Extract And Decode Google News RSS URLs to Clean Article Links

{
  "id": "3JsfhcDcjqxx0hr3",
  "meta": {
    "instanceId": "38fb1860cc6284b8af9ba3b485f32cc1851cd97470ef1b4a472b5e707f1c93b5"
  },
  "name": "Extract And Decode Google News RSS URLs to Clean Article Links",
  "tags": [
    {
      "id": "ROumyeVDIszTv7f5",
      "name": "no-ai",
      "createdAt": "2025-02-08T15:29:36.956Z",
      "updatedAt": "2025-02-08T15:29:36.956Z"
    },
    {
      "id": "XuoLgc5Eegoi3VEP",
      "name": "scraping",
      "createdAt": "2025-01-31T18:19:12.753Z",
      "updatedAt": "2025-01-31T18:19:12.753Z"
    },
    {
      "id": "nBHkkAND8NXbkg8m",
      "name": "news",
      "createdAt": "2025-03-13T15:47:18.420Z",
      "updatedAt": "2025-03-13T15:47:18.420Z"
    }
  ],
  "nodes": [
    {
      "id": "cdb0a726-e961-40ae-b679-43f7bd73650d",
      "name": "When clicking ‘Test workflow’",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        560,
        1240
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "028ddd3b-069c-43be-ad56-8f898805fccf",
      "name": "Limit",
      "type": "n8n-nodes-base.limit",
      "position": [
        1040,
        1000
      ],
      "parameters": {
        "maxItems": 5
      },
      "typeVersion": 1
    },
    {
      "id": "2215bfdc-1e6e-475c-9753-b05fd5b0d63a",
      "name": "Reading Google News RSS",
      "type": "n8n-nodes-base.rssFeedRead",
      "position": [
        840,
        1000
      ],
      "parameters": {
        "url": "https://news.google.com/rss?hl=it&gl=IT&ceid=IT:it",
        "options": {
          "ignoreSSL": false
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "23b50dac-9506-41cb-8b57-15373468ab3c",
      "name": "Decoded url",
      "type": "n8n-nodes-base.set",
      "position": [
        1520,
        1420
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "c51f320e-4fb8-4bd4-8e36-9330e251936e",
              "name": "google_news_url",
              "type": "string",
              "value": "={{ JSON.parse(JSON.parse($json.data.split('\n\n')[1])[0][2])[1] }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "40f54966-41c7-4dc3-95ac-18b8eaffe1db",
      "name": "Call decoding URL",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1280,
        1420
      ],
      "parameters": {
        "url": "https://news.google.com/_/DotsSplashUi/data/batchexecute",
        "method": "POST",
        "options": {
          "response": {
            "response": {
              "fullResponse": true,
              "responseFormat": "text"
            }
          }
        },
        "sendBody": true,
        "contentType": "form-urlencoded",
        "sendHeaders": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "f.req",
              "value": "={{ $json.f_req }}"
            }
          ]
        },
        "headerParameters": {
          "parameters": [
            {
              "name": "Content-Type",
              "value": "application/x-www-form-urlencoded;charset=UTF-8"
            },
            {
              "name": "User-Agent",
              "value": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36"
            },
            {
              "name": "Referer",
              "value": "https://www.google.com/"
            }
          ]
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "e7a208d3-bf65-4170-bb11-d13287f8dd78",
      "name": "Prepare decoding variables",
      "type": "n8n-nodes-base.code",
      "position": [
        1040,
        1420
      ],
      "parameters": {
        "jsCode": "return $input.all().map(item => {
    const gn_art_id = item.json.base64Str;
    const timestamp = item.json.timestamp;
    const signature = item.json.signature;

    const articlesReq = [
        'Fbv4je',
        `[\"garturlreq\",[[\"X\",\"X\",[\"X\",\"X\"],null,null,1,1,\"US:en\",null,1,null,null,null,null,null,0,1],\"X\",\"X\",1,[1,1,1],1,1,null,0,0,null,0],\"${gn_art_id}\",${timestamp},\"${signature}\"]`,
    ];

    return {
        json: {
            f_req: JSON.stringify([[articlesReq]])  // Questo verrà usato nel nodo HTTP Request
        }
    };
});"
      },
      "typeVersion": 2
    },
    {
      "id": "35fe85f1-82c7-4b50-b47b-14c56678e377",
      "name": "Get encoded news URL",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1280,
        1000
      ],
      "parameters": {
        "url": "={{ $('Limit').item.json.link }}",
        "options": {}
      },
      "typeVersion": 4.2
    },
    {
      "id": "3d640138-4247-4e6d-a0e9-fefc9f41e057",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        740,
        760
      ],
      "parameters": {
        "width": 220,
        "height": 400,
        "content": "## Get Google News

Change the language parameters on ISO639-1 standard 

1. hl=it
2. gl=IT
3. ceid=IT:it"
      },
      "typeVersion": 1
    },
    {
      "id": "1e7a5638-8829-49f1-a445-f510eb18bbd7",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        980,
        760
      ],
      "parameters": {
        "width": 220,
        "height": 400,
        "content": "## Limit result

I suggest limiting the results to a maximum of 3 because the entire workflow makes a lot of HTTP requests"
      },
      "typeVersion": 1
    },
    {
      "id": "24a405df-c334-461a-ab0d-91ebc39185c1",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        500,
        760
      ],
      "parameters": {
        "color": 5,
        "width": 220,
        "height": 820,
        "content": "## INFO

Disclaimer:
You can add a cron trigger but... don't do too often: Google could block your ip.

