{"id":"f5594010-00c7-415a-8689-b21553741e94","entityType":"agent","slug":"clawhub-langhuachuanshi-silas-wechat-article-search","name":"Silas WeChat Article Search","canonicalUrl":"https://www.xpersona.co/agent/clawhub-langhuachuanshi-silas-wechat-article-search","canonicalPath":"/agent/clawhub-langhuachuanshi-silas-wechat-article-search","generatedAt":"2026-10-12T21:05:24.683Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T22:24:23.989Z","emptyReason":null},"description":"微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。 Skill: Silas WeChat Article Search Owner: langhuachuanshi Summary: 微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。 Tags: latest:2.0.0 Version history: v2.0.0 | 2026-04-18T14:19:47.091Z | user v2.0: 合并parser+search双技能，Python解析全文(iPhone UA绕验证)，段落去重，零Node依赖，Serper转载兜底 v1.1.0 | 2026-04-18T12:40:16.086Z | user 去掉Node脚本和cheerio依赖，纯agent工具实现，零依赖 v1.0.0 | 2026-04-18T12:31:50.444Z | user Initial release: 微信公众号文章搜索，","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 985 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s172yjpf05bfj3wjfrwx88v8sx83hf31:silas-wechat-article-search","sourceUrl":"https://clawhub.ai/langhuachuanshi/silas-wechat-article-search","homepage":"https://clawhub.ai/langhuachuanshi/skills/silas-wechat-article-search","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/langhuachuanshi/silas-wechat-article-search","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/langhuachuanshi/skills/silas-wechat-article-search","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。 Skill: Silas WeChat Article Search Owner: langhuachuanshi Summary: 微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:24:23.989Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:24:23.989Z","emptyReason":null},"stars":null,"forks":null,"downloads":985,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"2.0.0","tractionLabel":"985 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:24:23.854Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T22:24:23.989Z","lastCrawledAt":"2026-10-11T22:24:23.854Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T22:24:23.854Z","lastVerifiedAt":null,"highlights":[{"version":"2.0.0","createdAt":"2026-04-18T14:19:47.091Z","changelog":"v2.0: 合并parser+search双技能，Python解析全文(iPhone UA绕验证)，段落去重，零Node依赖，Serper转载兜底","fileCount":5,"zipByteSize":6530},{"version":"1.1.0","createdAt":"2026-04-18T12:40:16.086Z","changelog":"去掉Node脚本和cheerio依赖，纯agent工具实现，零依赖","fileCount":3,"zipByteSize":2074},{"version":"1.0.0","createdAt":"2026-04-18T12:31:50.444Z","changelog":"Initial release: 微信公众号文章搜索，搜狗+新榜双源","fileCount":5,"zipByteSize":9587}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s172yjpf05bfj3wjfrwx88v8sx83hf31:silas-wechat-article-search","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-langhuachuanshi-silas-wechat-article-search/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-langhuachuanshi-silas-wechat-article-search/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-langhuachuanshi-silas-wechat-article-search/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-langhuachuanshi-silas-wechat-article-search/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