抓取获取36氪热榜文章内容

YAML 源码

app:
  description: 本工作流主要是通过抓取获取36氪热榜文章内容实现新闻获取，作者：wwwzhouhui
  icon: 🤖
  icon_background: '#FFEAD5'
  mode: workflow
  name: 抓取获取36氪热榜文章内容
  use_icon_as_answer_icon: false
kind: app
version: 0.1.2
workflow:
  conversation_variables: []
  environment_variables: []
  features:
    file_upload:
      allowed_file_extensions:
      - .JPG
      - .JPEG
      - .PNG
      - .GIF
      - .WEBP
      - .SVG
      allowed_file_types:
      - image
      allowed_file_upload_methods:
      - local_file
      - remote_url
      enabled: false
      image:
        enabled: false
        number_limits: 3
        transfer_methods:
        - local_file
        - remote_url
      number_limits: 3
    opening_statement: ''
    retriever_resource:
      enabled: true
    sensitive_word_avoidance:
      enabled: false
    speech_to_text:
      enabled: false
    suggested_questions: []
    suggested_questions_after_answer:
      enabled: false
    text_to_speech:
      enabled: false
      language: ''
      voice: ''
  graph:
    edges:
    - data:
        isInIteration: false
        sourceType: start
        targetType: http-request
      id: 1731575837911-source-1731575885694-target
      source: '1731575837911'
      sourceHandle: source
      target: '1731575885694'
      targetHandle: target
      type: custom
      zIndex: 0
    - data:
        isInIteration: false
        sourceType: http-request
        targetType: llm
      id: 1731575885694-source-1731575963411-target
      source: '1731575885694'
      sourceHandle: source
      target: '1731575963411'
      targetHandle: target
      type: custom
      zIndex: 0
    - data:
        isInIteration: false
        sourceType: llm
        targetType: code
      id: 1731575963411-source-1731576019023-target
      source: '1731575963411'
      sourceHandle: source
      target: '1731576019023'
      targetHandle: target
      type: custom
      zIndex: 0
    - data:
        isInIteration: false
        sourceType: code
        targetType: iteration
      id: 1731576019023-source-1731576069313-target
      source: '1731576019023'
      sourceHandle: source
      target: '1731576069313'
      targetHandle: target
      type: custom
      zIndex: 0
    - data:
        isInIteration: true
        iteration_id: '1731576069313'
        sourceType: iteration-start
        targetType: template-transform
      id: 1731576069313start-source-1731576098857-target
      source: 1731576069313start
      sourceHandle: source
      target: '1731576098857'
      targetHandle: target
      type: custom
      zIndex: 1002
    - data:
        isInIteration: true
        iteration_id: '1731576069313'
        sourceType: template-transform
        targetType: http-request
      id: 1731576098857-source-1731576128205-target
      source: '1731576098857'
      sourceHandle: source
      target: '1731576128205'
      targetHandle: target
      type: custom
      zIndex: 1002
    - data:
        isInIteration: true
        iteration_id: '1731576069313'
        sourceType: http-request
        targetType: llm
      id: 1731576128205-source-1731576166736-target
      source: '1731576128205'
      sourceHandle: source
      target: '1731576166736'
      targetHandle: target
      type: custom
      zIndex: 1002
    - data:
        isInIteration: false
        sourceType: iteration
        targetType: template-transform
      id: 1731576069313-source-1731576295463-target
      source: '1731576069313'
      sourceHandle: source
      target: '1731576295463'
      targetHandle: target
      type: custom
      zIndex: 0
    - data:
        isInIteration: false
        sourceType: template-transform
        targetType: end
      id: 1731576295463-source-1731576358614-target
      source: '1731576295463'
      sourceHandle: source
      target: '1731576358614'
      targetHandle: target
      type: custom
      zIndex: 0
    nodes:
    - data:
        desc: ''
        selected: false
        title: 开始
        type: start
        variables: []
      height: 54
      id: '1731575837911'
      position:
        x: 80
        y: 282
      positionAbsolute:
        x: 80
        y: 282
      selected: true
      sourcePosition: right
      targetPosition: left
      type: custom
      width: 244
    - data:
        authorization:
          config: null
          type: no-auth
        body:
          data: []
          type: none
        desc: ''
        headers: ''
        method: get
        params: ''
        selected: false
        timeout:
          max_connect_timeout: 0
          max_read_timeout: 0
          max_write_timeout: 0
        title: 获取36氪热榜
        type: http-request
        url: https://api.vvhan.com/api/hotlist/36Ke
        variables: []
      height: 110
      id: '1731575885694'
      position:
        x: 384
        y: 282
      positionAbsolute:
        x: 384
        y: 282
      selected: false
      sourcePosition: right
      targetPosition: left
      type: custom
