@tydung26/product-kit 1.4.0 → 1.5.0

package/skills/market-intel/scripts/search-product-hunt.py

@@ -0,0 +1,194 @@
+#!/usr/bin/env python3
+"""Product Hunt crawler via HTML scraping + __NEXT_DATA__ extraction. Zero deps.
+Usage: python3 search-product-hunt.py "<keywords>" [limit]
+Output: JSON CrawlResult to stdout
+"""
+
+import json
+import re
+import sys
+import urllib.request
+import urllib.parse
+from datetime import datetime, timezone
+
+
+def safe_fetch(url, timeout=10):
+    """Fetch URL with timeout and user-agent header."""
+    req = urllib.request.Request(url, headers={
+        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) "
+                       "AppleWebKit/537.36 (KHTML, like Gecko) "
+                       "Chrome/120.0.0.0 Safari/537.36",
+        "Accept-Language": "en-US,en;q=0.9",
+    })
+    return urllib.request.urlopen(req, timeout=timeout).read().decode("utf-8", errors="replace")
+
+
+def truncate(text, max_len=500):
+    return text[:max_len] + "..." if len(text) > max_len else text
+
+
+def extract_next_data(html):
+    """Extract __NEXT_DATA__ JSON from a Next.js page."""
+    match = re.search(r'<script\s+id="__NEXT_DATA__"[^>]*>(.*?)</script>', html, re.DOTALL)
+    if not match:
+        return None
+    try:
+        return json.loads(match.group(1))
+    except (json.JSONDecodeError, ValueError):
+        return None
+
+
+def deep_find_posts(obj, depth=0, max_depth=8):
+    """Recursively find post-like objects in nested data."""
+    if depth > max_depth or not isinstance(obj, (dict, list)):
+        return []
+
+    posts = []
+    if isinstance(obj, list):
+        for item in obj:
+            posts.extend(deep_find_posts(item, depth + 1, max_depth))
+        return posts
+
+    # Check if this dict looks like a post
+    if "slug" in obj and "name" in obj and isinstance(obj.get("name"), str):
+        posts.append(obj)
+
+    for value in obj.values():
+        if isinstance(value, (dict, list)):
+            posts.extend(deep_find_posts(value, depth + 1, max_depth))
+
+    return posts
+
+
+def extract_post_urls(html):
+    """Extract product post URLs from search results."""
+    urls = []
+    seen = set()
+    for match in re.finditer(r'href="(/posts/[^"?#]+)"', html):
+        path = match.group(1)
+        if path not in seen:
+            seen.add(path)
+            urls.append(f"https://www.producthunt.com{path}")
+    return urls
+
+
+def extract_post_from_page(html, url):
+    """Extract product details from a Product Hunt post page."""
+    next_data = extract_next_data(html)
+
+    if next_data:
+        # Search for post object in __NEXT_DATA__
+        posts = deep_find_posts(next_data)
+        for post in posts:
+            name = post.get("name", "")
+            if not name:
+                continue
+
+            tagline = post.get("tagline", "")
+            description = post.get("description", "") or tagline
+            votes = post.get("votesCount", 0)
+            rating = post.get("reviewsRating")
+            review_count = post.get("reviewsCount") or votes
+            topics = [t.get("name", "") for t in post.get("topics", []) if isinstance(t, dict)]
+
+            return {
