fix: edit img select and nhsource bundles

bundles/nikkei-markets.nhsource.json

 {
   "format": "news-harvester-source",
   "version": 1,
-  "exportedAt": "2026-07-30T08:41:39.136Z",
+  "exportedAt": "2026-08-04T04:39:33.227Z",
   "source": {
     "id": "nikkei-markets",
     "name": "日经亚洲市场",
@@ -10,6 +10,6 @@
     "vaultFolder": "日经亚洲/市场"
   },
   "files": {
-    "helpers/nikkei-markets.md": "---\nsource: nikkei-markets\nlistSelector: '[class*=\"StreamArticleCard\"], [class*=\"SpotlightArticleCard\"], [class*=\"SecondaryArticleCard\"]'\nlinkSelector: 'a[href]'\nurlPattern: 'asia\\.nikkei\\.com/(?:business|spotlight|economy|politics|editor-s-picks|location|opinion|features|life-arts|techasia)/[^/?#]+/.+'\nexcludeUrlPattern: '/(?:podcasts|static|infographics|member)/'\nscrollSteps: 3\nscrollWaitMs: 2000\nwaitMs: 15000\nvalidateArticle: true\nbodyMinChars: 500\nbodySelectors:\n  - '[class*=\"ArticleBody\"] p'\n  - '[class*=\"article-body\"] p'\n  - 'article p'\nbodyMinParagraphs: 3\ndateSelector: 'time[datetime]'\nauthorSelector: '[class*=\"author\"] a, [rel=\"author\"]'\nimageSelector: 'img'\nimageMinWidth: 200\nexcludeImage:\n  - logo\n  - icon\n  - avatar\n  - profile\n  - placeholder\n  - outbrainimg.com\ntitleStripSuffix: ' - Nikkei Asia$'\nmaxBodyChars: 15000\n---\n# 日经亚洲市场 抓取备忘\n\n## 列表页链接收集(`/business/markets`)\n\n- **listSelector 用复合卡片选择器**:`[class*=\"StreamArticleCard\"], [class*=\"SpotlightArticleCard\"], [class*=\"SecondaryArticleCard\"]`。实测 `/business/markets` 页面文章卡片分散在这三类容器里(StreamArticleCard 24 篇 + SpotlightArticleCard 3 篇 + SecondaryArticleCard 3 篇 = 30 篇)。\n- 与 nikkei-tech 同属 Nikkei 模板,卡片容器类型一致,复用同一复合选择器。\n- **urlPattern** 覆盖所有可能的文章路径段:`business`、`spotlight`、`economy`、`politics`、`editor-s-picks`、`location`、`opinion`、`features`、`life-arts`、`techasia`。`/[^/?#]+/.+` 要求至少 3 段路径。\n- **excludeUrlPattern** 剔除 `/podcasts/`、`/static/`、`/infographics/`、`/member/` 等非文章路径。\n- **validateArticle: true** 在 fetchPage 阶段用 og:type + JSON-LD + 正文字符数剔除分类页(卡片 tag 链接如 `/business/markets/currencies`、`/business/markets/property` 会被判 isArticle=false 并跳过)。\n- `scrollSteps: 3` 触发懒加载;Nikkei 用 `?page=N` 分页,query strip 自动排除分页链接。\n\n## 详情页正文验证\n\n`validateArticle: true` 让 `fetchPage` 采集判别信号,返回 `isArticle` 布尔;harvest 对 `isArticle === false` 直接 skip:\n\n```\nisArticle = (og:type === 'article' || JSON-LD @type ∈ {NewsArticle, Article})\n            && bodyChars >= 500\n            && bodyParagraphs >= 3\n```\n\n## 其他\n\n- 正文优先 `[class*=\"ArticleBody\"]`(Nikkei CSS Modules 正文容器)。\n- 部分文章有付费墙,bodyMinChars=500 + bodyMinParagraphs=3 过滤被截断到极短的页面。\n"