      width: 244
    - data:
        context:
          enabled: false
          variable_selector: []
        desc: ''
        model:
          completion_params:
            temperature: 0.7
          mode: chat
          name: deepseek-ai/DeepSeek-V2.5
          provider: siliconflow
        prompt_template:
        - id: b74dda26-e5e0-4c36-9260-3f27a7e4f152
          role: system
          text: "```xml\n<instruction>\n  <instructions>\n    1. 抓取了360氪新闻榜单 json\
            \ ：{{#1731575885694.body#}}\n    2. 只生成榜单前面 1 条数据\n    3. 生成如下结构的内容：\n\
            \      [{\n        \"title\": \"新闻标题\",\n        \"url\": \"新闻链接\"\n \
            \     }]\n    4.输出不要添加```json 包裹\n  </instructions>\n  \n  <examples>\n\
            \    <example>\n      <output>\n        [\n          {\"title\": \"8点1氪｜个人购房不超140平契税降至1%；特斯拉10万员工薪酬数据曝光；校园招聘严禁限定985和211高校\"\
            ,\"url\":\"https://36kr.com/p/3035465134387461\"},\n            {\"title\"\
            : \"避免内耗，吉利将整合极氪和领克两大品牌｜36氪独家\",\"url\":\"https://36kr.com/p/3034230633984003\"\
            },\n {\"title\": \"Transformer打破三十年数学猜想，Meta研究者用AI给出反例，算法杀手攻克数学难题｜36氪独家\"\
            ,\"url\":\"https://36kr.com/p/3034698843615238\"},\n        ]\n      </output>\n\
            \    </example>\n <examples> "
        selected: false
        title: LLM 梳理成新闻数组
        type: llm
        variables: []
        vision:
          enabled: false
      height: 98
      id: '1731575963411'
      position:
        x: 688
        y: 282
      positionAbsolute:
        x: 688
        y: 282
      selected: false
      sourcePosition: right
      targetPosition: left
      type: custom
      width: 244
    - data:
        author: ' 周辉'
        desc: ''
        height: 114
        selected: false
        showAuthor: true
        text: '{"root":{"children":[{"children":[{"detail":0,"format":1,"mode":"normal","style":"font-size:
          16px;","text":"API接口返回的数据比较多，考虑到效率这里我们获取3条新闻","type":"text","version":1}],"direction":"ltr","format":"","indent":0,"type":"paragraph","version":1,"textFormat":0}],"direction":"ltr","format":"","indent":0,"type":"root","version":1}}'
        theme: blue
        title: ''
        type: ''
        width: 462
      height: 114
      id: '1731576000111'
      position:
        x: 682
        y: 409
      positionAbsolute:
        x: 682
        y: 409
      selected: false
      sourcePosition: right
      targetPosition: left
      type: custom-note
      width: 462
    - data:
        code: "import json\n\ndef main(arg1: str) -> dict:\n    try:\n        json_object\
          \ = json.loads(arg1)\n        return {\n            \"result\": json_object\n\
          \        }\n    except json.JSONDecodeError as e:\n        return {\n  \
          \          \"result\": None,\n            \"error\": f\"Invalid JSON: {str(e)}\"\
          \n        }"
        code_language: python3
        desc: ''
        outputs:
          result:
            children: null
            type: array[object]
        selected: false
        title: 转成 Array[object]
        type: code
        variables:
        - value_selector:
          - '1731575963411'
          - text
          variable: arg1
      height: 54
      id: '1731576019023'
      position:
        x: 992
        y: 282
      positionAbsolute:
        x: 992
        y: 282
      selected: false
      sourcePosition: right
      targetPosition: left
      type: custom
      width: 244
    - data:
        desc: ''
        error_handle_mode: terminated
        height: 201
        is_parallel: false
        iterator_selector:
        - '1731576019023'
        - result
        output_selector:
        - '1731576166736'
        - text
        output_type: array[string]
        parallel_nums: 10
        selected: false
        start_node_id: 1731576069313start
        title: 迭代获取新闻正文
        type: iteration
        width: 996
      height: 201
      id: '1731576069313'
      position:
        x: 1296
        y: 282
      positionAbsolute:
        x: 1296
        y: 282
      selected: false
      sourcePosition: right
      targetPosition: left
      type: custom
      width: 996
      zIndex: 1
    - data:
        desc: ''
        isInIteration: true
        selected: false
        title: ''
        type: iteration-start
      draggable: false
      height: 48
      id: 1731576069313start
      parentId: '1731576069313'
      position:
        x: 24
        y: 68
      positionAbsolute:
        x: 1320
        y: 350
      selectable: false
      sourcePosition: right
      targetPosition: left
      type: custom-iteration-start
      width: 44
      zIndex: 1002
    - data:
        desc: ''
        isInIteration: true
        iteration_id: '1731576069313'
        selected: false
        template: '{{ arg1.url }}'
        title: 模板转换
        type: template-transform
        variables:
        - value_selector:
          - '1731576069313'
          - item
          variable: arg1
      height: 54
      id: '1731576098857'
      parentId...（过长已截断）