-langhuachuanshi-silas-wechat-article-search/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-langhuachuanshi-silas-wechat-article-search/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-12T21:05:24.683Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-langhuachuanshi-silas-wechat-article-search/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-langhuachuanshi-silas-wechat-article-search/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-langhuachuanshi-silas-wechat-article-search/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-langhuachuanshi-silas-wechat-article-search/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T22:24:23.989Z","emptyReason":null},"readme":"Skill: Silas WeChat Article Search\n\nOwner: langhuachuanshi\n\nSummary: 微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。\n\nTags: latest:2.0.0\n\nVersion history:\n\nv2.0.0 | 2026-04-18T14:19:47.091Z | user\n\nv2.0: 合并parser+search双技能，Python解析全文(iPhone UA绕验证)，段落去重，零Node依赖，Serper转载兜底\n\nv1.1.0 | 2026-04-18T12:40:16.086Z | user\n\n去掉Node脚本和cheerio依赖，纯agent工具实现，零依赖\n\nv1.0.0 | 2026-04-18T12:31:50.444Z | user\n\nInitial release: 微信公众号文章搜索，搜狗+新榜双源\n\nArchive index:\n\nArchive v2.0.0: 5 files, 6530 bytes\n\nFiles: references/example-output.json (444b), scripts/parse_article.py (4399b), skill-card.md (2422b), SKILL.md (4087b), _meta.json (146b)\n\nFile v2.0.0:SKILL.md\n\n---\nname: silas_wechat_article_search\ndescription: 微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。\nmetadata:\n  openclaw:\n    os: linux\n---\n\n# 微信公众号文章搜索与解析 v2.0\n\n搜索微信公众号文章 → 解析全文 → 评分 → 入库知识库。\n\n## 搜索源（按优先级）\n\n### 源1：搜狗微信（主力，零依赖）\n```bash\ncurl -s \"https://weixin.sogou.com/weixin?type=2&query=关键词\" \\\n  -H \"User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36\"\n```\n用 Python 正则提取标题和链接，返回搜狗中间链接列表。\n\n### 源2：新榜（补充）\n```bash\ncurl -s \"https://google.serper.dev/search\" \\\n  -H \"X-API-KEY: $SERPER_API_KEY\" \\\n  -d '{\"q\":\"site:newrank.cn 关键词\",\"num\":10}'\n```\n\n### 源3：Serper 转载兜底\n当微信原文无法解析时，搜索转载版：\n```bash\ncurl -s \"https://google.serper.dev/search\" \\\n  -H \"X-API-KEY: $SERPER_API_KEY\" \\\n  -d '{\"q\":\"文章标题\",\"num\":5}'\n```\n优先选新浪/搜狐/网易等全文转载。\n\n## 内容解析（Python 脚本）\n\n**核心脚本**：`scripts/parse_article.py`\n\n### 依赖\n```bash\npip3 install requests beautifulsoup4\n```\n\n### 用法\n```bash\npython3 scripts/parse_article.py \"https://mp.weixin.qq.com/s/xxxxx\"\npython3 scripts/parse_article.py \"URL\" --save\npython3 scripts/parse_article.py \"URL\" --save --output article.json\n```\n\n### 输出 JSON\n```json\n{\n  \"title\": \"文章标题\",\n  \"author\": \"公众号名称\",\n  \"publish_time\": \"2026-04-18\",\n  \"content\": \"正文全文...\",\n  \"word_count\": 5594,\n  \"images_count\": 21,\n  \"images\": [\"url1\", \"url2\", ...],\n  \"url\": \"原始链接\",\n  \"parsed_at\": \"2026-04-18 22:00:00\"\n}\n```\n\n### 原理\n- **iPhone UA** 绕过微信验证（关键！）\n- **BeautifulSoup** 解析 `rich_media_content` 提取正文\n- **段落结构保留**，过滤 <10 字的噪声\n- **图片提取**：`data-src` 属性（微信防盗链图）\n\n### 微信原文解析失败时\n1. Serper 搜转载版（新浪/搜狐/网易）\n2. web_fetch 抓转载全文\n3. browser-search 兜底\n\n## 入库流程\n\n### 1. 搜索\n```\n选词（从 web-keywords.json）→ 搜狗搜索 → 新榜补充 → 合并去重\n```\n\n### 2. 