import json
import logging
from xml.etree.ElementTree import Element, tostring
from xml.dom import minidom
from devplacepy.config import SITE_URL
from devplacepy.utils import strip_html
logger = logging.getLogger(__name__)
SITE_NAME = "DevPlace"
def truncate(text, max_len=160):
if not text:
return ""
text = " ".join(text.split())
if len(text) <= max_len:
return text
text = text[:max_len - 3].rsplit(" ", 1)[0]
return text + "..."
def site_url(request):
return SITE_URL or str(request.base_url).rstrip("/")
def website_schema(base_url):
return {
"@type": "WebSite",
"name": SITE_NAME,
"url": base_url,
"potentialAction": {
"@type": "SearchAction",
"target": {
"@type": "EntryPoint",
"urlTemplate": f"{base_url}/feed?search={{query}}"
},
"query-input": "required name=query"
}
}
def breadcrumb_schema(items, base_url):
return {
"@type": "BreadcrumbList",
"itemListElement": [
{
"@type": "ListItem",
"position": i + 1,
"item": {
"@id": item["url"] if item["url"].startswith("http") else f"{base_url}{item['url']}",
"name": item["name"]
}
}
for i, item in enumerate(items)
]
}
def discussion_forum_posting(post, author, comment_count, star_count, base_url):
schema = {
"@type": "DiscussionForumPosting",
"headline": post.get("title") or "Untitled",
"text": truncate(post.get("content", ""), 500),
"url": f"{base_url}/posts/{post.get('slug') or post['uid']}",
"author": {
"@type": "Person",
"name": author["username"] if author else "Unknown",
"url": f"{base_url}/profile/{author['username']}" if author else ""
},
"datePublished": post.get("created_at", ""),
"interactionStatistic": [
{"@type": "InteractionCounter", "interactionType": "https://schema.org/LikeAction", "userInteractionCount": star_count},
{"@type": "InteractionCounter", "interactionType": "https://schema.org/CommentAction", "userInteractionCount": comment_count}
]
}
return schema
def profile_page_schema(profile_user, post_count, base_url):
return {
"@type": "ProfilePage",
"mainEntity": {
"@type": "Person",
"name": profile_user.get("username", ""),
"alternateName": profile_user.get("username", ""),
"description": profile_user.get("bio", "") or f"Developer on {SITE_NAME}",
"interactionStatistic": [
{"@type": "InteractionCounter", "interactionType": "https://schema.org/WriteAction", "userInteractionCount": post_count}
]
}
}
def software_application_schema(project, base_url):
return {
"@type": "SoftwareApplication",
"name": project.get("title", "Untitled"),
"description": truncate(project.get("description", ""), 300),
"url": f"{base_url}/projects/{project.get('slug') or project['uid']}",
"applicationCategory": "DeveloperApplication",
"operatingSystem": project.get("platforms", "Cross-platform"),
"author": {
"@type": "Person",
"name": project.get("author_name", "Unknown")
},
"datePublished": project.get("created_at", ""),
"offers": {
"@type": "Offer",
"price": "0",
"priceCurrency": "USD"
}
}
def organization_schema(base_url):
return {
"@type": "Organization",
"name": SITE_NAME,
"url": base_url,
"logo": f"{base_url}{DEFAULT_OG_IMAGE}",
}
def news_article_schema(article, base_url, image_url=""):
url = f"{base_url}/news/{article.get('slug') or article['uid']}"
schema = {
"@type": "NewsArticle",
"headline": (article.get("title") or "Untitled")[:110],
"description": truncate(strip_html(article.get("description", "") or ""), 200),
"url": url,
"datePublished": article.get("synced_at", "") or article.get("created_at", ""),
"mainEntityOfPage": {"@type": "WebPage", "@id": url},
"author": {"@type": "Organization", "name": article.get("source_name") or SITE_NAME},
"publisher": organization_schema(base_url),
}
if image_url:
schema["image"] = image_url
return schema
def software_source_code_schema(gist, base_url):
return {
"@type": "SoftwareSourceCode",
"name": gist.get("title") or "Gist",
"description": truncate(strip_html(gist.get("description", "") or ""), 200),
"url": f"{base_url}/gists/{gist.get('slug') or gist['uid']}",
"programmingLanguage": gist.get("language", "") or "text",
