#!/usr/bin/env python3 """根据 comps.yaml 生成 rental-260705 的中间数据表、页面和媒体目录。 - 修复 租房260705/ 下乱码目录名 - 将拆分字段保存为 data.yaml（中间表格） - HTML 中用手工组织的自然语言展示，不再细碎地列出所有子字段 - 媒体通过 fetch('media.json') 动态加载，使用 BASE_PATH 解析绝对路径 - 生成压缩图、缩略图、media.json、data.yaml 和 comps.html """ import json import re import shutil import subprocess from pathlib import Path import yaml from PIL import Image BASE_DIR = Path(__file__).parent.resolve() # html_logs/ SRC_DIR = BASE_DIR / "租房260705" SRC_DIR_260630 = BASE_DIR / "租房260630" OUT_DIR = BASE_DIR / "rental-260705" # 乱码目录名修复：原始乱码 -> 正确中文 -> slug DIR_RENAME = { "厂洼2号院5号楼": "changwa-2-5", "厂洼一层": "changwa-1-102", "厂洼六层": "changwa-1-602", "理工附中家属楼南14": "ligong-fushu-nan14", "稻西4号楼8-1201": "daoxiang-4-1201", "稻西6号楼1207": "daoxiang-6-1207", "车道沟10号院": "chedaogou-10", "车道沟社区": "chedaogou-shequ-6-13", "厂洼17": "changwa-17", "汇新家园": "huixin-jiayuan", } # 6 月 30 日房源的目录 -> slug（用在 260705 综合页里） DIR_TO_SLUG_260630 = { "万北2-711": "wanquanzhuangbei-2-711", "万北4-310": "wanquanzhuangbei-4-310", "小南庄24": "xiaonanzhuang-24-762", "红5楼": "lixinhong-5-1-6", "三义庙": "sanyimiao-1ceng", "财智公馆G": "caizhihuiguan-G", "财智公馆3": "caizhihuiguan-3", } SLUGS = { 1: "wanquanzhuangbei-2-711", 2: "wanquanzhuangbei-4-310", 3: "xiaonanzhuang-24-762", 4: "lixinhong-5-1-6", 5: "sanyimiao-1ceng", 6: "caizhihuiguan-G", 7: "caizhihuiguan-3", 8: "nengjia-gongyu", 9: "ligong-fushu-nan14", 10: "chedaogou-shequ-6-13", 11: "chedaogou-10", 12: "changwa-1-102", 13: "changwa-1-602", 14: "changwa-2-5", 15: "changwa-17", 16: "daoxiang-4-1201", 17: "daoxiang-6-1207", 18: "huixin-jiayuan", } # 结构化字段 + 手工组织的自然语言概述 OVERRIDES = { 1: { "小区": "万泉庄北社区", "楼号": "2号楼", "房号": "711", "户型": "两室一厅", "面积": "60多平", "朝向": "东西向", "概述": "万泉庄北社区2号楼711，两室一厅约60多平，东西向。全瓷砖；东卧偏小、墙面有点脏，配的是小床带顶柜和硬床垫，西卧与原先房子差不多大，窗外全是树。", }, 2: { "小区": "万泉庄北社区", "楼号": "4号楼", "房号": "310", "户型": "一室一厅", "面积": "40多平", "朝向": "朝南", "概述": "万泉庄北社区4号楼310，一室一厅40多平，朝南，有阳台，木地板，装修质量一般。", }, 3: { "小区": "小南庄", "楼号": "24号楼", "房号": "762", "户型": "一室一厅", "面积": "40多平", "朝向": "朝南", "概述": "小南庄24号楼762，一室一厅40多平，朝南，有阳台，木地板。底价5200，另加10%服务费。", }, 4: { "小区": "立新红", "楼号": "5号楼", "单元": "1单元", "楼层": "6层", "面积": "20来平", "朝向": "朝南", "概述": "立新红5号楼1单元6层，20来平单间，朝南，窗外是紫金庄园，两户合租。楼道环境一般，一层是商户。", }, 5: { "小区": "三义庙", "楼层": "1层", "面积": "十几平", "朝向": "朝南", "概述": "三义庙1层，十几平狭长隔断房，朝南，木地板，四户合租。", }, 6: { "小区": "财智会馆", "楼层": "G层（二层）", "户型": "一室一厅", "面积": "45平", "朝向": "朝南", "概述": "财智会馆G层（二层），一室一厅45平，朝南，瓷砖，只有一小扇窗能开，装修比较新。", }, 7: { "小区": "财智会馆", "楼层": "3层（四层）", "户型": "一室一厅", "面积": "48平", "朝向": "朝东", "概述": "财智会馆3层（四层），一室一厅48平，朝东，木地板，柜子有木头味。", }, 8: { "小区": "展览馆路小区", "楼号": "能嘉公寓", "户型": "一室一厅公寓", "概述": "展览馆路小区能嘉公寓，一室一厅公寓，商电1.5元/度，供暖费400/月，其他免费，不可养宠物。", }, 9: { "小区": "理工附中家属楼", "房号": "南14", "户型": "平房（一室一厅+阁楼）", "面积": "40平左右", "朝向": "门朝北，南边有六层楼", "概述": "理工附中家属楼南14，平房带一室一厅和阁楼，共40平左右，门朝北，门外有种菜，墙是砖墙做了保温，南边有六层楼，冬天采光可能差点。", }, 10: { "小区": "车道沟社区", "楼号": "6号楼", "楼层": "13层", "户型": "一室一厅", "面积": "40平左右", "朝向": "朝南", "概述": "车道沟社区6号楼13层，一室一厅40平左右，朝南，视野宽阔，房东直租。", }, 11: { "小区": "车道沟10号院", "户型": "复式", "面积": "200多平", "概述": "车道沟10号院，200多平复式，一层住俩女生，二层住俩人加主卧和房东。", }, 12: { "小区": "厂洼2号院", "楼号": "1号楼", "房号": "102", "户型": "跳台", "概述": "厂洼2号院1号楼102，跳台，有霉点。", }, 13: { "小区": "厂洼2号院", "楼号": "1号楼", "房号": "602", "户型": "打隔断的两室一厅（按一室一厅租）", "概述": "厂洼2号院1号楼602，打隔断的两室一厅按一室一厅出租，另一家主卧带独卫不共用厨卫，明厨明卫朝南。", }, 14: { "小区": "厂洼2号院", "楼号": "5号楼", "户型": "主卧带独卫", "概述": "厂洼2号院5号楼，主卧带独卫，4家合租。", }, 15: { "小区": "厂洼小区", "楼号": "17号楼", "概述": "厂洼小区17号楼，3500能谈，还没去看。", }, 16: { "小区": "稻香园西里", "楼号": "4号楼", "单元": "8单元", "房号": "1201", "户型": "一室", "朝向": "朝西南", "概述": "稻香园西里4号楼8单元1201，一室朝西南，三家合租，前租户养猫。", }, 17: { "小区": "稻香园西里", "楼号": "6号楼", "房号": "1207", "户型": "未说明", "朝向": "朝北/朝西", "概述": "稻香园西里6号楼1207，大窗户朝北、小窗户朝西，四家合租，屋里有股味。", }, 18: { "小区": "汇新家园", "楼号": "4号楼", "房号": "502", "户型": "合租单间（客厅隔断）", "朝向": "朝东", "概述": "汇新家园4号楼502，朝东，三家合租，两个30多岁男的，采光一般，房间是客厅隔出来的，空间还行。", }, } IMAGE_EXTS = {".jpg", ".jpeg", ".png", ".webp", ".gif"} VIDEO_EXTS = {".mp4", ".mov", ".webm", ".mkv"} FULL_MAX_SIZE = 1600 FULL_QUALITY = 80 THUMB_MAX_SIZE = 480 THUMB_QUALITY = 75 VIDEO_MAX_WIDTH = 1280 VIDEO_CRF = 28 def fix_dir_names(): """把乱码目录重命名为 slug。""" if not SRC_DIR.exists(): print(f"源目录不存在：{SRC_DIR}") return [] renamed = [] for d in sorted(SRC_DIR.iterdir()): if not d.is_dir(): continue decoded = None try: decoded = d.name.encode('cp866').decode('utf-8') except Exception: decoded = d.name if decoded not in DIR_RENAME: print(f"未在映射表中找到：{decoded}") continue slug = DIR_RENAME[decoded] target = SRC_DIR / slug if target.exists(): print(f"目标已存在，跳过：{slug}") else: d.rename(target) print(f"重命名：{decoded} -> {slug}") renamed.append(slug) return renamed def compress_image(src: Path, dst: Path) -> bool: try: dst.parent.mkdir(parents=True, exist_ok=True) with Image.open(src) as im: if im.mode in ("RGBA", "P"): im = im.convert("RGB") im.thumbnail((FULL_MAX_SIZE, FULL_MAX_SIZE), Image.LANCZOS) im.save(dst, "JPEG", quality=FULL_QUALITY, optimize=True) return True except Exception as e: print(f" [图片压缩失败] {src}: {e}") return False def make_thumbnail(src: Path, dst: Path) -> bool: try: dst.parent.mkdir(parents=True, exist_ok=True) with Image.open(src) as im: if im.mode in ("RGBA", "P"): im = im.convert("RGB") im.thumbnail((THUMB_MAX_SIZE, THUMB_MAX_SIZE), Image.LANCZOS) im.save(dst, "JPEG", quality=THUMB_QUALITY, optimize=True) return True except Exception as e: print(f" [缩略图失败] {src}: {e}") return False def compress_video(src: Path, dst: Path) -> bool: dst.parent.mkdir(parents=True, exist_ok=True) cmd = [ "ffmpeg", "-y", "-i", str(src), "-c:v", "libx264", "-crf", str(VIDEO_CRF), "-preset", "medium", "-vf", f"scale='min({VIDEO_MAX_WIDTH},iw)':-2,format=yuv420p", "-c:a", "aac", "-b:a", "128k", "-movflags", "+faststart", str(dst), ] try: subprocess.run(cmd, check=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL) return True except subprocess.CalledProcessError as e: print(f" [视频压缩失败] {src}: {e}") return False def build_media(): """处理 租房260705/ 和 租房260630/ 下的媒体，输出到 rental-260705/media/。""" OUT_DIR.mkdir(parents=True, exist_ok=True) media_dir = OUT_DIR / "media" media_dir.mkdir(exist_ok=True) data = {} for slug in sorted(DIR_RENAME.values()): src = SRC_DIR / slug if not src.exists(): continue print(f"处理媒体 {slug}") _process_media_dir(src, slug, data, media_dir) for slug in sorted(DIR_TO_SLUG_260630.values()): # 源目录是中文名，用映射表查找 src_name = {v: k for k, v in DIR_TO_SLUG_260630.items()}[slug] src = SRC_DIR_260630 / src_name if not src.exists(): continue print(f"处理媒体 260630/{slug}") _process_media_dir(src, slug, data, media_dir) with open(OUT_DIR / "media.json", "w", encoding="utf-8") as fp: json.dump(data, fp, ensure_ascii=False, indent=2) print(f"已生成 {OUT_DIR / 'media.json'}") return data def _process_media_dir(src: Path, slug: str, data: dict, media_dir: Path): data[slug] = {"images": [], "thumbnails": [], "videos": []} dst_base = media_dir / slug thumb_dir = dst_base / "thumbs" thumb_dir.mkdir(parents=True, exist_ok=True) for f in sorted(src.iterdir()): if not f.is_file() or f.parent.name == "thumbs": continue ext = f.suffix.lower() if ext in IMAGE_EXTS: out_name = f.stem + ".jpg" full_dst = dst_base / out_name thumb_dst = thumb_dir / out_name if compress_image(f, full_dst): data[slug]["images"].append(f"media/{slug}/{out_name}") if make_thumbnail(f, thumb_dst): data[slug]["thumbnails"].append(f"media/{slug}/thumbs/{out_name}") elif ext in VIDEO_EXTS: out_name = f.stem + ".mp4" video_dst = dst_base / out_name if compress_video(f, video_dst): data[slug]["videos"].append(f"media/{slug}/{out_name}") def build_data(media: dict): """生成中间表格 data.yaml。""" with open(BASE_DIR / "comps.yaml", encoding="utf-8") as f: raw = yaml.safe_load(f) entries = [] for i, item in enumerate(raw, start=1): e = { "id": i, "slug": SLUGS[i], "位置": item.get("位置", ""), "小区": "", "楼号": "", "单元": "", "楼层": "", "房号": "", "户型": "", "面积": "", "朝向": "", "情况": item.get("情况", ""), "厨卫": item.get("厨卫") or "", "费用": item.get("费用") or "", "其他": item.get("其他") or "", "到单位通勤距离": "", "到现在居住地通勤距离": "", } e.update(OVERRIDES.get(i, {})) e["media"] = media.get(e["slug"], {"images": [], "thumbnails": [], "videos": []}) entries.append(e) with open(OUT_DIR / "data.yaml", "w", encoding="utf-8") as fp: yaml.dump(entries, fp, allow_unicode=True, sort_keys=False) print(f"已生成 {OUT_DIR / 'data.yaml'}") return entries def extract_service_fee(fee: str) -> str: if not fee: return "" m = re.search(r'\+(\d+(?:\.\d+)?%)服务费', fee) if m: return m.group(1) m = re.search(r'中介费(\d+个月)', fee) if m: return f"中介{m.group(1)}" if "无其他费用" in fee: return "无" return "" def location_summary(e: dict) -> str: parts = [e.get("小区", "")] for k in ["楼号", "单元", "楼层", "房号"]: v = e.get(k, "") if v: parts.append(v) return " ".join(p for p in parts if p) def type_summary(e: dict) -> str: parts = [e.get("户型", ""), e.get("面积", ""), e.get("朝向", "")] return "，".join(p for p in parts if p) or "-" def render_html(entries: list, title: str = "看房对比", subtitle: str = "") -> str: rows = [] for e in entries: rows.append( f" \n" f" {location_summary(e)}\n" f" {type_summary(e)}\n" f" {e.get('费用', '') or '-'}\n" f" {extract_service_fee(e.get('费用','')) or '-'}\n" f" {e.get('厨卫', '') or '-'}\n" f" " ) rows_html = "\n".join(rows) cards = [] for e in entries: title = e.get("位置", "") or location_summary(e) overview = e.get("概述", e.get("情况", "")) cards.append( f"
\n" f"

