Crawlora-org News media research
Search and read public news coverage from BBC, CNN, and The Guardian as normalized JSON, with outlet-native article, headline, live-story, and topic surfaces.
When to use this skill
- Get the latest headlines for a section or topic.
- Search an outlet for a story or article.
- Read an article's public body and metadata.
- Inspect a CNN or BBC live-story update stream.
- Browse Guardian topic or section archives.
Setup
- Get a Crawlora API key at crawlora.net.
- Set
CRAWLORA_API_KEYin the environment before running the helper. - The helper reads
CRAWLORA_API_KEYfrom the environment and sends requests tohttps://api.crawlora.net/api/v1.
How it works
- BBC: use
/bbc/headlines,/bbc/search, and/bbc/article; use/bbc/livefor a canonical live page. - CNN: use
/cnn/headlinesand/cnn/article; use/cnn/live-storyfor chronological live updates. - Guardian: use
/guardian/headlines,/guardian/article, and/guardian/topicfor archives.
Use reference/endpoints.md for exact parameters.
Example
scripts/crawlora.sh /bbc/headlines section=world | jq '.'
scripts/crawlora.sh /cnn/article url="https://www.cnn.com/example" | jq '.'
scripts/crawlora.sh /guardian/topic topic=technology page=1 | jq '.'