"dateCreated": gist.get("created_at", ""),
}
def combine(schemas):
if not schemas:
return None
cleaned = []
for s in schemas:
if s is not None:
s.pop("@context", None)
cleaned.append(s)
if not cleaned:
return None
if len(cleaned) == 1:
return json.dumps({"@context": "https://schema.org", **cleaned[0]}, ensure_ascii=False)
return json.dumps({"@context": "https://schema.org", "@graph": cleaned}, ensure_ascii=False)
DEFAULT_OG_IMAGE = "/static/og-default.png"
def base_seo_context(request, title="", description="", robots="index,follow", og_type="website", og_image=None, breadcrumbs=None, schemas=None):
base = site_url(request)
page_title = f"{title} - {SITE_NAME}" if title else SITE_NAME
canonical = f"{base}{request.url.path}"
page = request.query_params.get("page")
if page and page not in ("", "1"):
canonical = f"{canonical}?page={page}"
clean_description = truncate(strip_html(description), 160)
og_img = og_image or f"{base}{DEFAULT_OG_IMAGE}"
return {
"page_title": page_title,
"meta_description": clean_description,
"meta_robots": robots,
"canonical_url": canonical,
"og_title": title or SITE_NAME,
"og_description": clean_description,
"og_image": og_img,
"og_type": og_type,
"breadcrumbs": breadcrumbs or [],
"page_schema": combine(schemas or []),
}
def make_sitemap(base_url):
from devplacepy.database import get_table, db
def url_element(loc, lastmod=None, changefreq=None, priority=None):
u = Element("url")
loc_el = Element("loc")
loc_el.text = loc
u.append(loc_el)
if lastmod:
lm = Element("lastmod")
lm.text = lastmod
u.append(lm)
if changefreq:
cf = Element("changefreq")
cf.text = changefreq
u.append(cf)
if priority is not None:
pr = Element("priority")
pr.text = str(priority)
u.append(pr)
return u
urlset = Element("urlset")
urlset.set("xmlns", "http://www.sitemaps.org/schemas/sitemap/0.9")
urlset.append(url_element(f"{base_url}/", changefreq="daily", priority="1.0"))
urlset.append(url_element(f"{base_url}/feed", changefreq="hourly", priority="0.9"))
urlset.append(url_element(f"{base_url}/news", changefreq="hourly", priority="0.9"))
urlset.append(url_element(f"{base_url}/projects", changefreq="daily", priority="0.8"))
urlset.append(url_element(f"{base_url}/gists", changefreq="daily", priority="0.8"))
if "posts" in db.tables:
posts = list(get_table("posts").find(order_by=["-created_at"], _limit=500))
for p in posts:
urlset.append(url_element(
f"{base_url}/posts/{p.get('slug') or p['uid']}",
lastmod=p.get("created_at", ""),
changefreq="weekly",
priority="0.7"
))
if "projects" in db.tables:
projects = list(get_table("projects").find(order_by=["-created_at"], _limit=1000))
for p in projects:
urlset.append(url_element(
f"{base_url}/projects/{p.get('slug') or p['uid']}",
lastmod=p.get("created_at", ""),
changefreq="weekly",
priority="0.6"
))
if "gists" in db.tables:
gists = list(get_table("gists").find(order_by=["-created_at"], _limit=500))
for g in gists:
urlset.append(url_element(
f"{base_url}/gists/{g.get('slug') or g['uid']}",
lastmod=g.get("created_at", ""),
changefreq="weekly",
priority="0.6"
))
if "news" in db.tables:
articles = list(get_table("news").find(status="published", order_by=["-synced_at"], _limit=500))
for a in articles:
urlset.append(url_element(
f"{base_url}/news/{a.get('slug') or a['uid']}",
lastmod=a.get("synced_at", "") or a.get("created_at", ""),
changefreq="weekly",
priority="0.7"
))
if "users" in db.tables:
post_counts = {}
if "posts" in db.tables:
for row in db.query("SELECT user_uid, COUNT(*) AS c FROM posts GROUP BY user_uid"):
post_counts[row["user_uid"]] = row["c"]
users = list(get_table("users").find(order_by=["-created_at"], _limit=200))
for u in users:
if post_counts.get(u["uid"], 0) < 2:
continue
urlset.append(url_element(
f"{base_url}/profile/{u['username']}",
lastmod=u.get("created_at", ""),
changefreq="weekly",
priority="0.4"
))
rough = tostring(urlset, encoding="unicode")
dom = minidom.parseString(rough)
return dom.toprettyxml(indent=" ")
Reference in New Issue View Git Blame Copy Permalink