{title}

\n" f"

{overview}

\n" f"
\n" f"

厨卫：{e.get('厨卫', '') or '—'}

\n" f"

费用：{e.get('费用', '') or '—'}

\n" f"

到单位通勤：{e.get('到单位通勤距离', '') or '—'}

\n" f"

到现居地通勤：{e.get('到现在居住地通勤距离', '') or '—'}

\n" f"

其他：{e.get('其他', '') or '—'}

\n" f"
\n" f"
\n" f"

照片 / 视频

\n" f"
\n" f"
\n" f"
" ) cards_html = "\n\n".join(cards) return f""" 看房对比

{title}

{subtitle or f"共 {len(entries)} 套房源，点击表格可跳转到详情"}

{rows_html}
位置 户型/面积/朝向 费用 服务费 厨卫
{cards_html}
× \"\"
""" def main(): print("=== 修复目录名 ===") fix_dir_names() print("\n=== 处理媒体 ===") media = build_media() print("\n=== 生成中间表格 ===") entries = build_data(media) print("\n=== 生成页面 ===") html = render_html(entries) with open(OUT_DIR / "comps.html", "w", encoding="utf-8") as f: f.write(html) print(f"已生成 {OUT_DIR / 'comps.html'}") final_slugs = ["ligong-fushu-nan14", "changwa-1-602", "daoxiang-4-1201", "huixin-jiayuan"] final_entries = [e for e in entries if e["slug"] in final_slugs] final_html = render_html( final_entries, title="决赛圈", subtitle=" shortlisted 4 套，重点对比", ) with open(OUT_DIR / "final.html", "w", encoding="utf-8") as f: f.write(final_html) print(f"已生成 {OUT_DIR / 'final.html'}") print(f"\n本地预览: file://{OUT_DIR / 'comps.html'}") print(f"决赛圈预览: file://{OUT_DIR / 'final.html'}") if __name__ == "__main__": main()