解析\n```\n对每篇目标文章：\na. 先用 Python 脚本解析微信原文\nb. 失败 → Serper 搜转载 → web_fetch 抓全文\nc. 提取：标题、作者、正文、图片\n```\n\n### 3. 评分\n```\n5 维度评分（同 web-search 技能标准）：\n- 数据密度 30%、实操性 25%、时效性 20%、相关性 15%、来源权威 10%\n- < 5.0 不入库\n- ≥ 8.5 通知管理员\n```\n\n### 4. 去重\n```\na. feishu_search_doc_wiki 搜索知识库标题\nb. memory/collect-log.json 查历史\nc. URL + 标题去重\n```\n\n### 5. 入库\n```\na. 读 wiki-directory-manager 技能匹配目录\nb. feishu_create_doc 创建文档（标题不带评分）\nc. 正文格式：\n   > 来源：URL\n   > 发布日期：YYYY-MM-DD\n   > 采集日期：YYYY-MM-DD\n   > 评分：X.X 🟢/🟡/🟠/🔴\n   \n   正文内容...\nd. 有信息量图片 → 保存本地 → feishu_doc_media insert\ne. 写多维表格索引（目录必须和实际一致）\n```\n\n## 图片处理\n\n- **保存标准**：数据图表/流程图/对比截图/产品截图\n- **跳过**：装饰图/广告/头像/logo\n- 每篇最多 10 张，单张 <20MB\n- 保存路径：`/tmp/openclaw/images/`\n\n## 踩坑指南\n\n- **微信验证码**：iPhone UA 可绕过，Desktop UA 会被拦截\n- **搜狗中间链接**：不能直接 web_fetch，需先解析跳转或用 Python 脚本\n- **微信图片防盗链**：`data-src` 是真实地址，但直接访问需要 Referer\n- **频繁请求被封**：搜狗搜索间隔 3-5 秒\n- **转载版内容可能有删减**：优先用微信原文，转载版做兜底\n- **不要用 Node.js**：Python 脚本足够，避免 cheerio 依赖\n- **save_to_feishu.py 不用**：飞书写入用 agent 原生工具（feishu_create_doc）\n\n## 频率\n\nCron：每小时第22分钟（ID: de3ee2d3）\n每次 1 个关键词，搜索 → 解析 → 评分 → 入库\n\nFile v2.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn78r3ca13npsxrn5f905res8n821ssm\",\n  \"slug\": \"silas-wechat-article-search\",\n  \"version\": \"2.0.0\",\n  \"publishedAt\": 1776521987091\n}\n\nFile v2.0.0:references/example-output.json\n\n{\n  \"query\": \"AI 一人公司 创业\",\n  \"total\": 5,\n  \"articles\": [\n    {\n      \"title\": \"AI时代一人公司怎么赚钱？\",\n      \"url\": \"https://weixin.sogou.com/link?url=xxx\",\n      \"summary\": \"随着AI工具的普及，越来越多的人开始尝试一人公司模式...\",\n      \"datetime\": \"2026-04-15 10:30:00\",\n      \"date_text\": \"2026年04月15日\",\n      \"date_description\": \"3天前\",\n      \"source\": \"AI创业笔记\"\n    }\n  ]\n}\n\nFile v2.0.0:skill-card.md\n\n## Description:\n\n微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[langhuachuanshi](https://clawhub.ai/user/langhuachuanshi)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and content operations agents use this skill to search WeChat public-account articles, parse article text and images, score and de-duplicate results, and publish selected content to a knowledge base.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Search terms and article metadata may be sent to Sogou, Serper, and article-source sites.\n\nMitigation: Use the skill only where those external requests are acceptable, and review search terms before execution.\n\nRisk: Collected content can be written persistently to Feishu knowledge-base destinations.\n\nMitigation: Require explicit confirmation before Feishu writes and verify the target directory before publishing.\n\nRisk: The workflow can fetch user- or agent-selected article URLs without a stated allowlist.\n\nMitigation: Add URL allowlisting for approved search and article domains before unattended use.\n\nRisk: Runtime Python dependencies are not pinned in the artifact.\n\nMitigation: Pin and review dependency versions before deployment.