'repost'
# Check bookmark-of
for bookmark in props.get('bookmark-of', []):
url = bookmark if isinstance(bookmark, str) else bookmark.get('value', '')
if urlparse(url)._replace(fragment='').geturl().rstrip('/') == target_normalized:
return 'bookmark'
# Default fallback
return 'mention'
def _first_str(props: Dict, name: str) -> Optional[str]:
"""
First value of an mf2 property as a string
mf2py gives u-photo with alt text as {'value': url, 'alt': ...} and nested
microformats as dicts with a 'value'; reduce those to the plain value.
"""
values = props.get(name) or [None]
value = values[0]
if isinstance(value, dict):
value = value.get('value')
return value if isinstance(value, str) and value else None
def _is_http_url(value: Optional[str]) -> bool:
"""True if value is an absolute http or https URL"""
if not value:
return False
parsed = urlparse(value.strip())
return parsed.scheme.lower() in ('http', 'https') and bool(parsed.netloc)
def extract_author(parsed_mf2: Dict, source_url: str) -> Dict[str, Optional[str]]:
"""
Extract author information from h-card.
Args:
parsed_mf2: Parsed microformats data from mf2py
source_url: Source URL (fallback for author URL)
Returns:
Dict with author_name, author_url, author_photo
"""
author_name = None
author_url = None
author_photo = None
# Find h-entry first
entry = None
for item in parsed_mf2.get('items', []):
if 'h-entry' in item.get('type', []):
entry = item
break
# Check for author property in h-entry
if entry:
author_prop = entry.get('properties', {}).get('author', [])
if author_prop:
author_data = author_prop[0]
if isinstance(author_data, dict):
# h-card object
props = author_data.get('properties', {})
author_name = _first_str(props, 'name')
author_url = _first_str(props, 'url')
author_photo = _first_str(props, 'photo')
# If no author in h-entry, find representative h-card
if not author_name:
for item in parsed_mf2.get('items', []):
if 'h-card' in item.get('type', []):
props = item.get('properties', {})
author_name = _first_str(props, 'name')
author_url = _first_str(props, 'url')
author_photo = _first_str(props, 'photo')
break
# Fallback to hostname if no author found
if not author_name:
author_name = urlparse(source_url).netloc
# Only http(s) URLs are rendered as links (blocks javascript: and data:)
if not _is_http_url(author_url):
author_url = source_url
if not _is_http_url(author_photo):
author_photo = None
return {
'author_name': author_name,
'author_url': author_url,
'author_photo': author_photo
}
def extract_content(parsed_mf2: Dict) -> Optional[str]:
"""
Extract content snippet from h-entry.
Args:
parsed_mf2: Parsed microformats data from mf2py
Returns:
Sanitized content snippet (max 500 chars) or None
"""
# Find h-entry
for item in parsed_mf2.get('items', []):
if 'h-entry' not in item.get('type', []):
continue
props = item.get('properties', {})
# Try e-content first (HTML)
content_prop = props.get('content', [])
if content_prop:
content_data = content_prop[0]
if isinstance(content_data, dict):
content = content_data.get('html', '') or content_data.get('value', '')
else:
content = content_data
if content:
# Sanitize HTML
sanitized = sanitize_content(content)
# Truncate to 500 chars
if len(sanitized) > 500:
sanitized = sanitized[:497] + '...'
return sanitized
# Try p-summary as fallback
summary = props.get('summary', [])
if summary:
content = summary[0]
if isinstance(content, dict):
content = content.get('value', '')
if content:
sanitized = sanitize_content(content)
if len(sanitized) > 500:
sanitized = sanitized[:497] + '...'
return sanitized
return None
def sanitize_content(html: str) -> str:
"""
Sanitize HTML content using nh3.
Per api-contract.md:
- Allowed tags: p, br, strong, em, b, i, a, code, pre, blockquote
- Allowed attributes: a[href, rel]
Args:
html: HTML content to sanitize
Returns:
Sanitized HTML
"""
allowed_tags = {'p', 'br', 'strong', 'em', 'b', 'i', 'a', 'code', 'pre', 'blockquote'}
allowed_attributes = {'a': {'href'}}
return nh3.clean(
html,
tags=allowed_tags,
attributes=allowed_attributes,
link_rel='nofollow noopener'
)
def process_webmention(source_url: str, target_url: str, site_url: str) -> Dict[str, Any]:
"""
Process and validate a webmention.
Args:
source_url: Source URL of the webmention
target_url: Target URL being mentioned
site_url: Site URL for User-Agent header
Returns:
Dict with validation results:
- valid: bool
- error: str (if valid=False)
- mention_type: str
- author_name: str
- author_url: str
- author_photo: str or None
- content_snippet: str or None
Raises:
ValidationError: If validation fails with specific error
"""
# Fetch source content
content, content_type = fetch_source(source_url, site_url)
# Verify target link presence
if not verify_link_presence(content, target_url, content_type):
raise ValidationError("Source does not link to target")
# Parse microformats (only for HTML)
parsed_mf2 = None
if 'html' in content_type.lower():
try:
parsed_mf2 = mf2py.parse(doc=content, url=source_url)
except Exception as e:
logger.debug(f"Microformat parsing failed for {source_url}: {e}")
# Extract data
mention_type = 'mention'
author_info = {
'author_name': urlparse(source_url).netloc,
'author_url': source_url,
'author_photo': None
}
content_snippet = None
if parsed_mf2:
mention_type = detect_mention_type(parsed_mf2, target_url)
author_info = extract_author(parsed_mf2, source_url)
content_snippet = extract_content(parsed_mf2)
return {
'valid': True,
'mention_type': mention_type,
**author_info,
'content_snippet': content_snippet
}