Fetch JTWC Products #87
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Fetch JTWC Products | |
| # 触发条件：每10分钟自动运行，且允许手动触发 | |
| on: | |
| schedule: | |
| - cron: '*/10 * * * *' # 每10分钟运行一次 | |
| workflow_dispatch: # 允许手动触发 | |
| jobs: | |
| fetch-and-commit: | |
| runs-on: ubuntu-latest | |
| steps: | |
| # 检出代码仓库 | |
| - name: Checkout repository | |
| uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 # 确保获取所有分支历史 | |
| # 切换到pgtw分支，如果不存在则创建 | |
| - name: Switch to pgtw branch or create it | |
| run: | | |
| if git ls-remote --heads origin pgtw | grep -q pgtw; then | |
| echo "Remote branch pgtw exists" | |
| if git rev-parse --verify pgtw 2>/dev/null; then | |
| git checkout pgtw | |
| else | |
| git checkout -b pgtw origin/pgtw | |
| fi | |
| git pull origin pgtw | |
| else | |
| echo "Branch pgtw does not exist remotely, creating new local branch" | |
| git checkout --orphan pgtw | |
| git rm -rf . 2>/dev/null || true | |
| fi | |
| # 步骤1：从natyphoon获取最近3天活跃的台风系统 | |
| - name: Fetch active systems from natyphoon | |
| run: | | |
| echo "==========================================" | |
| echo " Step 1: Fetch active typhoon list" | |
| echo "==========================================" | |
| # 下载natyphoon目录页 | |
| curl -o natyphoon_index.html "https://www.natyphoon.top/atcf/temp/?C=M;O=A" | |
| echo "=== natyphoon page size: $(wc -c < natyphoon_index.html) bytes ===" | |
| # 计算3天前的日期 (格式: YYYY/MM/DD) | |
| CUTOFF_DATE=$(date -u -d '3 days ago' +'%Y/%m/%d') | |
| echo "=== Cutoff date: $CUTOFF_DATE ===" | |
| # 提取所有 b{region}{num}{year}.dat 文件行，包含文件名和日期 | |
| # 页面格式示例: <a href="bwp902026.dat">bwp902026.dat</a> 2026/04/08 10:45 1.2K | |
| echo "" | |
| echo "=== All .dat files found ===" | |
| grep -oP 'href="(b[a-z]{2}\d{2,3}\d{4}\.dat)"[^>]*>[^<]*</a>\s+\d{4}/\d{2}/\d{2}\s+\d{2}:\d{2}' natyphoon_index.html || echo "(no matches with date pattern)" | |
| echo "" | |
| echo "=== Filtering files updated in last 3 days (since $CUTOFF_DATE) ===" | |
| # 提取文件名和修改日期，筛选最近3天的 | |
| ACTIVE_FILES="" | |
| while IFS= read -r line; do | |
| # 提取文件名 | |
| FNAME=$(echo "$line" | grep -oP 'b[a-z]{2}\d{2,3}\d{4}\.dat' | head -1) | |
| # 提取日期 | |
| FDATE=$(echo "$line" | grep -oP '\d{4}/\d{2}/\d{2}' | head -1) | |
| if [ -n "$FNAME" ] && [ -n "$FDATE" ]; then | |
| # 比较日期（字符串比较即可，YYYY/MM/DD格式天然有序） | |
| if [ "$FDATE" \>= "$CUTOFF_DATE" ] || [ "$FDATE" = "$CUTOFF_DATE" ]; then | |
| echo " ACTIVE: $FNAME (last modified: $FDATE)" | |
| ACTIVE_FILES="$ACTIVE_FILES $FNAME" | |
| fi | |
| fi | |
| done < <(grep -P 'b[a-z]{2}\d{2,3}\d{4}\.dat' natyphoon_index.html) | |
| if [ -z "$ACTIVE_FILES" ]; then | |
| echo "No active systems found in last 3 days." | |
| echo "=== Raw page content (first 100 lines) for debugging ===" | |
| head -100 natyphoon_index.html | |
| exit 0 | |
| fi | |
| echo "" | |
| echo "==========================================" | |
| echo " Step 2: Construct JTWC URLs and fetch" | |
| echo "==========================================" | |
| # 对每个活跃的台风系统，构造JTWC URL并尝试下载 | |
| for datfile in $ACTIVE_FILES; do | |
| # 从 b{region}{num}{year}.dat 中提取信息 | |
| # 例如 bwp902026.dat -> region=wp, num=90, year=2026, shortyear=26 | |
| REGION=$(echo "$datfile" | sed -E 's/^b([a-z]{2})[0-9]+[0-9]{4}\.dat$/\1/') | |
| NUM=$(echo "$datfile" | sed -E 's/^b[a-z]{2}([0-9]{2,3})[0-9]{4}\.dat$/\1/') | |
| YEAR=$(echo "$datfile" | sed -E 's/^b[a-z]{2}[0-9]{2,3}([0-9]{4})\.dat$/\1/') | |
| SHORT_YEAR=${YEAR: -2} | |
| echo "" | |
| echo "--- System: $datfile ---" | |
| echo " Region=$REGION, Num=$NUM, Year=$YEAR, ShortYear=$SHORT_YEAR" | |
| # 尝试三种type: web, prog, fix | |
| for TYPE in web prog fix; do | |
| URL="https://www.metoc.navy.mil/jtwc/products/${REGION}${NUM}${SHORT_YEAR}${TYPE}.txt" | |
| OUTFILE="${REGION}${NUM}${SHORT_YEAR}${TYPE}.txt" | |
| echo " Trying: $URL" | |
| HTTP_CODE=$(curl -o "$OUTFILE" -w '%{http_code}' -s "$URL") | |
| if [ "$HTTP_CODE" = "200" ]; then | |
| # 检查内容是否为Error页面 | |
| if grep -qiP '^\s*<' "$OUTFILE" || grep -qi 'error\|not found\|403\|forbidden' "$OUTFILE"; then | |
| echo " -> HTTP 200 but content looks like error page, skipping" | |
| echo " -> First 3 lines: $(head -3 "$OUTFILE")" | |
| rm -f "$OUTFILE" | |
| else | |
| FILESIZE=$(wc -c < "$OUTFILE") | |
| echo " -> SUCCESS ($FILESIZE bytes)" | |
| echo " -> First 3 lines:" | |
| head -3 "$OUTFILE" | sed 's/^/ /' | |
| fi | |
| else | |
| echo " -> HTTP $HTTP_CODE, skipping" | |
| rm -f "$OUTFILE" | |
| fi | |
| done | |
| done | |
| echo "" | |
| echo "==========================================" | |
| echo " Step 3: Summary of downloaded files" | |
| echo "==========================================" | |
| echo "=== Files in current directory ===" | |
| ls -la *.txt 2>/dev/null || echo "(no .txt files downloaded)" | |
| # 测试模式：不提交，只打印结果 | |
| - name: Summary (test mode - no commit) | |
| run: | | |
| echo "==========================================" | |
| echo " TEST MODE - No files will be committed" | |
| echo "==========================================" | |
| echo "Downloaded .txt files:" | |
| for f in *.txt; do | |
| if [ -f "$f" ]; then | |
| echo " $f ($(wc -c < "$f") bytes)" | |
| fi | |
| done 2>/dev/null || echo " (none)" |