Website Content Crawler
No credit card required
Website Content Crawler
No credit card required
Crawl websites and extract text content to feed AI models, LLM applications, vector databases, or RAG pipelines. The Actor supports rich formatting using Markdown, cleans the HTML, downloads files, and integrates well with 🦜🔗 LangChain, LlamaIndex, and the wider LLM ecosystem.
Do you want to learn more about this Actor?
Get a demoset the depth to 0 yet more then 900 pages are scanned
Hi, thank you for using the Website Content Crawler.
This appears to be a UX issue on our side. You’ve specified a startURLs
value and set the crawling depth to 0, but you’ve also kept the Consider URLs from Sitemaps
option enabled.
As a result, all URLs from the sitemap are being scraped, which may not be what you intended.
I understand how this can be confusing, and I’ll raise it internally for improvement.
To resolve the issue, please disable the Consider URLs from Sitemaps
option, and the crawler will work as expected. You can check my run as an example.
I hope this helps!
I’ll leave this issue open for now.
Hi, I’ve created a GitHub issue in our private repository to improve the UX when setting maxCrawlDepth
to 0.
I’ll go ahead and close this issue for now. The documentation will be updated in the next release.
Actor Metrics
4k monthly users
-
840 stars
>99% runs succeeded
1 days response time
Created in Mar 2023
Modified 21 hours ago