
Website Content Crawler
Pricing
Pay per usage

Website Content Crawler
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.
4.6 (38)
Pricing
Pay per usage
1247
Total users
46.8k
Monthly users
6.6k
Runs succeeded
>99%
Response time
4.9 days
Last modified
11 hours ago
Large number of requests fail
Open
Hello, lately many requests from runs with the 'cheerio' crawler time out. I am not sure how that is supposed to happen, as the crawler should dynamically update the number of requests and the website does not block the requests (to my understanding). Is there some misconfiguration on my side? I am ok with the run taking some time, it is more important that the requests don't time out, without setting some especially high value. In a test run, I increased the memory and time out duration and it crawled more pages, but still far from all, which surprises me. Any guidance would be very helpful. Thank you.