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/langhuachuanshi/skills/silas-wechat-article-search)\n- [Example search output](references/example-output.json)\n- [Sogou WeChat search endpoint](https://weixin.sogou.com/weixin?type=2&query=%E5%85%B3%E9%94%AE%E8%AF%8D)\n- [Serper search endpoint](https://google.serper.dev/search)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown instructions with bash examples, Python parser usage, and JSON article records.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires SERPER_API_KEY for Serper fallback; parser output can be printed or saved as JSON.]\n\n## Skill Version(s):\n\n2.0.0 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.1.0: 3 files, 2074 bytes\n\nFiles: references/example-output.json (444b), SKILL.md (2257b), _meta.json (146b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: silas_wechat_article_search\ndescription: 微信公众号文章搜索。搜狗微信+新榜双源，纯 agent 工具实现，零依赖。\nmetadata:\n  openclaw:\n    os: linux\n---\n\n# 微信公众号文章搜索\n\n通过搜狗微信和新榜搜索公众号文章，纯 agent 工具实现，无需 Node 脚本或第三方依赖。\n\n## 搜索源\n\n### 源1：搜狗微信（主力）\n\n```bash\n# 直接用 web_fetch 抓取搜狗搜索结果\nweb_fetch \"https://weixin.sogou.com/weixin?type=2&query=关键词\"\n```\n\n返回 HTML 中包含文章列表，用 agent 解析提取：\n- 标题\n- 链接（搜狗中间链接）\n- 摘要\n- 公众号名称\n- 发布时间\n\n**注意**：搜狗返回的是中间链接（`weixin.sogou.com/link?url=...`），需浏览器跳转到真实微信链接。直接 web_fetch 中间链接会 403。\n\n### 源2：新榜（补充）\n\n```bash\n# 用 Serper 搜索新榜\ncurl -s \"https://google.serper.dev/search\" \\\n  -H \"X-API-KEY: $SERPER_API_KEY\" \\\n  -d '{\"q\":\"site:newrank.cn 关键词\",\"num\":10}'\n\n# 或用 browser-search\nbrowser-search \"关键词 site:newrank.cn\"\n```\n\n### 源3：browser-search 兜底\n\n```bash\n# 直接搜微信公众号文章\nbrowser-search \"关键词 微信公众号\"\n```\n\n## 文章内容提取\n\n拿到文章链接后：\n\n1. **微信原文链接**：`web_fetch` + `?scene=1` 后缀\n2. **搜狗中间链接**：用 `browser` 工具打开后提取真实链接\n3. **403 时**：用 `browser-search` 或 `browser` 工具兜底\n\n```bash\n# 微信文章加 scene=1 参数更容易抓取\nweb_fetch \"https://mp.weixin.qq.com/s/xxxxx?scene=1\"\n```\n\n## 输出格式\n\n```\n📊 搜索：[关键词] | 来源：搜狗+新榜 | 结果：X条\n\n| # | 标题 | 公众号 | 时间 | 来源 |\n|---|------|--------|------|------|\n| 1 | xxx | xxx | 2026-04-18 | 搜狗 |\n```\n\n## 去重\n\n- URL 去重（同一文章不同搜索源可能重复）\n- 标题相似度去重\n\n## 踩坑指南\n\n- **搜狗反爬**：频繁请求会被封 IP，每次搜索间隔 3-5 秒\n- **微信文章 403**：不加 `?scene=1` 很容易被拦截\n- **搜狗中间链接**：不能直接 fetch，需要浏览器跳转\n- **新榜需要登录**：部分内容需要登录才能查看\n- **不要用 Node 脚本**：agent 原生工具足够，避免额外依赖\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn78r3ca13npsxrn5f905res8n821ssm\",\n  \"slug\": \"silas-wechat-article-search\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1776516016086\n}\n\nFile v1.1.0:references/example-output.json\n\n{\n  \"query\": \"AI 一人公司 创业\",\n  \"total\": 5,\n  \"articles\": [\n    {\n      \"title\": \"AI时代一人公司怎么赚钱？\",\n      \"url\": \"https://weixin.sogou.com/link?url=xxx\",\n      \"summary\": \"随着AI工具的普及，越来越多的人开始尝试一人公司模式...\",\n      \"datetime\": \"2026-04-15 10:30:00\",\n      \"date_text\": \"2026年04月15日\",\n      \"date_description\": \"3天前\",\n      \"source\": \"AI创业笔记\"\n    }\n  ]\n}\n\nArchive v1.0.0: 5 files, 9587 bytes\n\nFiles: package.json (126b), references/example-output.json (444b), scripts/search_wechat.js (23261b), SKILL.md (1823b), _meta.json (146b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: silas-wechat-search\ndescription: 搜索微信公众号文章。通过搜狗微信搜索获取文章列表，支持关键词检索，返回标题、摘要、发布时间、来源公众号与链接。可作为通用工具使用，不依赖特定知识库。\nmetadata:\n  openclaw:\n    version: 1.0.0\n---\n\n# 微信公众号文章搜索\n\n## 概述\n\n通过搜狗微信搜索获取微信公众号文章列表。