+    "helpers/nikkei-markets.md": "---\nsource: nikkei-markets\nlistSelector: '[class*=\"StreamArticleCard\"], [class*=\"SpotlightArticleCard\"], [class*=\"SecondaryArticleCard\"]'\nlinkSelector: 'a[href]'\nurlPattern: 'asia\\.nikkei\\.com/(?:business|spotlight|economy|politics|editor-s-picks|location|opinion|features|life-arts|techasia)/[^/?#]+(?:/.+)?'\nexcludeUrlPattern: '/(?:podcasts|static|infographics|member)/'\nscrollSteps: 3\nscrollWaitMs: 2000\nwaitMs: 15000\nvalidateArticle: true\nbodyMinChars: 500\nbodySelectors:\n  - '[class*=\"ArticleBody\"] p'\n  - '[class*=\"article-body\"] p'\n  - 'article p'\nbodyMinParagraphs: 3\ndateSelector: 'time[datetime]'\nauthorSelector: '[class*=\"author\"] a, [rel=\"author\"]'\nimageSelector: 'img'\n# 文章底部\"推荐/相关文章\"卡片缩略图与 hero 头图共用 images.ft.com CDN,\n# src 子串排除(excludeImage)无法区分,改用容器选择器整块排除。\n# 实测容器:RelatedArticle* / RelatedArticleFeature* / LatestOnTopicBottom* / Outbrain(.ob-rec-image)。\n# hero 头图在 NewsArticleHeaderImage 内,不在排除范围 → 保留。\nexcludeImageSelector: '[class*=\"RelatedArticle\"], [class*=\"RelatedArticleFeature\"], [class*=\"LatestOnTopicBottom\"], .ob-rec-image'\nimageMinWidth: 200\nexcludeImage:\n  - logo\n  - icon\n  - avatar\n  - profile\n  - placeholder\n  - outbrainimg.com\ntitleStripSuffix: ' - Nikkei Asia$'\nmaxBodyChars: 15000\n---\n# 日经亚洲市场 抓取备忘\n\n## 列表页链接收集(`/business/markets`)\n\n- **listSelector 用复合卡片选择器**:`[class*=\"StreamArticleCard\"], [class*=\"SpotlightArticleCard\"], [class*=\"SecondaryArticleCard\"]`。实测 `/business/markets` 页面文章卡片分散在这三类容器里(StreamArticleCard 24 篇 + SpotlightArticleCard 3 篇 + SecondaryArticleCard 3 篇 = 30 篇)。\n- 与 nikkei-tech 同属 Nikkei 模板,卡片容器类型一致,复用同一复合选择器。\n- **urlPattern** 覆盖所有可能的文章路径段:`business`、`spotlight`、`economy`、`politics`、`editor-s-picks`、`location`、`opinion`、`features`、`life-arts`、`techasia`。第三段 `(?:/.+)?` 可选——Nikkei 的 URL 结构不统一:`/business/markets/currencies/<slug>` 是 3 段,但 `/opinion/<slug>`、`/economy/<slug>`、`/politics/<slug>` 是 2 段。2 段 URL 会混入分类页(如 `/business/markets/commodities`),由 `validateArticle: true` 在 fetchPage 阶段剔除。\n- **excludeUrlPattern** 剔除 `/podcasts/`、`/static/`、`/infographics/`、`/member/` 等非文章路径。\n- **validateArticle: true** 在 fetchPage 阶段用 og:type + JSON-LD + 正文字符数剔除分类页(卡片 tag 链接如 `/business/markets/currencies`、`/business/markets/property` 会被判 isArticle=false 并跳过)。\n- `scrollSteps: 3` 触发懒加载;Nikkei 用 `?page=N` 分页,query strip 自动排除分页链接。\n\n## 详情页正文验证\n\n`validateArticle: true` 让 `fetchPage` 采集判别信号,返回 `isArticle` 布尔;harvest 对 `isArticle === false` 直接 skip:\n\n```\nisArticle = (og:type === 'article' || JSON-LD @type ∈ {NewsArticle, Article})\n            && bodyChars >= 500\n            && bodyParagraphs >= 3\n```\n\n## 其他\n\n- 正文优先 `[class*=\"ArticleBody\"]`(Nikkei CSS Modules 正文容器)。\n- 部分文章有付费墙,bodyMinChars=500 + bodyMinParagraphs=3 过滤被截断到极短的页面。\n"
   }
 }
\ No newline at end of file

bundles/nikkei-tech.nhsource.json

 {
   "format": "news-harvester-source",
   "version": 1,
-  "exportedAt": "2026-07-29T07:04:52.699Z",
+  "exportedAt": "2026-08-04T04:39:33.187Z",
   "source": {
     "id": "nikkei-tech",
     "name": "日经亚洲科技",
@@ -10,7 +10,7 @@
     "vaultFolder": "日经亚洲/科技"
   },
   "files": {