+                "name": name,
+                "url": url,
+                "description": truncate(description),
+                "tagline": tagline or None,
+                "rating": round(float(rating), 1) if rating else None,
+                "reviewCount": review_count or None,
+                "pricing": {"free": True, "other": post.get("pricing")},
+                "features": [t for t in topics[:5] if t],
+                "reviews": [],
+            }
+
+    # Fallback: meta tags
+    name_match = re.search(r'<meta\s+property="og:title"\s+content="([^"]*)"', html)
+    desc_match = re.search(r'<meta\s+property="og:description"\s+content="([^"]*)"', html)
+    name = name_match.group(1).replace(" | Product Hunt", "") if name_match else ""
+    description = desc_match.group(1) if desc_match else ""
+
+    if not name:
+        return None
+
+    return {
+        "name": name,
+        "url": url,
+        "description": truncate(description),
+        "tagline": None,
+        "pricing": {"free": True},
+        "features": [],
+        "reviews": [],
+    }
+
+
+def main():
+    if len(sys.argv) < 2:
+        print(json.dumps({"error": "Usage: python3 search-product-hunt.py <keywords> [limit]"}))
+        sys.exit(1)
+
+    query = sys.argv[1]
+    limit = 5
+    if len(sys.argv) >= 3:
+        try:
+            limit = max(1, min(int(sys.argv[2]), 10))
+        except ValueError:
+            limit = 5
+
+    errors = []
+    search_url = f"https://www.producthunt.com/search?q={urllib.parse.quote(query)}"
+
+    try:
+        search_html = safe_fetch(search_url)
+    except Exception as e:
+        print(json.dumps({
+            "platform": "product_hunt", "query": query,
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "results": [], "errors": [f"Product Hunt search error: {e}"],
+        }, indent=2))
+        return
+
+    # Try to get post URLs from search page
+    post_urls = extract_post_urls(search_html)[:limit]
+
+    # Fallback: extract from __NEXT_DATA__ on search page
+    if not post_urls:
+        next_data = extract_next_data(search_html)
+        if next_data:
+            posts = deep_find_posts(next_data)
+            post_urls = [
+                f"https://www.producthunt.com/posts/{p['slug']}"
+                for p in posts[:limit] if p.get("slug")
+            ]
+
+    if not post_urls:
+        errors.append("No post URLs found — page may require JS rendering")
+        print(json.dumps({
+            "platform": "product_hunt", "query": query,
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "results": [], "errors": errors,
+        }, indent=2))
+        return
+
+    results = []
+    for url in post_urls:
+        try:
+            page_html = safe_fetch(url)
+            entry = extract_post_from_page(page_html, url)
+            if entry:
+                results.append(entry)
+        except Exception as e:
+            errors.append(f"Error fetching {url}: {e}")
+
+    print(json.dumps({
+        "platform": "product_hunt",
+        "query": query,
+        "timestamp": datetime.now(timezone.utc).isoformat(),
+        "results": results,
+        "errors": errors,
+    }, indent=2))
+
+
+if __name__ == "__main__":
+    main()

