URL & Meta Extractor
Pricing
from $1.00 / 1,000 url extracteds
Extract the title and meta description from any URL – perfect for SEO checks, data enrichment, or quick research.
Pricing
from $1.00 / 1,000 url extracteds
Rating
0.0
(0)
Developer
Mitchel Davis
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
a day ago
Last modified
Categories
Share
storagenode_modules.venvFROM apify/actor-python:3.13
COPY requirements.txt ./
RUN echo "Python version:" \ && python --version \ && echo "Installing dependencies:" \ && pip install -r requirements.txt \ && echo "All installed Python packages:" \ && pip freeze
COPY . ./
RUN python -m compileall -q src/
CMD ["python", "-m", "src"]1apify2requests3beautifulsoup4{ "actorSpecification": 1, "name": "url-title-meta-extractor", "title": "URL & Meta Extractor", "description": "Extract the title and meta description from any URL - perfect for SEO checks, data enrichment, or quick research.", "version": "0.0", "buildTag": "latest", "meta": { "templateId": "python-empty" }, "inputSchema": "./input_schema.json", "output": "./output_schema.json", "storages": { "dataset": "./dataset_schema.json" }, "environmentVariables": {}}{ "actorSpecification": 1, "fields": {}, "views": { "overview": { "title": "Overview", "transformation": { "fields": [ "url", "title", "meta_description", "error" ] }, "display": { "component": "table", "properties": { "url": { "label": "URL", "format": "link" }, "title": { "label": "Page title", "format": "text" }, "meta_description": { "label": "Meta description", "format": "text" }, "error": { "label": "Error", "format": "text" } } } } }}{ "title": "URL & Meta Extractor Input", "type": "object", "schemaVersion": 1, "properties": { "urls": { "title": "URLs to extract", "type": "array", "description": "List of URLs to fetch. For each URL, the actor returns the page's <title> and meta description.", "editor": "requestListSources", "default": [{ "url": "https://apify.com" }], "prefill": [{ "url": "https://apify.com" }] } }, "required": ["urls"]}{ "$schema": "https://apify.com/schemas/v1/output.ide.json", "actorOutputSchemaVersion": 1, "title": "Output schema", "properties": { "results": { "type": "string", "title": "Results", "template": "{{links.apiDefaultDatasetUrl}}/items" } }}1from __future__ import annotations2
3import requests4from bs4 import BeautifulSoup5
6from apify import Actor7
8
9def extract_title_and_meta(url: str) -> dict:10 try:11 headers = {12 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '13 'AppleWebKit/537.36 (KHTML, like Gecko) '14 'Chrome/91.0.4472.124 Safari/537.36'15 }16 r = requests.get(url, headers=headers, timeout=10)17 r.raise_for_status()18 soup = BeautifulSoup(r.text, 'html.parser')19
20 title = soup.title.string if soup.title else ''21
22 meta_tag = soup.find('meta', attrs={'name': 'description'})23 if meta_tag and meta_tag.get('content'):24 meta_desc = meta_tag.get('content', '')25 else:26 meta_tag = soup.find('meta', attrs={'property': 'og:description'})27 meta_desc = meta_tag.get('content', '') if meta_tag else ''28
29 return {30 'url': url,31 'title': (title or '').strip(),32 'meta_description': (meta_desc or '').strip(),33 'error': None,34 }35 except Exception as e:36 return {37 'url': url,38 'title': None,39 'meta_description': None,40 'error': str(e),41 }42
43
44async def main() -> None:45 async with Actor:46 actor_input = await Actor.get_input() or {}47
48 urls = actor_input.get('urls')49 if not urls:50 single_url = actor_input.get('url')51 urls = [single_url] if single_url else []52
53 # Accept both plain strings and Apify's requestListSources-style54 # objects ({"url": "..."} ) so the input schema can use either editor.55 normalized_urls = []56 for item in urls:57 if isinstance(item, str):58 normalized_urls.append(item)59 elif isinstance(item, dict) and item.get('url'):60 normalized_urls.append(item['url'])61
62 if not normalized_urls:63 Actor.log.warning('No URLs provided in input. Nothing to do.')64 return65
66 for url in normalized_urls:67 Actor.log.info(f'Extracting title/meta from {url}')68 result = extract_title_and_meta(url)69 await Actor.push_data(result)70
71
72if __name__ == '__main__':73 import asyncio74 asyncio.run(main())1
1import asyncio2
3from .main import main4
5if __name__ == "__main__":6 asyncio.run(main())