-    "helpers/nikkei-tech.md": "---\nsource: nikkei-tech\nlistSelector: '[class*=\"StreamArticleCard\"], [class*=\"SpotlightArticleCard\"], [class*=\"SecondaryArticleCard\"]'\nlinkSelector: 'a[href]'\nurlPattern: 'asia\\.nikkei\\.com/(?:business|spotlight|economy|politics|editor-s-picks|location|opinion|features|life-arts)/[^/?#]+/.+'\nexcludeUrlPattern: '/(?:podcasts|static|infographics|member)/'\nscrollSteps: 3\nscrollWaitMs: 2000\nwaitMs: 15000\n# 详情页正文验证(见 fetcher-helper.js buildExtractExpr):放宽 urlPattern 后,\n# 靠 og:type / JSON-LD @type / 正文字符数在 fetchPage 阶段剔除分类页,而不是\n# 靠 URL 末段连字符数猜测。实测文章 og:type=article + 正文>3000字符;分类页\n# og:type=website + 正文 0,判别力极强。\nvalidateArticle: true\nbodyMinChars: 500\nbodySelectors:\n  - '[class*=\"ArticleBody\"] p'\n  - '[class*=\"article-body\"] p'\n  - 'article p'\nbodyMinParagraphs: 3\ndateSelector: 'time[datetime]'\nauthorSelector: '[class*=\"author\"] a, [rel=\"author\"]'\nimageSelector: 'img'\nimageMinWidth: 200\nexcludeImage:\n  - logo\n  - icon\n  - avatar\n  - profile\n  - placeholder\n  - outbrainimg.com\ntitleStripSuffix: ' - Nikkei Asia$'\nmaxBodyChars: 15000\n---\n# 日经亚洲科技 抓取备忘\n\n## 列表页链接收集(`/business/tech`)\n\n- **listSelector 用复合卡片选择器**:`[class*=\"StreamArticleCard\"], [class*=\"SpotlightArticleCard\"], [class*=\"SecondaryArticleCard\"]`。实测文章卡片分散在这三类容器里(StreamArticleCard 27 篇 + SpotlightArticleCard 3 篇 + SecondaryArticleCard 3 篇 = 33 篇)。旧规则只锁定 `StreamArticleCard`,丢了 6 篇在 `SpotlightArticleCard`/`SecondaryArticleCard` 里的真实文章(含 SK Hynix、Philippine women、humanoid robots、Kumamoto quake、Panasonic、KOSPI 等)。\n- **为什么不直接 `listSelector: null`(全页)**:实测全页扫描会被导航栏的 `/location/<country>` 国家下拉链接(`/location/east-asia/china` 等 ~30 条)在 `maxLinks: 30` 上限内塞满,导致真实文章一条都收不到。卡片容器范围是必须的,只要把三类 ArticleCard 容器都纳入即可覆盖全部文章且避开 nav。\n- **urlPattern 扩展顶层段白名单**。旧 pattern 只覆盖 `/business/`、`/spotlight/`;实测 `/economy/`、`/politics/`、`/editor-s-picks/`、`/location/`、`/opinion/`、`/features/`、`/life-arts/` 下都出现文章。`/[^/?#]+/.+` 要求至少 3 段路径(顶层/子段/slug),同时覆盖 2 段深文章(如 `/economy/<slug>`)和 3 段深文章(如 `/business/tech/semiconductors/<slug>`)。\n- **excludeUrlPattern** 剔除 `/podcasts/`、`/static/`、`/infographics/`、`/member/` 等非文章路径。\n- **删除\"末段 ≥5 连字符\"硬规则**。旧 pattern 用 `(?:-[^/?#]*){5,}$` 猜测\"长 slug=文章\",但分类页 slug 也可能很长(如 `artificial-intelligence`、`wealth-management`),短标题文章又会被误伤。改由详情页验证区分。卡片里仍会混入 ~18 条子分类页链接(如 `/business/tech/semiconductors`、`/spotlight/trump-administration`,作为卡片的 tag 链接出现),由 `validateArticle` 在 fetchPage 阶段剔除。\n- `scrollSteps: 3` 触发懒加载;Nikkei 用 `?page=N` 分页(非无限滚动),query strip 自动排除分页链接。\n\n## 详情页正文验证(取代 URL 猜测)\n\n`validateArticle: true` 让 `fetchPage` 在提取正文时额外采集判别信号,返回 `isArticle` 布尔;harvest 对 `isArticle === false` 的候选直接 skip。判别逻辑:\n\n```\nisArticle = (og:type === 'article' || JSON-LD @type ∈ {NewsArticle, Article})\n            && bodyChars >= 500\n            && bodyParagraphs >= 3\n```\n\n实测信号(2026-07-29):\n| 页面类型 | og:type | JSON-LD @type | 正文段落 | 正文字符 |\n|----------|---------|---------------|----------|----------|\n| 文章(SK Hynix Q2) | article | NewsArticle | 11 | 3671 |\n| 文章(Philippine women) | article | NewsArticle | 30 | 5647 |\n| 分类页(/business/tech/semiconductors) | website | Thing | 0 | 0 |\n\n正文验证发生在候选链接被收集**之后**(fetchPage 阶段),所以放宽 urlPattern 混入的少量分类页会在这一步被剔除,不会进入 registry 或落盘。\n\n## 其他\n\n- 正文优先 `[class*=\"ArticleBody\"]`(Nikkei 的 CSS Modules 正文容器)。\n- 部分文章有付费墙,正文可能不完整——bodyMinChars=500 + bodyMinParagraphs=3 的下限会过滤掉被付费墙截断到极短的页面;preview 验证后若 charCount 过低需排除。\n- 回归测试:`node scripts/recipe-test.js nikkei-tech`(固定文章 URL 必须 isArticle,固定分类页 URL 必须非 isArticle,列表页链接数 ≥10 且不含 exclude 路径)。\n",
