1fc45ffac8
- Fixed widespread typo: `temprature` → `temperature` across LLMConfig and related files - Enhanced CSS/XPath selector guidance for more reliable LinkedIn data extraction - Added Google Colab display server support for running Crawl4AI in notebook environments - Improved browser debugging with verbose startup args logging - Updated LinkedIn schemas and HTML snippets for better parsing accuracy 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
51 lines
1.2 KiB
JSON
51 lines
1.2 KiB
JSON
{
|
|
"name": "LinkedIn Company Search Result Card",
|
|
"baseSelector": "div[data-chameleon-result-urn][data-view-name=\"search-entity-result-universal-template\"]",
|
|
"baseFields": [
|
|
{
|
|
"name": "chameleon_result_urn",
|
|
"type": "attribute",
|
|
"attribute": "data-chameleon-result-urn"
|
|
},
|
|
{
|
|
"name": "view_name",
|
|
"type": "attribute",
|
|
"attribute": "data-view-name"
|
|
}
|
|
],
|
|
"fields": [
|
|
{
|
|
"name": "handle",
|
|
"selector": "div.mb1 div.display-flex span a[data-test-app-aware-link]",
|
|
"type": "attribute",
|
|
"attribute": "href"
|
|
},
|
|
{
|
|
"name": "profile_image",
|
|
"selector": "div.ivm-image-view-model img",
|
|
"type": "attribute",
|
|
"attribute": "src"
|
|
},
|
|
{
|
|
"name": "name",
|
|
"selector": "div.mb1 div.display-flex span a[data-test-app-aware-link]",
|
|
"type": "text"
|
|
},
|
|
{
|
|
"name": "descriptor",
|
|
"selector": "div.mb1 > div[class*=\"t-14 t-black\"]",
|
|
"type": "text"
|
|
},
|
|
{
|
|
"name": "about",
|
|
"selector": "p.entity-result__summary--2-lines",
|
|
"type": "text"
|
|
},
|
|
{
|
|
"name": "followers",
|
|
"selector": "div.mb1 > div:nth-of-type(3)",
|
|
"type": "regex",
|
|
"pattern": "(\\d+[KM]?) followers"
|
|
}
|
|
]
|
|
} |