使用 Huginn 实现微信公众号全文 RSS

wechat.json

{
  "schema_version": 1,
  "name": "WeChat",
  "description": "微信公众号全文 RSS",
  "source_url": false,
  "guid": "dd67102f09869c2228f8ed903a32d063",
  "tag_fg_color": "#333333",
  "tag_bg_color": "#66ff66",
  "icon": "leaf",
  "exported_at": "2019-01-12T10:56:41Z",
  "agents": [
    {
      "type": "Agents::WebsiteAgent",
      "name": "0 获取微信公众号文章",
      "disabled": false,
      "guid": "00a23c266080e989591e35697d91b21e",
      "options": {
        "expected_update_period_in_days": "2",
        "url": [
          "http://weixin.sogou.com/weixin?type=1&s_from=input&query=pongba_mindhacks",
          "http://weixin.sogou.com/weixin?type=1&s_from=input&query=ling-lunch",
          "http://weixin.sogou.com/weixin?type=1&s_from=input&query=noon-story",
          "http://weixin.sogou.com/weixin?type=1&s_from=input&query=mzmojo"
        ],
        "type": "html",
        "mode": "on_change",
        "extract": {
          "title": {
            "css": "#sogou_vr_11002301_box_0 > dl:last>dd>a",
            "value": ".//text()"
          },
          "url": {
            "css": "#sogou_vr_11002301_box_0 > dl:last>dd>a",
            "value": "@href"
          }
        },
        "user_agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X x.y; rv:42.0) Gecko/20100101 Firefox/42.0"
      },
      "schedule": "every_12h",
      "keep_events_for": 172800,
      "propagate_immediately": true
    },
    {
      "type": "Agents::DataOutputAgent",
      "name": "4 输出RSS",
      "disabled": false,
      "guid": "1ea34bb7e56575e6c007bf2e2f48b990",
      "options": {
        "secrets": [
          "wechat202"
        ],
        "expected_receive_period_in_days": 2,
        "template": {
          "title": "微信公众号",
          "description": "微信公众号全文",
          "item": {
            "title": "{{author}} | {{title}}",
            "description": "{{fulltext}}",
            "link": "{{url}}"
          },
          "icon": "https://res.wx.qq.com/mmbizwap/zh_CN/htmledition/images/icon/common/favicon22c41b.ico"
        },
        "rss_content_type": "text/xml"
      },
      "propagate_immediately": true
    },
    {
      "type": "Agents::DeDuplicationAgent",
      "name": "1 标题去重",
      "disabled": false,
      "guid": "6406a562f112d0686bf2ae24afcac902",
      "options": {
        "property": "{{title}}",
        "lookback": "200",
        "expected_update_period_in_days": "6"
      },
      "keep_events_for": 345600,
      "propagate_immediately": true
    },
    {
      "type": "Agents::TriggerAgent",
      "name": "2 过滤广告",
      "disabled": false,
      "guid": "822097071177a8c9d57eb0aea8b7554f",
      "options": {
        "expected_receive_period_in_days": "6",
        "keep_event": "true",
        "rules": [
          {
            "type": "!regex",
            "value": "(市集)|(广告)|(推广)|(招人)|(限时)|(福利)",
            "path": "title"
          }
        ],
        "message": "没有看到广告，放行！"
      },
      "keep_events_for": 259200,
      "propagate_immediately": true
    },
    {
      "type": "Agents::WebsiteAgent",
      "name": "3 获取文章全文",
      "disabled": false,
      "guid": "c5b16d43997a5195533911e8d1824711",
      "options": {
        "expected_update_period_in_days": "2",
        "url_from_event": "{{url}}",
        "type": "html",
        "mode": "merge",
        "extract": {
          "fulltext": {
            "css": "#js_content",
            "value": "."
          },
          "title_": {
            "css": "#activity-name",
            "value": "normalize-space(.)"
          },
          "author": {
            "css": "#profileBt > a",
            "value": "normalize-space(.)"
          }
        },
        "template": {
          "fulltext": "{{ fulltext |strip_newlines|replace: \"<br>\",\"\" | regex_replace:'data-src','src'}}"
        },
        "user_agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X x.y; rv:42.0) Gecko/20100101 Firefox/42.0"
      },
      "schedule": "every_12h",
      "keep_events_for": 604800,
      "propagate_immediately": true
    }
  ],
  "links": [
    {
      "source": 0,
      "receiver": 2
    },
    {
      "source": 2,
      "receiver": 3
    },
    {
      "source": 3,
      "receiver": 4
    },
    {
      "source": 4,
      "receiver": 1
    }
  ],
  "control_links": [

  ]
}

@cdpath 还有这中图文也不行https://mp.weixin.qq.com/s?timestamp=1527129225&src=3&ver=1&signature=J1vwPTXibs8iYk-lr9ahXu94S0JntHvzxKYeAMId*KeP-Wb7Dnw0cMZtJVOUjQ83DcbGmOKnOFgPNw2GTIuAjOAOYEJOoKYkoxX8cc2EwWWKfHTmzKpqcQ*H9UE0pzTWkI4gPkD2nc*N7dwjHZgxdMmLOB0DWWAj*4RzTQ0GJ-w=

最新的反爬虫该Scenario 不可用，我写了个新的 https://gist.github.com/dequn/674b0401c1f31f7919b112ad64640552。

楼主这个现在还能使用吗 @cdpath