+    "helpers/nikkei-tech.md": "---\nsource: nikkei-tech\nlistSelector: '[class*=\"StreamArticleCard\"], [class*=\"SpotlightArticleCard\"], [class*=\"SecondaryArticleCard\"]'\nlinkSelector: 'a[href]'\nurlPattern: 'asia\\.nikkei\\.com/(?:business|spotlight|economy|politics|editor-s-picks|location|opinion|features|life-arts|techasia)/[^/?#]+(?:/.+)?'\nexcludeUrlPattern: '/(?:podcasts|static|infographics|member)/'\nscrollSteps: 3\nscrollWaitMs: 2000\nwaitMs: 15000\n# 详情页正文验证(见 fetcher-helper.js buildExtractExpr):放宽 urlPattern 后,\n# 靠 og:type / JSON-LD @type / 正文字符数在 fetchPage 阶段剔除分类页,而不是\n# 靠 URL 末段连字符数猜测。实测文章 og:type=article + 正文>3000字符;分类页\n# og:type=website + 正文 0,判别力极强。\nvalidateArticle: true\nbodyMinChars: 500\nbodySelectors:\n  - '[class*=\"ArticleBody\"] p'\n  - '[class*=\"article-body\"] p'\n  - 'article p'\nbodyMinParagraphs: 3\ndateSelector: 'time[datetime]'\nauthorSelector: '[class*=\"author\"] a, [rel=\"author\"]'\nimageSelector: 'img'\n# 文章底部\"推荐/相关文章\"卡片缩略图与 hero 头图共用 images.ft.com CDN,\n# src 子串排除(excludeImage)无法区分,改用容器选择器整块排除。\n# 实测容器:RelatedArticle* / RelatedArticleFeature* / LatestOnTopicBottom* / Outbrain(.ob-rec-image)。\n# hero 头图在 NewsArticleHeaderImage 内,不在排除范围 → 保留。\nexcludeImageSelector: '[class*=\"RelatedArticle\"], [class*=\"RelatedArticleFeature\"], [class*=\"LatestOnTopicBottom\"], .ob-rec-image'\nimageMinWidth: 200\nexcludeImage:\n  - logo\n  - icon\n  - avatar\n  - profile\n  - placeholder\n  - outbrainimg.com\ntitleStripSuffix: ' - Nikkei Asia$'\nmaxBodyChars: 15000\n---\n# 日经亚洲科技 抓取备忘\n\n## 列表页链接收集(`/business/tech`)\n\n- **listSelector 用复合卡片选择器**:`[class*=\"StreamArticleCard\"], [class*=\"SpotlightArticleCard\"], [class*=\"SecondaryArticleCard\"]`。实测文章卡片分散在这三类容器里(StreamArticleCard 27 篇 + SpotlightArticleCard 3 篇 + SecondaryArticleCard 3 篇 = 33 篇)。旧规则只锁定 `StreamArticleCard`,丢了 6 篇在 `SpotlightArticleCard`/`SecondaryArticleCard` 里的真实文章(含 SK Hynix、Philippine women、humanoid robots、Kumamoto quake、Panasonic、KOSPI 等)。\n- **为什么不直接 `listSelector: null`(全页)**:实测全页扫描会被导航栏的 `/location/<country>` 国家下拉链接(`/location/east-asia/china` 等 ~30 条)在 `maxLinks: 30` 上限内塞满,导致真实文章一条都收不到。卡片容器范围是必须的,只要把三类 ArticleCard 容器都纳入即可覆盖全部文章且避开 nav。\n- **urlPattern 扩展顶层段白名单**。旧 pattern 只覆盖 `/business/`、`/spotlight/`;实测 `/economy/`、`/politics/`、`/editor-s-picks/`、`/location/`、`/opinion/`、`/features/`、`/life-arts/`、`/techasia/` 下都出现文章。第三段 `(?:/.+)?` 可选——Nikkei 的 URL 结构不统一:`/business/tech/semiconductors/<slug>` 是 3 段,但 `/opinion/<slug>`、`/economy/<slug>`、`/politics/<slug>` 是 2 段。2 段 URL 会混入分类页(如 `/business/markets`),由 `validateArticle: true` 在 fetchPage 阶段剔除。