Search ERIC education research papers.
Searches ERIC, the US Education Resources Information Center, like its results page: title, link to the record, source (authors, journal or report, year) and the abstract excerpt of each hit. Returns the first results page only (about 15 records). Returns an empty list when nothing matches.
- Site
- ERIC, United States
- Version
- v1
- Runs, last 7 days
- No reports yet
- sha256
- fb22df3c3865…
Run it with your agent
after installing WieldAsk in plain words. Your agent finds this recipe and calls it:
“Search ERIC education research papers.”
Read-only: it changes nothing on the site. No login needed.
{ "tool": "run", "arguments": { "recipe_id": "eric.ed.gov/search-papers", "params": { "query": "mathematics" } } }
Requests
sent from your browser, in order- 1GET/?qServer-rendered results page /?q=...; read-only GET. Each record is div.r_i with its title link in div.r_t, source line in div.r_a and abstract excerpt in div.r_d. The record's id attribute (r_EJ..., r_ED...) names the record.
Parameters
from your agentReturns
to your agentWhere it can send
- eric.ed.gov
Anything else is blocked by the extension.
Reads from your session
Nothing. Your browser attaches the site's cookies by itself.
Used only in requests to the addresses on the left. Never sent to wield.run or your agent.
Checks
a run passes when- length(output.records) > `0`
- length(output.records[?starts_with(url, 'https://eric.ed.gov/?id=')]) == length(output.records)
- length(output.records[?title != `null`]) == length(output.records)
Raw recipe
Served as canonical JSON from /api/v1/recipes/eric.ed.gov/search-papers, so its sha256 matches the ETag and the index.
curl -s https://wield.run/api/v1/recipes/eric.ed.gov/search-papers | shasum -a 256 # fb22df3c3865e68f4e97070b4e0677144fa2b8a8ff4cf0c13e03b0553c23e846
{ "description": "Searches ERIC, the US Education Resources Information Center, like its results page: title, link to the record, source (authors, journal or report, year) and the abstract excerpt of each hit. Returns the first results page only (about 15 records). Returns an empty list when nothing matches.", "effect": "read", "id": "eric.ed.gov/search-papers", "keywords": [ "eric", "eric.ed.gov", "education", "bildung", "research", "papers", "journal articles", "pädagogik", "mathematics", "reading", "stem", "teaching", "science education", "education research" ], "output": { "schema": { "properties": { "query": { "type": "string" }, "records": { "items": { "properties": { "abstract": { "description": "Abstract excerpt, may be cut off", "type": [ "string", "null" ] }, "source": { "description": "Authors, then journal or report and year", "type": [ "string", "null" ] }, "title": { "type": "string" }, "url": { "type": "string" } }, "required": [ "title", "url" ], "type": "object" }, "type": "array" } }, "required": [ "query", "records" ], "type": "object" }, "value": "{query: params.query, records: steps.search.records[?title != `null` && id != `null`].{title: title, url: join('', ['https://eric.ed.gov/?id=', split(id, '_')[1]]), source: source, abstract: abstract}}" }, "params": { "additionalProperties": false, "properties": { "query": { "description": "Topic to search ERIC for, e.g. 'mathematics', 'reading comprehension', 'STEM'", "maxLength": 100, "minLength": 2, "type": "string" } }, "required": [ "query" ], "type": "object" }, "provenance": { "method": "har", "notes": "GET /?q=<query> returns the server-rendered ERIC results page with one div.r_i per record. Title, source line and abstract excerpt come from div.r_t, div.r_a and div.r_d. The record URL is built from the div id (r_EJ...) as /?id=EJ..., the canonical record page, rather than the href, which carries the search terms. Facet and filter controls are not read.", "recorded_at": "2026-11-08T16:55:00.000Z", "recorded_by": "wield-forge (claude-haiku agent)" }, "requires_login": false, "schema": "https://wield.run/schema/recipe/v1.json", "site": { "country": "US", "id": "eric.ed.gov", "language": "en", "name": "ERIC", "origin": "https://eric.ed.gov", "origins": [ "https://eric.ed.gov" ] }, "steps": [ { "description": "Server-rendered results page /?q=...; read-only GET. Each record is div.r_i with its title link in div.r_t, source line in div.r_a and abstract excerpt in div.r_d. The record's id attribute (r_EJ..., r_ED...) names the record.", "expect": { "content_type": "html", "status": [ 200 ] }, "extract": { "html_items": { "records": { "fields": { "abstract": { "selector": "div.r_d" }, "id": { "attr": "id", "selector": ":scope" }, "source": { "selector": "div.r_a" }, "title": { "selector": "div.r_t a" } }, "max": 50, "selector": "div.r_i" } } }, "id": "search", "request": { "headers": { "Accept": "text/html" }, "method": "GET", "query": { "q": "{{params.query}}" }, "url": "/" } } ], "task": "Search ERIC education research papers", "tos": { "notes": "Not reviewed. One search page per call, the same page a visitor loads. The site's terms on automated access were not checked.", "reviewed": false }, "verify": { "checks": [ "length(output.records) > `0`", "length(output.records[?starts_with(url, 'https://eric.ed.gov/?id=')]) == length(output.records)", "length(output.records[?title != `null`]) == length(output.records)" ], "example_params": { "query": "mathematics" }, "max_ms": 5000 }, "version": 1 }