This workflow works until works: the decoding procedure is hardcoded and based on reverse engineering. Requests and responses are not documented by Google.


"
      },
      "typeVersion": 1
    },
    {
      "id": "c54e9729-7cbd-4628-b7be-ee072047b3d4",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1220,
        760
      ],
      "parameters": {
        "color": 3,
        "width": 220,
        "height": 400,
        "content": "## Get encoded content

Here we retrieve HTML content"
      },
      "typeVersion": 1
    },
    {
      "id": "a5b25d20-0d06-4650-b8bc-0d03c97eb416",
      "name": "Map needed keys",
      "type": "n8n-nodes-base.set",
      "position": [
        780,
        1420
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "b5a11795-2bd1-412f-a215-f7402bece002",
              "name": "signature",
              "type": "string",
              "value": "={{ $json.signature }}"
            },
            {
              "id": "33267283-3ac8-4d65-9a01-c7f154a7d061",
              "name": "timestamp",
              "type": "string",
              "value": "={{ $json.timestamp }}"
            },
            {
              "id": "bff8f19a-30d6-4307-87da-9b98b26cee8b",
              "name": "base64Str",
              "type": "string",
              "value": "={{ $('Limit').item.json.guid }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "116eec84-dbfe-4880-8fc4-d350ff99d4be",
      "name": "Extract decoding keys",
      "type": "n8n-nodes-base.html",
      "position": [
        1520,
        1000
      ],
      "parameters": {
        "options": {},
        "operation": "extractHtmlContent",
        "extractionValues": {
          "values": [
            {
              "key": "signature",
              "attribute": "data-n-a-sg",
              "cssSelector": "div",
              "returnValue": "attribute"
            },
            {
              "key": "timestamp",
              "attribute": "data-n-a-ts",
              "cssSelector": "div",
              "returnValue": "attribute"
            }
          ]
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "22825293-d9f8-4fa2-99b4-2150a74b2a12",
      "name": "Sticky Note5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1460,
        760
      ],
      "parameters": {
        "width": 220,
        "height": 400,
        "content": "## Decoding Keys

The HTML content extracted contains the necessary variables for decoding:

+ signature
+ timestamp
+ base64string (already in the URL)"
      },
      "typeVersion": 1
    },
    {
      "id": "46dce5e2-1c4f-45d8-a849-ebe13d673ef9",
      "name": "Sticky Note6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        740,
        1180
      ],
      "parameters": {
        "width": 220,
        "height": 400,
        "content": "## Clean output

Mapping variables for easy utilization"
      },
      "typeVersion": 1
    },
    {
      "id": "9dbc9f69-d34a-470e-81af-c3bcc9a92a48",
      "name": "Sticky Note7",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        980,
        1180
      ],
      "parameters": {
        "color": 3,
        "width": 220,
        "height": 400,
        "content": "## Preparing Request

Decoding the request requires specific body content. Here, we build it using the decoding keys."
      },
      "typeVersion": 1
    },
    {
      "id": "39a492a7-a099-4ae7-ac17-d3842f0682fe",
      "name": "Sticky Note8",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1220,
        1180
      ],
      "parameters": {
        "color": 3,
        "width": 220,
        "height": 400,
        "content": "## This is decoding step

Sending a request to a specific Google decoding URL"
      },
      "typeVersion": 1
    },
    {
      "id": "29d3b1a3-5882-484d-9add-68a746f0a7b8",
      "name": "Sticky Note9",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1460,
        1180
      ],
      "parameters": {
        "width": 220,
        "height": 400,
        "content": "## Cleaning URL

Google adds some unwanted and random characters at the beginning of the URL"
      },
      "typeVersion": 1
    },
    {
      "id": "6b2fc671-2a22-4a6d-bcc5-38294981d9fe",
      "name": "Sticky Note10",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1700,
        760
      ],
      "parameters": {
        "color": 4,
        "width": 220,
        "height": 820,
        "content": "## OUTPUT

A lot of requests are made before getting clean News URLs.

You can add an HttpRequest and get News text with jina.ai, extract by using HTML node, or a custom node like https://www.npmjs.com/package/n8n-nodes-webpage-content-extractor

"
      },
      "typeVersion": 1
    },
    {
      "id": "6c82769b-e784-4a38-b2ed-447da7f1a6f7",
      "name": "Aggregate results in a single object",
      "type": "n8n-nodes-base.aggregate",
      "position": [
        1760,
        1080
      ],
      "parameters": {
        "options": {},
        "aggregate": "aggregateAllItemData"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "c4fbad75-5811-4031-bdfe-ee494067ded3",
  "connections": {
    "Limit": {
      "main": [
        [
          {
            "node": "Get encoded news URL",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Decoded url": {
      "main": [
        [
          {
            "node": "Aggregate results in a single object",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Map needed keys": {
      "main": [
        [
          {
            "node": "Prepare decoding variables",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Call decoding URL": {
      "main": [
        [
          {
            "node": "Decoded url",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get encoded news URL": {
      "main": [
        [
          {
            "node": "Extract decoding keys",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract decoding keys": {
      "main": [
        [
          {
            "node": "Map needed keys",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Reading Google News RSS": {
      "main": [
        [
          {
            "node": "Limit",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Prepare decoding variables": {
      "main": [
        [
          {
            "node": "Call decoding URL",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When clicking ‘Test workflow’": {
      "main": [
        [
          {
            "node": "Reading Google News RSS",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}