支持关键词检索、数量限制、JSON 输出、真实 URL 解析。\n\n## 依赖\n\n```bash\nnpm install cheerio\n```\n\n## 搜索\n\n```bash\nnode scripts/search_wechat.js \"关键词\" -n 10\n```\n\n### 参数\n\n| 参数 | 说明 | 默认值 |\n|------|------|--------|\n| `query` | 搜索关键词（必填） | - |\n| `-n, --num` | 返回数量 | 10（最大50） |\n| `-o, --output` | 输出 JSON 文件路径 | stdout |\n| `-r, --resolve-url` | 解析真实微信文章 URL | false |\n\n## 输出字段\n\n每篇文章包含：`title`、`url`、`summary`、`datetime`、`date_text`、`date_description`、`source`（公众号名称）。\n\n## 文章内容提取\n\n获取到文章 URL 后，用以下方式提取正文：\n\n1. **首选 web_fetch**：对 `mp.weixin.qq.com` 链接直接提取\n2. **兜底 browser-search**：若 web_fetch 失败，用 browser-search 技能打开页面提取\n\n```bash\n# web_fetch 提取示例\n# URL 格式：https://mp.weixin.qq.com/s/xxxxx\n```\n\n## 新榜搜索（备用源）\n\n当搜狗搜索结果不足或失败时，可用 browser-search 技能在新榜搜索：\n\n1. 用 browser-search 打开 `https://www.newrank.cn/public/info/list.html?period=day&type=data_article`\n2. 在搜索框输入关键词\n3. 提取搜索结果列表\n\n## 注意事项\n\n- 本工具仅用于学习和研究目的\n- 搜狗微信有反爬机制，解析真实 URL 可能失败\n- 避免频繁请求，IP 可能被封禁\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn78r3ca13npsxrn5f905res8n821ssm\",\n  \"slug\": \"silas-wechat-article-search\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1776515510444\n}\n\nFile v1.0.0:references/example-output.json\n\n{\n  \"query\": \"AI 一人公司 创业\",\n  \"total\": 5,\n  \"articles\": [\n    {\n      \"title\": \"AI时代一人公司怎么赚钱？\",\n      \"url\": \"https://weixin.sogou.com/link?url=xxx\",\n      \"summary\": \"随着AI工具的普及，越来越多的人开始尝试一人公司模式...\",\n      \"datetime\": \"2026-04-15 10:30:00\",\n      \"date_text\": \"2026年04月15日\",\n      \"date_description\": \"3天前\",\n      \"source\": \"AI创业笔记\"\n    }\n  ]\n}\n\nFile v1.0.0:package.json\n\n{\n  \"name\": \"silas-wechat-search\",\n  \"version\": \"1.0.0\",\n  \"private\": true,\n  \"dependencies\": {\n    \"cheerio\": \"^1.0.0\"\n  }\n}","readmeExcerpt":"Skill: Silas WeChat Article Search Owner: langhuachuanshi Summary: 微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。 Tags: latest:2.0.0 Version history: v2.0.0 | 2026-04-18T14:19:47.091Z | user v2.0: 合并parser+search双技能，Python解析全文(iPhone UA绕验证)，段落去重，零Node依赖，Serper转载兜底 v1.1.0 | 2026-04-18T12:40:16.086Z | user 去掉Node脚本和cheerio依赖，纯agent工具实现，零依赖 v1.0.0 | 2026-04-18T12:31:50.444Z | user Initial release: 微信公众号文章搜索，","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"curl -s \"https://weixin.sogou.com/weixin?type=2&query=关键词\" \\\n  -H \"User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36\""},{"language":"bash","snippet":"curl -s \"https://weixin.sogou.com/weixin?type=2&query=关键词\" \\\n  -H \"User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36\""},{"language":"bash","snippet":"curl -s \"https://google.serper.dev/search\" \\\n  -H \"X-API-KEY: $SERPER_API_KEY\" \\\n  -d '{\"q\":\"site:newrank.cn 关键词\",\"num\":10}'"},{"language":"bash","snippet":"curl -s \"https://google.serper.dev/search\" \\\n  -H \"X-API-KEY: $SERPER_API_KEY\" \\\n  -d '{\"q\":\"site:newrank.cn 关键词\",\"num\":10}'"},{"language":"bash","snippet":"curl -s \"https://google.serper.dev/search\" \\\n  -H \"X-API-KEY: $SERPER_API_KEY\" \\\n  -d '{\"q\":\"文章标题\",\"num\":5}'"},{"language":"bash","snippet":"curl -s \"https://google.serper.dev/search\" \\\n  -H \"X-API-KEY: $SERPER_API_KEY\" \\\n  -d '{\"q\":\"文章标题\",\"num\":5}'"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: silas_wechat_article_search\ndescription: 微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。