From 88288358fd73500a43214c2894de91175eeac970 Mon Sep 17 00:00:00 2001 From: admin9webs Date: Fri, 10 Jul 2026 16:10:59 +0800 Subject: [PATCH] Add archived/tongtool-temu-y2-cheapest-scraper --- .../SKILL.md | 243 ++++++++++++++++++ 1 file changed, 243 insertions(+) create mode 100644 skills/archived/tongtool-temu-y2-cheapest-scraper/SKILL.md diff --git a/skills/archived/tongtool-temu-y2-cheapest-scraper/SKILL.md b/skills/archived/tongtool-temu-y2-cheapest-scraper/SKILL.md new file mode 100644 index 0000000..66ac922 --- /dev/null +++ b/skills/archived/tongtool-temu-y2-cheapest-scraper/SKILL.md @@ -0,0 +1,243 @@ +--- +name: tongtool-temu-y2-cheapest-scraper +skill_name: tongtool-temu-y2-cheapest-scraper +category: cross-border-ecommerce +description: > + 全流程自动化:登录Tongtool(通途)ERP → 筛选产品 → 抓取TEMU Y2 cheapest价格数据 → 添加订单备注。 + 适用于从通途ERP批量采集TEMU最低价并同步记录订单备注信息。 +tags: [tongtool, temu, y2, scraping, e-commerce, price-monitoring, 通途, 订单备注] +--- + +# 通途 ERP → TEMU Y2 cheapest 抓取 + 订单备注流程 + +## 前置条件 +- 通途账号:`ozonezsjgw@163.com`(Cookie 已保存,通常可自动登录) +- 通途 Cookie 文件:`/home/ubuntu/.hermes/cookies/tongtool_cookies.json` +- 工具:Playwright(Node.js)或 DrissionPage +- 页面特征:通途ERP TEMU → Y2版本 → cheapest列、订单详情页备注框 + +## 步骤 1:登录通途 ERP + +### 1.1 加载 Cookie 免密登录(推荐) +```python +import json +from playwright.sync_api import sync_playwright + +with sync_playwright() as p: + browser = p.chromium.launch(headless=True) + context = browser.new_context(ignore_https_errors=True) + + # 加载已保存的 Cookie + with open('/home/ubuntu/.hermes/cookies/tongtool_cookies.json', 'r') as f: + cookies = json.load(f) + context.add_cookies(cookies) + + page = context.new_page() + page.goto("https://erp.tongtool.com") + # Cookie有效则自动进入工作台;若失效则走账号密码重登 +``` + +### 1.2 账号密码登录(备用) +- 账号:`ozonezsjgw@163.com` +- 密码:根据实际凭证 +- 注意:通途可能有滑动验证码,参照 `captcha-auto-login` skill + +## 步骤 2:导航至 TEMU Y2 页面 + +### 2.1 进入 TEMU 模块 +```python +page.click('text=TEMU 半托管') # 或对应菜单文字 +page.wait_for_load_state('networkidle') +``` + +### 2.2 切换到 Y2 视图 +```python +page.click('text=Y2') # 页面上的 Y2 标签/按钮 +page.wait_for_timeout(1000) +``` + +### 2.3 确认页面定位成功 +```python +assert page.locator('text=Y2 cheapest, nth=0').is_visible() or \ + page.locator('th:has-text("Y2 cheapest")').count() > 0 +``` + +## 步骤 3:筛选目标产品 + +常用筛选条件: +- 品类/类目 +- 店铺 +- 价格区间 +- 上架状态 + +```python +# 示例:展开筛选面板并设置条件 +page.click('button:has-text("筛选")') +page.select_option('select[name="category"]', '家居百货') # 根据实际控件调整 +page.click('button:has-text("查询")') +page.wait_for_timeout(1500) +``` + +等待列表加载: +```python +page.wait_for_selector('table tbody tr') +``` + +## 步骤 4:抓取 Y2 cheapest 数据 + +### 4.1 定位 Y2 cheapest 列 +- 表头关键词:`Y2 cheapest` +- 值特征:数字,可能带 `$` 或 `USD` 前缀,颜色可能标识低价优势 + +### 4.2 单页抓取 +```python +import json + +data = [] +rows = page.query_selector_all('table tbody tr') + +for row in rows: + cells = row.query_selector_all('td') + product_name = cells[1].inner_text().strip() if len(cells) > 1 else "" + y2_cheapest = cells[-2].inner_text().strip().replace('$', '').replace(',', '') if len(cells) > 2 else "" + + data.append({ + "product_name": product_name, + "y2_cheapest": float(y2_cheapest) if y2_cheapest else None + }) + +with open('temu_y2_cheapest.json', 'w', encoding='utf-8') as f: + json.dump(data, f, ensure_ascii=False, indent=2) +``` + +### 4.3 分页抓取 +```python +while True: + scrape_page() + next_btn = page.query_selector('button.next:enabled, a:has-text("下一页"):not(.disabled)') + if not next_btn or "disabled" in (next_btn.get_attribute('class') or ''): + break + next_btn.click() + page.wait_for_timeout(2000) +``` + +## 步骤 5:添加订单备注 + +在抓取 Y2 cheapest 后,为对应订单添加备注以便后续运营跟踪。 + +### 5.1 打开订单详情页 +列表页中点击目标订单的「订单号」或「详情」按钮: +```python +# 点击第一行的"查看详情"或订单号链接(假设操作列在末尾) +first_row = page.query_selector('table tbody tr') +detail_btn = first_row.query_selector('a:has-text("详情"), button:has-text("详情")') +if detail_btn: + detail_btn.click() + page.wait_for_timeout(1500) +``` + +### 5.2 打开备注/留言输入区域 +备注入口通常位于: +- 订单详情页的 **"订单备注"** 标签页 +- 右下角弹出的备注图标 +- 页面底部的备注输入框 + +```python +# 方法 A:点击备注标签 +remark_tab = page.locator('.el-tabs__item:has-text("订单备注"), text=订单备注') +if remark_tab.count() > 0: + remark_tab.click() + page.wait_for_timeout(500) + +# 方法 B:直接定位备注文本域 +remark_box = page.locator('textarea[placeholder*="备注"], textarea[placeholder*="留言"], .remark-input') +``` + +### 5.3 填写并保存备注 +```python +remark_text = f"Y2 cheapest 采集价: ${price_val} — 采集时间: {datetime.now().strftime('%Y-%m-%d %H:%M')}" + +# 填入备注框 +page.fill('textarea[placeholder*="备注"]', remark_text) + +# 点击保存/提交 +page.click('button:has-text("保存备注"), button:has-text("提交"), button:has-text("确定")') +page.wait_for_timeout(800) + +# 可选:等待保存成功提示 +page.wait_for_selector('.el-notification:has-text("成功"), .el-message:has-text("保存成功")') +``` + +### 5.4 快捷:列表页批量添加备注(如支持) +部分版本支持在列表行内直接展开备注: +```python +# 点击备注图标展开编辑 +remark_icon = row.query_selector('i.icon-remark, span:has-text("备注")') +if remark_icon: + remark_icon.click() + page.wait_for_timeout(300) + page.fill('.inline-remark-input', remark_text) + page.press('.inline-remark-input', 'Enter') +``` + +### 5.5 批量备注完整示例 +结合抓取与备注: +```python +from datetime import datetime + +rows = page.query_selector_all('table tbody tr') +for idx, row in enumerate(rows): + cells = row.query_selector_all('td') + if len(cells) < 3: + continue + + order_no = cells[0].inner_text().strip() # 订单编号 + y2_price = cells[-2].inner_text().strip().replace('$', '') + + remark = f"TEMU Y2 cheapest: {y2_price} | 采集: {datetime.now().strftime('%Y-%m-%d')}" + + # 进入详情写备注 + detail = row.query_selector('a:has-text("详情")') + if detail: + detail.click() + page.wait_for_timeout(1000) + + page.fill('textarea[placeholder*="备注"]', remark) + page.click('button:has-text("保存")') + page.wait_for_timeout(500) + + # 返回列表 + page.click('button:has-text("返回"), .back-btn') + page.wait_for_timeout(500) +``` + +## 步骤 6(可选):导出 CSV +```python +import csv + +with open('temu_y2_cheapest.csv', 'w', newline='', encoding='utf-8-sig') as f: + writer = csv.DictWriter(f, fieldnames=["product_name", "y2_cheapest"]) + writer.writeheader() + writer.writerows(data) +``` + +## 常见问题与排查 + +| 问题 | 原因 | 解决 | +|------|------|------| +| Cookie 登录失效 | Cookie过期或被注销 | 需重新手动登录并导出Cookie | +| 页面无 Y2 标签 | 账号权限或菜单结构不同 | 确认通途账号有TEMU Y2权限 | +| Y2 cheapest 列值空 | 数据未加载或 lazily rendered | 滚动页面或等 `networkidle` 再抓 | +| 备注保存失败 | 输入框未聚焦或页面未正确渲染 | 先 `click()` 再 `fill()` 备注框 | +| 抓取频率受限 | 触发风控 | 增加随机延时 `random.uniform(2,5)` | + +## 相关技能 +- `tongtool-erp-automation` — 通途ERP通用自动化 +- `tongtool-temu-shipping-calc` — 通途TEMU运费计算 +- `captcha-auto-login` — 验证码自动识别登录 +- `node-playwright-web-automation` — Node.js Playwright 自动化指南 + +## 安全提示 +- Cookie 文件含敏感凭证,勿上传公开仓库 +- 建议对 `tongtool_cookies.json` 设置 `chmod 600` +- 遵守通途平台服务条款,避免高频自动化导致封号