package/skills/market-intel/scripts/search-yc-launch.py

@@ -0,0 +1,160 @@
+#!/usr/bin/env python3
+"""YC Launch (Y Combinator) crawler via HTML scraping. Zero external dependencies.
+Usage: python3 search-yc-launch.py "<keywords>" [limit]
+Output: JSON CrawlResult to stdout
+"""
+
+import json
+import re
+import sys
+import urllib.request
+import urllib.parse
+from datetime import datetime, timezone
+
+
+def safe_fetch(url, timeout=10):
+    """Fetch URL with timeout and user-agent header."""
+    req = urllib.request.Request(url, headers={
+        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) "
+                       "AppleWebKit/537.36 (KHTML, like Gecko) "
+                       "Chrome/120.0.0.0 Safari/537.36",
+        "Accept-Language": "en-US,en;q=0.9",
+    })
+    return urllib.request.urlopen(req, timeout=timeout).read().decode("utf-8", errors="replace")
+
+
+def truncate(text, max_len=500):
+    return text[:max_len] + "..." if len(text) > max_len else text
+
+
+def extract_launch_urls(html):
+    """Extract launch URLs from YC launches page."""
+    urls = []
+    seen = set()
+    for match in re.finditer(r'href="(/launches/[^"?#]+)"', html):
+        path = match.group(1)
+        if path not in seen:
+            seen.add(path)
+            urls.append(f"https://www.ycombinator.com{path}")
+    return urls
+
+
+def extract_launch_from_page(html, url):
+    """Extract launch details from a YC launch page."""
+    # Try JSON-LD
+    ld_match = re.search(
+        r'<script[^>]*type="application/ld\+json"[^>]*>(.*?)</script>',
+        html, re.DOTALL
+    )
+    name = ""
+    description = ""
+
+    if ld_match:
+        try:
+            data = json.loads(ld_match.group(1))
+            name = data.get("name", "")
+            description = data.get("description", "")
+        except (json.JSONDecodeError, ValueError):
+            pass
+
+    # Fallback: meta tags
+    if not name:
+        m = re.search(r'<meta\s+property="og:title"\s+content="([^"]*)"', html)
+        if m:
+            name = m.group(1).replace(" | Y Combinator", "").replace("Launch YC: ", "")
+
+    if not description:
+        m = re.search(r'<meta\s+property="og:description"\s+content="([^"]*)"', html)
+        if not m:
+            m = re.search(r'<meta\s+name="description"\s+content="([^"]*)"', html)
+        if m:
+            description = m.group(1)
+
+    if not name:
+        # Try h1 tag
+        m = re.search(r'<h1[^>]*>([^<]+)</h1>', html)
+        if m:
+            name = m.group(1).strip()
+
+    if not name:
+        return None
+
+    # Try to extract longer pitch from page body
+    pitch = ""
+    # Look for main content paragraphs
+    for m in re.finditer(r'<p[^>]*>([^<]{50,})</p>', html):
+        candidate = m.group(1).strip()
+        if len(candidate) > len(pitch):
+            pitch = candidate
+
+    return {
+        "name": name,
+        "url": url,
+        "description": truncate(pitch or description),
+        "tagline": description[:150] if len(description) < 150 else None,
+        "rating": None,
+        "reviewCount": None,
+        "pricing": {"free": True, "other": None},
+        "features": [],
+        "reviews": [],
+    }
+
+
+def main():
+    if len(sys.argv) < 2:
+        print(json.dumps({"error": "Usage: python3 search-yc-launch.py <keywords> [limit]"}))
+        sys.exit(1)
+
+    query = sys.argv[1]
+    limit = 5
+    if len(sys.argv) >= 3:
+        try:
+            limit = max(1, min(int(sys.argv[2]), 10))
+        except ValueError:
+            limit = 5
+
+    errors = []
+    search_url = f"https://www.ycombinator.com/launches?q={urllib.parse.quote(query)}"
+
+    try:
+        search_html = safe_fetch(search_url)
+    except Exception as e:
+        print(json.dumps({
+            "platform": "yc_launch", "query": query,
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "results": [], "errors": [f"YC launches error: {e}"],
+        }, indent=2))
+        return
+
+    launch_urls = extract_launch_urls(search_html)[:limit]
+
+    if not launch_urls:
+        errors.append("No launch URLs found — page may require JS rendering")
+        print(json.dumps({
+            "platform": "yc_launch", "query": query,
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "results": [], "errors": errors,
+        }, indent=2))
+        return
+
+    results = []
+    for url in launch_urls:
+        try:
+            page_html = safe_fetch(url)
+            entry = extract_launch_from_page(page_html, url)
+            if entry:
+                results.append(entry)
+        except Exception as e:
+            errors.append(f"Error fetching {url}: {e}")
+
+    print(json.dumps({
+        "platform": "yc_launch",
+        "query": query,
+        "timestamp": datetime.now(timezone.utc).isoformat(),
+        "results": results,
+        "errors": errors,
+    }, indent=2))
+
+
+if __name__ == "__main__":
+    main()

package/dist/commands/config/index.d.ts

@@ -1,3 +0,0 @@
-import type { CAC } from 'cac';
-export declare function registerConfig(cli: CAC): void;
-//# sourceMappingURL=index.d.ts.map

package/dist/commands/config/index.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/commands/config/index.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,GAAG,EAAE,MAAM,KAAK,CAAC;AAI/B,wBAAgB,cAAc,CAAC,GAAG,EAAE,GAAG,QA2BtC"}