\n- **excludeUrlPattern** 剔除 `/podcasts/`、`/static/`、`/infographics/`、`/member/` 等非文章路径。\n- **删除\"末段 ≥5 连字符\"硬规则**。旧 pattern 用 `(?:-[^/?#]*){5,}$` 猜测\"长 slug=文章\",但分类页 slug 也可能很长(如 `artificial-intelligence`、`wealth-management`),短标题文章又会被误伤。改由详情页验证区分。卡片里仍会混入 ~18 条子分类页链接(如 `/business/tech/semiconductors`、`/spotlight/trump-administration`,作为卡片的 tag 链接出现),由 `validateArticle` 在 fetchPage 阶段剔除。\n- `scrollSteps: 3` 触发懒加载;Nikkei 用 `?page=N` 分页(非无限滚动),query strip 自动排除分页链接。\n\n## 详情页正文验证(取代 URL 猜测)\n\n`validateArticle: true` 让 `fetchPage` 在提取正文时额外采集判别信号,返回 `isArticle` 布尔;harvest 对 `isArticle === false` 的候选直接 skip。判别逻辑:\n\n```\nisArticle = (og:type === 'article' || JSON-LD @type ∈ {NewsArticle, Article})\n            && bodyChars >= 500\n            && bodyParagraphs >= 3\n```\n\n实测信号(2026-07-29):\n| 页面类型 | og:type | JSON-LD @type | 正文段落 | 正文字符 |\n|----------|---------|---------------|----------|----------|\n| 文章(SK Hynix Q2) | article | NewsArticle | 11 | 3671 |\n| 文章(Philippine women) | article | NewsArticle | 30 | 5647 |\n| 分类页(/business/tech/semiconductors) | website | Thing | 0 | 0 |\n\n正文验证发生在候选链接被收集**之后**(fetchPage 阶段),所以放宽 urlPattern 混入的少量分类页会在这一步被剔除,不会进入 registry 或落盘。\n\n## 其他\n\n- 正文优先 `[class*=\"ArticleBody\"]`(Nikkei 的 CSS Modules 正文容器)。\n- 部分文章有付费墙,正文可能不完整——bodyMinChars=500 + bodyMinParagraphs=3 的下限会过滤掉被付费墙截断到极短的页面;preview 验证后若 charCount 过低需排除。\n- 回归测试:`node scripts/recipe-test.js nikkei-tech`(固定文章 URL 必须 isArticle,固定分类页 URL 必须非 isArticle,列表页链接数 ≥10 且不含 exclude 路径)。\n",
     "helpers/nikkei-tech.fixtures.json": "{\n  \"_comment\": \"Regression fixtures for the nikkei-tech recipe. Article URLs must fetch with isArticle=true (og:type=article + body ≥500 chars); section URLs must fetch with isArticle=false (og:type=website). URLs verified 2026-07-29 against https://asia.nikkei.com/business/tech. Update when Nikkei archives these — pick current articles from the same path depths (2-seg /economy/<slug>, 3-seg /business/tech/semiconductors/<slug>).\",\n  \"articles\": [\n    \"https://asia.nikkei.com/business/tech/semiconductors/sk-hynix-q2-profit-surges-but-misses-market-forecast-shares-slide\",\n    \"https://asia.nikkei.com/business/tech/semiconductors/ai-chip-boom-shifts-bottleneck-to-advanced-packaging-says-at-s-ceo\",\n    \"https://asia.nikkei.com/spotlight/society/for-philippine-women-in-taiwan-s-tech-factories-motherhood-is-impossible\",\n    \"https://asia.nikkei.com/spotlight/trump-administration/us-bans-new-chinese-humanoid-robots-to-protect-ai-buildout\",\n    \"https://asia.nikkei.com/economy/natural-disasters/major-japan-quake-traps-people-inside-kumamoto-shopping-mall-factory\",\n    \"https://asia.nikkei.com/business/markets/south-korea-s-kospi-plunges-11-on-china-chip-competition-fears\",\n    \"https://asia.nikkei.com/business/companies/panasonic-to-end-tv-production-in-malaysia-cutting-jobs\"\n  ],\n  \"sections\": [\n    \"https://asia.nikkei.com/business/tech\",\n    \"https://asia.nikkei.com/business/tech/semiconductors\",\n    \"https://asia.nikkei.com/business/markets\",\n    \"https://asia.nikkei.com/economy/natural-disasters\",\n    \"https://asia.nikkei.com/spotlight/society\"\n  ],\n  \"minLinks\": 10\n}\n"
