Fix temperature typo and enhance LinkedIn extraction with Colab support

- 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>
This commit is contained in:
UncleCode
2025-05-25 16:47:12 +08:00
parent 9c2cc7f73c
commit 1fc45ffac8
15 changed files with 355 additions and 136 deletions

View File

@@ -1,39 +1,51 @@
{
"name": "LinkedIn Company Card",
"baseSelector": "div.search-results-container ul[role='list'] > li",
"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": "a[href*='/company/']",
"selector": "div.mb1 div.display-flex span a[data-test-app-aware-link]",
"type": "attribute",
"attribute": "href"
},
{
"name": "profile_image",
"selector": "a[href*='/company/'] img",
"selector": "div.ivm-image-view-model img",
"type": "attribute",
"attribute": "src"
},
{
"name": "name",
"selector": "span[class*='t-16'] a",
"selector": "div.mb1 div.display-flex span a[data-test-app-aware-link]",
"type": "text"
},
{
"name": "descriptor",
"selector": "div[class*='t-black t-normal']",
"selector": "div.mb1 > div[class*=\"t-14 t-black\"]",
"type": "text"
},
{
"name": "about",
"selector": "p[class*='entity-result__summary--2-lines']",
"selector": "p.entity-result__summary--2-lines",
"type": "text"
},
{
"name": "followers",
"selector": "div:contains('followers')",
"selector": "div.mb1 > div:nth-of-type(3)",
"type": "regex",
"pattern": "(\\d+)\\s*followers"
"pattern": "(\\d+[KM]?) followers"
}
]
}

View File

@@ -1,38 +1,41 @@
{
"name": "LinkedIn People Card",
"name": "LinkedIn People Profile Card",
"baseSelector": "li.org-people-profile-card__profile-card-spacing",
"baseFields": [],
"fields": [
{
"name": "profile_url",
"selector": "a.eETATgYTipaVsmrBChiBJJvFsdPhNpulhPZUVLHLo",
"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": ".artdeco-entity-lockup__title .lt-line-clamp--single-line",
"selector": "div.artdeco-entity-lockup__title a div.lt-line-clamp--single-line",
"type": "text"
},
{
"name": "headline",
"selector": ".artdeco-entity-lockup__subtitle .lt-line-clamp--multi-line",
"selector": "div.artdeco-entity-lockup__subtitle div.lt-line-clamp--multi-line",
"type": "text"
},
{
"name": "followers",
"selector": ".lt-line-clamp--multi-line.t-12",
"type": "text"
"selector": "span.text-align-center span.lt-line-clamp--multi-line",
"type": "regex",
"pattern": "(\\d+)"
},
{
"name": "connection_degree",
"selector": ".artdeco-entity-lockup__badge .artdeco-entity-lockup__degree",
"type": "text"
},
{
"name": "avatar_url",
"selector": ".artdeco-entity-lockup__image img",
"type": "attribute",
"attribute": "src"
"selector": "span.artdeco-entity-lockup__degree",
"type": "regex",
"pattern": "(\\d+\\w+)"
}
]
}