package/dist/commands/config/index.js

@@ -1,34 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.registerConfig = registerConfig;
-const config_1 = require("../../domains/config");
-const logger_1 = require("../../shared/logger");
-function registerConfig(cli) {
-    // pkit config → show current config
-    cli
-        .command('config', 'View or set pkit configuration')
-        .action(() => {
-        const config = (0, config_1.getConfig)();
-        logger_1.log.plain('\npkit configuration\n');
-        logger_1.log.plain(`  defaultScope         ${config.defaultScope}`);
-        logger_1.log.plain(`  toolPaths.claude     ${config.toolPaths.claude}`);
-        logger_1.log.plain(`  toolPaths.antigravity  ${config.toolPaths.antigravity}`);
-        logger_1.log.plain(`  toolPaths.opencode   ${config.toolPaths.opencode}`);
-        logger_1.log.plain('\nChange with: pkit config set <key> <value>');
-        logger_1.log.plain('Keys: defaultScope, toolPaths.claude, toolPaths.antigravity, toolPaths.opencode');
-    });
-    // pkit config set <key> <value>
-    cli
-        .command('config set <key> <value>', 'Set a configuration value')
-        .action((key, value) => {
-        try {
-            (0, config_1.setConfigValue)(key, value);
-            logger_1.log.success(`Set ${key} = ${value}`);
-        }
-        catch (err) {
-            logger_1.log.error(err instanceof Error ? err.message : String(err));
-            process.exit(1);
-        }
-    });
-}
-//# sourceMappingURL=index.js.map

package/dist/commands/config/index.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/commands/config/index.ts"],"names":[],"mappings":";;AAIA,wCA2BC;AA9BD,iDAAiE;AACjE,gDAA0C;AAE1C,SAAgB,cAAc,CAAC,GAAQ;IACrC,oCAAoC;IACpC,GAAG;SACA,OAAO,CAAC,QAAQ,EAAE,gCAAgC,CAAC;SACnD,MAAM,CAAC,GAAG,EAAE;QACX,MAAM,MAAM,GAAG,IAAA,kBAAS,GAAE,CAAC;QAC3B,YAAG,CAAC,KAAK,CAAC,wBAAwB,CAAC,CAAC;QACpC,YAAG,CAAC,KAAK,CAAC,0BAA0B,MAAM,CAAC,YAAY,EAAE,CAAC,CAAC;QAC3D,YAAG,CAAC,KAAK,CAAC,0BAA0B,MAAM,CAAC,SAAS,CAAC,MAAM,EAAE,CAAC,CAAC;QAC/D,YAAG,CAAC,KAAK,CAAC,4BAA4B,MAAM,CAAC,SAAS,CAAC,WAAW,EAAE,CAAC,CAAC;QACtE,YAAG,CAAC,KAAK,CAAC,0BAA0B,MAAM,CAAC,SAAS,CAAC,QAAQ,EAAE,CAAC,CAAC;QACjE,YAAG,CAAC,KAAK,CAAC,8CAA8C,CAAC,CAAC;QAC1D,YAAG,CAAC,KAAK,CAAC,iFAAiF,CAAC,CAAC;IAC/F,CAAC,CAAC,CAAC;IAEL,gCAAgC;IAChC,GAAG;SACA,OAAO,CAAC,0BAA0B,EAAE,2BAA2B,CAAC;SAChE,MAAM,CAAC,CAAC,GAAW,EAAE,KAAa,EAAE,EAAE;QACrC,IAAI,CAAC;YACH,IAAA,uBAAc,EAAC,GAAG,EAAE,KAAK,CAAC,CAAC;YAC3B,YAAG,CAAC,OAAO,CAAC,OAAO,GAAG,MAAM,KAAK,EAAE,CAAC,CAAC;QACvC,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,YAAG,CAAC,KAAK,CAAC,GAAG,YAAY,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC;YAC5D,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QAClB,CAAC;IACH,CAAC,CAAC,CAAC;AACP,CAAC"}