   }
 }
\ No newline at end of file

bundles/nikkei-world.nhsource.json

 {
   "format": "news-harvester-source",
   "version": 1,
-  "exportedAt": "2026-07-30T08:41:39.076Z",
+  "exportedAt": "2026-08-04T04:39:33.259Z",
   "source": {
     "id": "nikkei-world",
     "name": "日经亚洲世界",
@@ -10,6 +10,6 @@
     "vaultFolder": "日经亚洲/世界"
   },
   "files": {
-    "helpers/nikkei-world.md": "---\nsource: nikkei-world\nlistSelector: '[class*=\"StreamArticleCard\"], [class*=\"SpotlightArticleCard\"], [class*=\"SecondaryArticleCard\"]'\nlinkSelector: 'a[href]'\nurlPattern: 'asia\\.nikkei\\.com/(?:business|spotlight|economy|politics|editor-s-picks|location|opinion|features|life-arts|techasia)/[^/?#]+/.+'\nexcludeUrlPattern: '/(?:podcasts|static|infographics|member)/'\nscrollSteps: 3\nscrollWaitMs: 2000\nwaitMs: 15000\nvalidateArticle: true\nbodyMinChars: 500\nbodySelectors:\n  - '[class*=\"ArticleBody\"] p'\n  - '[class*=\"article-body\"] p'\n  - 'article p'\nbodyMinParagraphs: 3\ndateSelector: 'time[datetime]'\nauthorSelector: '[class*=\"author\"] a, [rel=\"author\"]'\nimageSelector: 'img'\nimageMinWidth: 200\nexcludeImage:\n  - logo\n  - icon\n  - avatar\n  - profile\n  - placeholder\n  - outbrainimg.com\ntitleStripSuffix: ' - Nikkei Asia$'\nmaxBodyChars: 15000\n---\n# 日经亚洲世界 抓取备忘\n\n## 列表页链接收集(`/location`)\n\n- **listSelector 用复合卡片选择器**:`[class*=\"StreamArticleCard\"], [class*=\"SpotlightArticleCard\"], [class*=\"SecondaryArticleCard\"]`。实测 `/location` 页面文章卡片分散在这三类容器里(StreamArticleCard 26 篇 + SpotlightArticleCard 3 篇 + SecondaryArticleCard 3 篇 = 32 篇)。\n- 与 nikkei-tech 同属 Nikkei 模板,卡片容器类型一致,复用同一复合选择器。\n- **urlPattern** 覆盖所有可能的文章路径段:`business`、`spotlight`、`economy`、`politics`、`editor-s-picks`、`location`、`opinion`、`features`、`life-arts`、`techasia`。`/[^/?#]+/.+` 要求至少 3 段路径。\n- **excludeUrlPattern** 剔除 `/podcasts/`、`/static/`、`/infographics/`、`/member/` 等非文章路径。\n- **validateArticle: true** 在 fetchPage 阶段用 og:type + JSON-LD + 正文字符数剔除分类页(卡片 tag 链接如 `/business/markets/commodities` 会被判 isArticle=false 并跳过)。\n- `scrollSteps: 3` 触发懒加载;Nikkei 用 `?page=N` 分页,query strip 自动排除分页链接。\n\n## 详情页正文验证\n\n`validateArticle: true` 让 `fetchPage` 采集判别信号,返回 `isArticle` 布尔;harvest 对 `isArticle === false` 直接 skip:\n\n```\nisArticle = (og:type === 'article' || JSON-LD @type ∈ {NewsArticle, Article})\n            && bodyChars >= 500\n            && bodyParagraphs >= 3\n```\n\n## 其他\n\n- 正文优先 `[class*=\"ArticleBody\"]`(Nikkei CSS Modules 正文容器)。\n- 部分文章有付费墙,bodyMinChars=500 + bodyMinParagraphs=3 过滤被截断到极短的页面。\n"
