#!/bin/bash
# SEO进化知识吸收 v1.0
# 发现项目 → 分析 → 提取知识 → 优化自己的系统

CANDIDATES="/root/.openclaw/workspace/seo/evolution-candidates.md"
KNOWLEDGE="/root/.openclaw/workspace/seo/knowledge-absorbed.md"
LOG="/root/.openclaw/logs/evolution-absorb.log"

log() { echo "[$(date '%H:%M:%S')] $1" | tee -a "$LOG"; }

# 分析项目并提取知识
analyze_project() {
    local url="$1"
    local name="$2"
    local proxy="http://192.168.0.31:7890"
    local token="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"
    
    log "分析: $name"
    
    # 获取项目详情（带认证）
    local content=$(curl -s --proxy "$proxy" --max-time 20 \
        -H "Authorization: token $token" \
        "https://api.github.com/repos/$name" 2>/dev/null)
    [ -z "$content" ] && return
    
    # 提取有用信息
    local stars=$(echo "$content" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('stargazers_count','0')" 2>/dev/null || echo "0")
    local desc=$(echo "$content" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('description','')" 2>/dev/null || echo "")
    local lang=$(echo "$content" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('language','')" 2>/dev/null || echo "")
    
    log "⭐$stars $name ($lang)"
    log "  $desc"
    
    # 提取技术要点
    case "$desc" in
        *SEO*)
            log "  → SEO相关知识"
            echo "## SEO知识: $name" >> "$KNOWLEDGE"
            echo "⭐$stars $desc" >> "$KNOWLEDGE"
            echo "链接: https://github.com/$name" >> "$KNOWLEDGE"
            echo "" >> "$KNOWLEDGE"
            ;;
        *keyword*|*crawl*|*scrap*)
            log "  → 爬虫技术"
            echo "## 爬虫技术: $name" >> "$KNOWLEDGE"
            echo "⭐$stars $desc" >> "$KNOWLEDGE"
            echo "" >> "$KNOWLEDGE"
            ;;
    esac
}

# 主流程
log "=== 知识吸收开始 ==="

# 读取候选项目并分析
if [ -f "$CANDIDATES" ]; then
    while IFS= read -r line; do
        [[ "$line" =~ github.com/([^/]+/[^\s]+) ]] && analyze_project "${BASH_REMATCH[1]}" "${BASH_REMATCH[1]}"
    done < "$CANDIDATES"
fi

log "=== 知识吸收完成 ==="