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>
41 lines
1.1 KiB
JSON
41 lines
1.1 KiB
JSON
{
|
|
"name": "LinkedIn People Profile Card",
|
|
"baseSelector": "li.org-people-profile-card__profile-card-spacing",
|
|
"baseFields": [],
|
|
"fields": [
|
|
{
|
|
"name": "profile_url",
|
|
"selector": "div.artdeco-entity-lockup__title a[data-test-app-aware-link]",
|
|
"type": "attribute",
|
|
"attribute": "href"
|
|
},
|
|
{
|
|
"name": "avatar_url",
|
|
"selector": "div.artdeco-entity-lockup__image img",
|
|
"type": "attribute",
|
|
"attribute": "src"
|
|
},
|
|
{
|
|
"name": "name",
|
|
"selector": "div.artdeco-entity-lockup__title a div.lt-line-clamp--single-line",
|
|
"type": "text"
|
|
},
|
|
{
|
|
"name": "headline",
|
|
"selector": "div.artdeco-entity-lockup__subtitle div.lt-line-clamp--multi-line",
|
|
"type": "text"
|
|
},
|
|
{
|
|
"name": "followers",
|
|
"selector": "span.text-align-center span.lt-line-clamp--multi-line",
|
|
"type": "regex",
|
|
"pattern": "(\\d+)"
|
|
},
|
|
{
|
|
"name": "connection_degree",
|
|
"selector": "span.artdeco-entity-lockup__degree",
|
|
"type": "regex",
|
|
"pattern": "(\\d+\\w+)"
|
|
}
|
|
]
|
|
} |