+    "helpers/nikkei-world.md": "---\nsource: nikkei-world\nlistSelector: '[class*=\"StreamArticleCard\"], [class*=\"SpotlightArticleCard\"], [class*=\"SecondaryArticleCard\"]'\nlinkSelector: 'a[href]'\nurlPattern: 'asia\\.nikkei\\.com/(?:business|spotlight|economy|politics|editor-s-picks|location|opinion|features|life-arts|techasia)/[^/?#]+(?:/.+)?'\nexcludeUrlPattern: '/(?:podcasts|static|infographics|member)/'\nscrollSteps: 3\nscrollWaitMs: 2000\nwaitMs: 15000\nvalidateArticle: true\nbodyMinChars: 500\nbodySelectors:\n  - '[class*=\"ArticleBody\"] p'\n  - '[class*=\"article-body\"] p'\n  - 'article p'\nbodyMinParagraphs: 3\ndateSelector: 'time[datetime]'\nauthorSelector: '[class*=\"author\"] a, [rel=\"author\"]'\nimageSelector: 'img'\n# 文章底部\"推荐/相关文章\"卡片缩略图与 hero 头图共用 images.ft.com CDN,\n# src 子串排除(excludeImage)无法区分,改用容器选择器整块排除。\n# 实测容器:RelatedArticle* / RelatedArticleFeature* / LatestOnTopicBottom* / Outbrain(.ob-rec-image)。\n# hero 头图在 NewsArticleHeaderImage 内,不在排除范围 → 保留。\nexcludeImageSelector: '[class*=\"RelatedArticle\"], [class*=\"RelatedArticleFeature\"], [class*=\"LatestOnTopicBottom\"], .ob-rec-image'\nimageMinWidth: 200\nexcludeImage:\n  - logo\n  - icon\n  - avatar\n  - profile\n  - placeholder\n  - outbrainimg.com\ntitleStripSuffix: ' - Nikkei Asia$'\nmaxBodyChars: 15000\n---\n# 日经亚洲世界 抓取备忘\n\n## 列表页链接收集(`/location`)\n\n- **listSelector 用复合卡片选择器**:`[class*=\"StreamArticleCard\"], [class*=\"SpotlightArticleCard\"], [class*=\"SecondaryArticleCard\"]`。实测 `/location` 页面文章卡片分散在这三类容器里(StreamArticleCard 26 篇 + SpotlightArticleCard 3 篇 + SecondaryArticleCard 3 篇 = 32 篇)。\n- 与 nikkei-tech 同属 Nikkei 模板,卡片容器类型一致,复用同一复合选择器。\n- **urlPattern** 覆盖所有可能的文章路径段:`business`、`spotlight`、`economy`、`politics`、`editor-s-picks`、`location`、`opinion`、`features`、`life-arts`、`techasia`。第三段 `(?:/.+)?` 可选——Nikkei 的 URL 结构不统一:`/business/markets/currencies/<slug>` 是 3 段,但 `/opinion/<slug>`、`/economy/<slug>`、`/politics/<slug>` 是 2 段。2 段 URL 会混入分类页(如 `/business/markets`),由 `validateArticle: true` 在 fetchPage 阶段剔除。\n- **excludeUrlPattern** 剔除 `/podcasts/`、`/static/`、`/infographics/`、`/member/` 等非文章路径。\n- **validateArticle: true** 在 fetchPage 阶段用 og:type + JSON-LD + 正文字符数剔除分类页(卡片 tag 链接如 `/business/markets/commodities` 会被判 isArticle=false 并跳过)。\n- `scrollSteps: 3` 触发懒加载;Nikkei 用 `?page=N` 分页,query strip 自动排除分页链接。\n\n## 详情页正文验证\n\n`validateArticle: true` 让 `fetchPage` 采集判别信号,返回 `isArticle` 布尔;harvest 对 `isArticle === false` 直接 skip:\n\n```\nisArticle = (og:type === 'article' || JSON-LD @type ∈ {NewsArticle, Article})\n            && bodyChars >= 500\n            && bodyParagraphs >= 3\n```\n\n## 其他\n\n- 正文优先 `[class*=\"ArticleBody\"]`(Nikkei CSS Modules 正文容器)。\n- 部分文章有付费墙,bodyMinChars=500 + bodyMinParagraphs=3 过滤被截断到极短的页面。\n"
   }
 }
\ No newline at end of file

scripts/fetcher-helper.js

@@ -64,6 +64,11 @@ const DEFAULTS = {
   imageSelector: 'img',
   imageMinWidth: 200,
   excludeImage: ['logo', 'icon', 'avatar', 'profile'],
+  // CSS selector: any <img> whose closest ancestor (or itself) matches is
+  // dropped during extraction. Use this to exclude "recommended articles" /
+  // "related articles" thumbnails that share the same CDN host as the hero
+  // image (so src-substring excludeImage can't tell them apart). null = off.