\nmetadata:\n  openclaw:\n    os: linux\n---\n\n# 微信公众号文章搜索与解析 v2.0\n\n搜索微信公众号文章 → 解析全文 → 评分 → 入库知识库。\n\n## 搜索源（按优先级）\n\n### 源1：搜狗微信（主力，零依赖）\n```bash\ncurl -s \"https://weixin.sogou.com/weixin?type=2&query=关键词\" \\\n  -H \"User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36\"\n```\n用 Python 正则提取标题和链接，返回搜狗中间链接列表。\n\n### 源2：新榜（补充）\n```bash\ncurl -s \"https://google.serper.dev/search\" \\\n  -H \"X-API-KEY: $SERPER_API_KEY\" \\\n  -d '{\"q\":\"site:newrank.cn 关键词\",\"num\":10}'\n```\n\n### 源3：Serper 转载兜底\n当微信原文无法解析时，搜索转载版：\n```bash\ncurl -s \"https://google.serper.dev/search\" \\\n  -H \"X-API-KEY: $SERPER_API_KEY\" \\\n  -d '{\"q\":\"文章标题\",\"num\":5}'\n```\n优先选新浪/搜狐/网易等全文转载。\n\n## 内容解析（Python 脚本）\n\n**核心脚本**：`scripts/parse_article.py`\n\n### 依赖\n```bash\npip3 install requests beautifulsoup4\n```\n\n### 用法\n```bash\npython3 scripts/parse_article.py \"https://mp.weixin.qq.com/s/xxxxx\"\npython3 scripts/parse_article.py \"URL\" --save\npython3 scripts/parse_article.py \"URL\" --save --output article.json\n```\n\n### 输出 JSON\n```json\n{\n  \"title\": \"文章标题\",\n  \"author\": \"公众号名称\",\n  \"publish_time\": \"2026-04-18\",\n  \"content\": \"正文全文...\",\n  \"word_count\": 5594,\n  \"images_count\": 21,\n  \"images\": [\"url1\", \"url2\", ...],\n  \"url\": \"原始链接\",\n  \"parsed_at\": \"2026-04-18 22:00:00\"\n}\n```\n\n### 原理\n- **iPhone UA** 绕过微信验证（关键！）\n- **BeautifulSoup** 解析 `rich_media_content` 提取正文\n- **段落结构保留**，过滤 <10 字的噪声\n- **图片提取**：`data-src` 属性（微信防盗链图）\n\n### 微信原文解析失败时\n1. Serper 搜转载版（新浪/搜狐/网易）\n2. web_fetch 抓转载全文\n3. browser-search 兜底\n\n## 入库流程\n\n### 1. 搜索\n```\n选词（从 web-keywords.json）→ 搜狗搜索 → 新榜补充 → 合并去重\n```\n\n### 2. 解析\n```\n对每篇目标文章：\na. 先用 Python 脚本解析微信原文\nb. 失败 → Serper 搜转载 → web_fetch 抓全文\nc. 提取：标题、作者、正文、图片\n```\n\n### 3. 评分\n```\n5 维度评分（同 web-search 技能标准）：\n- 数据密度 30%、实操性 25%、时效性 20%、相关性 15%、来源权威 10%\n- < 5.0 不入库\n- ≥ 8.5 通知管理员\n```\n\n### 4. 去重\n```\na. feishu_search_doc_wiki 搜索知识库标题\nb. memory/collect-log.json 查历史\nc. URL + 标题去重\n```\n\n### 5. 入库\n```\na. 读 wiki-directory-manager 技能匹配目录\nb. feishu_create_doc 创建文档（标题不带评分）\nc. 正文格式：\n   > 来源：URL\n   > 发布日期：YYYY-MM-DD\n   > 采集日期：YYYY-MM-DD\n   > 评分：X.X 🟢/🟡/🟠/🔴\n   \n   正文内容...\nd. 有信息量图片 → 保存本地 → feishu_doc_media insert\ne. 写多维表格索引（目录必须和实际一致）\n```\n\n## 图片处理\n\n- **保存标准**：数据图表/流程图/对比截图/产品截图\n- **跳过**：装饰图/广告/头像/logo\n- 每篇最多 10 张，单张 <20MB\n- 保存路径：`/tmp/openclaw/images/`\n\n## 踩坑指南\n\n- **微信验证码**：iPhone UA 可绕过，Desktop UA 会被拦截\n- **搜狗中间链接**：不能直接 web_fetch，需先解析跳转或用 Python 脚本\n- **微信图片防盗链**：`data-src` 是真实地址，但直接访问需要 Referer\n- **频繁请求被封**：搜狗搜索间隔 3-5 秒\n- **转载版内容可能有删减**：优先用微信原文，转载版做兜底\n- **不要用 Node.js**：Python 脚本足够，避免 cheerio 依赖\n- **save_to_feishu.py 不用**：飞书写入用 agent 原生工具（feishu_create_doc）\n\n## 频率\n\nCron：每小时第22分钟（ID: de3ee2d3）\n每次 1 个关键词，搜索 → 解析 → 评分 → 入库"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn78r3ca13npsxrn5f905res8n821ssm\",\n  \"slug\": \"silas-wechat-article-search\",\n  \"version\": \"2.0.0\",\n  \"publishedAt\": 1776521987091\n}"},{"path":"references/example-output.json","content":"{\n  \"query\": \"AI 一人公司 创业\",\n  \"total\": 5,\n  \"articles\": [\n    {\n      \"title\": \"AI时代一人公司怎么赚钱？