Skip to main content

Search Wrangles

Search wrangles, with recipe examples, parameters, and behavior.

Perform web searches to find links. Returns structured search results with titles, links, snippets, and optional pricing.

Parameters​

NameDescriptionAccepted ValuesDefaultRequired
I/O
queriesName or list of input columns containing search queries.string, array—Yes
idName of the column containing the row ID to append to each search result.string—Yes
outputOutput column for the dictionaries. If a list of 2 is provided, outputs [dicts_column, pretty_strings_column].string, array, nullnullNo
Options
n_resultsNumber of search results to return per query (default 10, max 100).integer10No
countryCountry code for search results (default 'us'). Alias: gl.string—No
languageLanguage code for search results (default 'en'). Alias: hl.string—No
locationLocation for search results (e.g., 'Austin, Texas').string—No
deviceDevice type for search results.string; one of:
  • desktop
  • mobile
  • tablet
—No
Conditions
ifCondition that determines whether the wrangle runs as a whole. Recipe variables may be referenced with ${variable}.string—No
whereFilter rows before applying the wrangle using SQL-like criteria, such as column1 = 123 OR column2 = 'abc'.string—No
where_paramsValues used with where for parameterized criteria. Uses SQLite placeholder syntax such as ? or :name.array, object—No
Execution
threadsNumber of concurrent threads for parallel processing (default 10).integer10No
Details
clientThe search provider to use.string; one of:
  • serpapi
"serpapi"No
api_keyAPI key for the search client. Can also be set as an environment variable (e.g., SERPAPI_API_KEY).string, nullnullNo

Examples​

This template searches once per query and returns structured result dictionaries. Search results vary by provider, location, and time.

wrangles:
- search.find_links:
id: Row ID
queries:
- Search Query
output:
- Search Results
api_key: Your SerpApi API key
client: serpapi
n_results: 5
Row IDSearch Query
1001SKF 6202 bearing supplier
Search Results
[{"title": "Example result", "link": "https://example.com/6202", "snippet": "SKF 6202 bearing"}]

Template based on the documented parameters; no published source example is currently available.

Access
RequirementValue
AI-poweredNo
Requires WrangleWorks accountNo
Requires subscriptionNo
Requires external API keyNo
Technical details
FieldValue
Catalog ID47
Catalog keysearch.find_links
Recipe keysearch.find_links
Catalog statusactive
Lifecycle statusactive
Recipe Writer eligibleYes
Namespacesearch
Documentation groupsearch
AliasesNone
Runtime symbolwrangles.recipe_wrangles.search.find_links
Legacy UUIDec1f661b-2cbc-4a47-88e3-646179104376

Sources


Retrieves targeted content from web pages using LLM URL extraction. Can optionally output a second column containing a clean, human-readable text summary of the retrieved data.

Parameters​

NameDescriptionAccepted ValuesDefaultRequired
I/O
inputName or list of input columns containing URLs or Scored Search Result dictionaries.string, array—Yes
outputName of the output column for the raw dictionaries. To output BOTH the raw dictionaries and the formatted text, provide a list of exactly two column names (e.g., [page_data, page_text]).string, array, nullnullNo
Options
promptOptional custom system prompt to guide the extraction behavior and output format.string, nullnullNo
Formatting
output_formatThe desired format for the extracted content.string; one of:
  • markdown
  • json
"json"No
Conditions
ifCondition that determines whether the wrangle runs as a whole. Recipe variables may be referenced with ${variable}.string—No
whereFilter rows before applying the wrangle using SQL-like criteria, such as column1 = 123 OR column2 = 'abc'.string—No
where_paramsValues used with where for parameterized criteria. Uses SQLite placeholder syntax such as ? or :name.array, object—No
Execution
threadsNumber of concurrent threads for parallel processing (default 10).integer10No
Details
clientThe retrieval provider to use.string; one of:
  • google_url_context
"google_url_context"No
api_keyAPI key for the provider. Can also be set as an environment variable (e.g., GOOGLE_API_KEY).string, nullnullNo
model_idThe specific model ID to use (default models/gemini-3-flash-preview).string"models/gemini-3-flash-preview"No

Examples​

This template extracts JSON content from a URL. Returned fields depend on the page, prompt, and retrieval model.

wrangles:
- search.retrieve_link_content:
input:
- Product URL
output:
- Page Data
api_key: Your Google API key
client: google_url_context
output_format: json
prompt: Extract the product title and manufacturer.
Page Data
{"title": "6202 Bearing", "manufacturer": "SKF"}

Template based on the documented parameters; no published source example is currently available.

Access
RequirementValue
AI-poweredNo
Requires WrangleWorks accountNo
Requires subscriptionNo
Requires external API keyNo
Technical details
FieldValue
Catalog ID48
Catalog keysearch.retrieve_link_content
Recipe keysearch.retrieve_link_content
Catalog statusactive
Lifecycle statusactive
Recipe Writer eligibleYes
Namespacesearch
Documentation groupsearch
AliasesNone
Runtime symbolwrangles.recipe_wrangles.search.retrieve_link_content
Legacy UUID3d5faa87-9e96-48c0-8226-5ae566e8d76c

Sources