+  excludeImageSelector: null,
   noisePrefixes: [
     'Reporting by', 'Editing by', 'Access unmatched', 'Browse an unrivalled',
     'Screen for heightened', 'Sign up here', 'Reuters, the news',
@@ -129,6 +134,19 @@ function buildExtractExpr(spec) {
   const authorSelector = JSON.stringify(spec.authorSelector);
   const imageMinWidth = spec.imageMinWidth;
   const excludeImage = JSON.stringify(spec.excludeImage);
+  // imageSelector scopes which <img> nodes are candidates for download. The
+  // default 'img' (whole document) is kept for backward compat, but recipes
+  // should narrow it to the article-body container so bottom-of-page
+  // "recommended articles" thumbnails aren't pulled into assets/. Supported
+  // as a single CSS selector or a comma-separated list (querySelectorAll
+  // handles both); null/empty falls back to 'img'.
+  const imageSelector = JSON.stringify(spec.imageSelector || 'img');
+  // excludeImageSelector: drop an <img> if it (or any ancestor) matches this
+  // CSS selector. Comma-separated lists are valid. null → no container-based
+  // exclusion (existing behaviour). Used to filter "recommended articles"
+  // thumbnails that share a CDN host with the hero image.
+  const excludeImageSelector = spec.excludeImageSelector
+    ? JSON.stringify(spec.excludeImageSelector) : 'null';
   const noisePrefixes = JSON.stringify(spec.noisePrefixes);
   const titleStripRe = JSON.stringify(spec.titleStripSuffix);
   const maxBodyChars = spec.maxBodyChars;
@@ -169,12 +187,20 @@ function buildExtractExpr(spec) {
       .map(function(a){ return a.innerText.trim(); }).filter(Boolean)
       .filter(function(v,i,a){ return a.indexOf(v) === i; }).join(', ');
     if (!authors && ldAuthorNames.length) authors = ldAuthorNames.join(', ');
-    var imgs = Array.from(document.querySelectorAll('img')).map(function(img){
-      return { src: img.src, alt: img.alt || '', width: img.naturalWidth || img.width || 0 };
-    }).filter(function(i){
-      return i.src && i.src.indexOf('http') === 0 && i.width > ${imageMinWidth}
-        && !${excludeImage}.some(function(x){ return i.src.toLowerCase().indexOf(x) !== -1; });
-    }).slice(0, 6);
+    var exclImgSel = ${excludeImageSelector};
+    var imgs = Array.from(document.querySelectorAll(${imageSelector}))
+      .filter(function(img){
+        // Container-based exclusion: drop if the img (or any ancestor) sits
+        // inside a "recommended/related articles" block. Skipped when no
+        // excludeImageSelector is configured.
+        return !exclImgSel || !img.closest(exclImgSel);
+      })
+      .map(function(img){
+        return { src: img.src, alt: img.alt || '', width: img.naturalWidth || img.width || 0 };
+      }).filter(function(i){
+        return i.src && i.src.indexOf('http') === 0 && i.width > ${imageMinWidth}
+          && !${excludeImage}.some(function(x){ return i.src.toLowerCase().indexOf(x) !== -1; });
+      }).slice(0, 6);
     var body = '';
     var bodyParagraphs = 0;
     var sels = ${bodySelectors};

scripts/inspect-source.js

@@ -222,6 +222,8 @@ bodySelectors:
 bodyMinParagraphs: 3
 dateSelector: 'time[datetime]'
 authorSelector: '[rel="author"], [class*="author"] a'
+# Scope to the article-body container (e.g. '[class*="ArticleBody"] img, article img')
+# so bottom-of-page "recommended articles" thumbnails aren't downloaded into assets/.
 imageSelector: 'img'
 imageMinWidth: 200
 excludeImage:
@@ -229,6 +231,9 @@ excludeImage:
   - icon
   - avatar
   - profile
+# excludeImageSelector drops imgs whose ancestor matches — use for
+# "recommended/related articles" thumbnails sharing the hero image's CDN host.
+# excludeImageSelector: '[class*="RelatedArticle"], [class*="RecommendedArticle"]'
 titleStripSuffix: ''
 maxBodyChars: 15000
 ---

scripts/source-manage.js

@@ -201,6 +201,8 @@ bodySelectors:
 bodyMinParagraphs: 3
 dateSelector: 'time[datetime]'
 authorSelector: '[rel="author"], [class*="author"] a'
+# Scope to the article-body container (e.g. '[class*="ArticleBody"] img, article img')
+# so bottom-of-page "recommended articles" thumbnails aren't downloaded into assets/.
 imageSelector: 'img'
 imageMinWidth: 200
 excludeImage:
@@ -208,6 +210,9 @@ excludeImage:
   - icon
   - avatar
   - profile
+# excludeImageSelector drops imgs whose ancestor matches — use for
+# "recommended/related articles" thumbnails sharing the hero image's CDN host.
+# excludeImageSelector: '[class*="RelatedArticle"], [class*="RecommendedArticle"]'
 titleStripSuffix: ''
 maxBodyChars: 15000
 ---