\",\n      \"url\": \"https://weixin.sogou.com/link?url=xxx\",\n      \"summary\": \"随着AI工具的普及，越来越多的人开始尝试一人公司模式...\",\n      \"datetime\": \"2026-04-15 10:30:00\",\n      \"date_text\": \"2026年04月15日\",\n      \"date_description\": \"3天前\",\n      \"source\": \"AI创业笔记\"\n    }\n  ]\n}"},{"path":"skill-card.md","content":"## Description:\n\n微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[langhuachuanshi](https://clawhub.ai/user/langhuachuanshi)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and content operations agents use this skill to search WeChat public-account articles, parse article text and images, score and de-duplicate results, and publish selected content to a knowledge base.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Search terms and article metadata may be sent to Sogou, Serper, and article-source sites.\n\nMitigation: Use the skill only where those external requests are acceptable, and review search terms before execution.\n\nRisk: Collected content can be written persistently to Feishu knowledge-base destinations.\n\nMitigation: Require explicit confirmation before Feishu writes and verify the target directory before publishing.\n\nRisk: The workflow can fetch user- or agent-selected article URLs without a stated allowlist.\n\nMitigation: Add URL allowlisting for approved search and article domains before unattended use.\n\nRisk: Runtime Python dependencies are not pinned in the artifact.\n\nMitigation: Pin and review dependency versions before deployment.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/langhuachuanshi/skills/silas-wechat-article-search)\n- [Example search output](references/example-output.json)\n- [Sogou WeChat search endpoint](https://weixin.sogou.com/weixin?type=2&query=%E5%85%B3%E9%94%AE%E8%AF%8D)\n- [Serper search endpoint](https://google.serper.dev/search)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown instructions with bash examples, Python parser usage, and JSON article records.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires SERPER_API_KEY for Serper fallback; parser output can be printed or saved as JSON.]\n\n## Skill Version(s):\n\n2.0.0 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。 Skill: Silas WeChat Article Search Owner: langhuachuanshi Summary: 微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。 Tags: latest:2.0.0 Version history: v2.0.0 | 2026-04-18T14:19:47.091Z | user v2.0: 合并parser+search双技能，Python解析全文(iPhone UA绕验证)，段落去重，零Node依赖，Serper转载兜底 v1.1.0 | 2026-04-18T12:40:16.086Z | user 去掉Node脚本和cheerio依赖，纯agent工具实现，零依赖 v1.0.0 | 2026-04-18T12:31:50.444Z | user Initial release: 微信公众号文章搜索，","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":773,"uniquenessScore":58,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T22:24:23.989Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T22:24:23.989Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-12T21:05:24.683Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}