Pricing

from $0.80 / 1,000 pages

Try for free

Go to Apify Store

Web to Markdown for AI – Japanese & Chinese Ready

Try for free

Turn web pages or raw HTML into clean Markdown or text for LLMs and RAG. Decodes Shift_JIS, EUC-JP, GBK and Big5 correctly, handles furigana/ruby, respects robots.txt, and can report what changed since the last run. $0.80 per 1,000 pages.

Pricing

from $0.80 / 1,000 pages

Rating

0.0

(0)

Developer

Kumo Data Tools

Actor stats

Bookmarked

Total users

Monthly active users

4 days ago

Last modified

Categories

Developer tools

Automation

You can access the Web to Markdown for AI – Japanese & Chinese Ready programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.

Python

JavaScript

CLI

OpenAPI

HTTP

MCP

{
  "openapi": "3.0.1",
  "info": {
    "version": "0.1",
    "x-build-id": "LyOkm94ThG0de7hUG"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/kumo-data-tools~web-to-markdown-cjk/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-kumo-data-tools-web-to-markdown-cjk",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/kumo-data-tools~web-to-markdown-cjk/runs": {
      "post": {
        "operationId": "runs-sync-kumo-data-tools-web-to-markdown-cjk",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/kumo-data-tools~web-to-markdown-cjk/run-sync": {
      "post": {
        "operationId": "run-sync-kumo-data-tools-web-to-markdown-cjk",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "inputSchema": {
        "type": "object",
        "properties": {
          "urls": {
            "title": "Page URLs",
            "type": "array",
            "description": "Web pages to convert (http/https), up to 1,000 per run. Leave empty (and HTML below empty) to try the free bundled Shift_JIS sample.",
            "items": {
              "type": "string"
            }
          },
          "htmlDocuments": {
            "title": "Raw HTML documents",
            "type": "array",
            "description": "Already have the HTML? Pass objects `{\"html\": \"<html>…\", \"url\": \"https://… (optional, used to resolve links)\"}`. Nothing is fetched for these. Up to 100 per run, 5 MB each."
          },
          "formats": {
            "title": "Output formats",
            "type": "array",
            "description": "Any of `markdown`, `text`, `html` (cleaned main content) and `links`.",
            "default": [
              "markdown"
            ]
          },
          "mainContentOnly": {
            "title": "Main content only",
            "type": "boolean",
            "description": "Keep the article / main text and drop menus, footers and ads. Turn off to keep more of the page.",
            "default": true
          },
          "ruby": {
            "title": "Furigana / ruby annotations",
            "enum": [
              "drop",
              "parentheses",
              "keep"
            ],
            "type": "string",
            "description": "Pages with <ruby> (furigana, pinyin) otherwise break into one character per line. `drop` keeps the base text (私), `parentheses` adds the reading (私（わたくし）), `keep` leaves the HTML as is.",
            "default": "drop"
          },
          "forceEncoding": {
            "title": "Force encoding",
            "type": "string",
            "description": "Optional. Decode every fetched page with this encoding (e.g. `shift_jis`, `euc-jp`, `gbk`, `big5`, `utf-8`) instead of detecting it. Leave empty for automatic detection."
          },
          "respectRobotsTxt": {
            "title": "Respect robots.txt",
            "type": "boolean",
            "description": "Skip pages the site's robots.txt disallows (not charged). Turn off only for sites you own or have permission to fetch.",
            "default": true
          },
          "trackChanges": {
            "title": "Report changes since the last run",
            "type": "boolean",
            "description": "Remember each page's content in a named key-value store in your account and return `changeStatus` (new / changed / unchanged) plus a line diff. Ideal for a daily schedule.",
            "default": false
          },
          "trackerName": {
            "title": "Tracker name",
            "type": "string",
            "description": "Name of the key-value store that remembers pages. Use different names for different watch lists.",
            "default": "web-markdown-tracker"
          }
        }
      },
      "runsResponseSchema": {
        "type": "object",
        "properties": {
          "data": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string"
              },
              "actId": {
                "type": "string"
              },
              "userId": {
                "type": "string"
              },
              "startedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "finishedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "status": {
                "type": "string",
                "example": "READY"
              },
              "meta": {
                "type": "object",
                "properties": {
                  "origin": {
                    "type": "string",
                    "example": "API"
                  },
                  "userAgent": {
                    "type": "string"
                  }
                }
              },
              "stats": {
                "type": "object",
                "properties": {
                  "inputBodyLen": {
                    "type": "integer",
                    "example": 2000
                  },
                  "rebootCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "restartCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "resurrectCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "computeUnits": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "options": {
                "type": "object",
                "properties": {
                  "build": {
                    "type": "string",
                    "example": "latest"
                  },
                  "timeoutSecs": {
                    "type": "integer",
                    "example": 300
                  },
                  "memoryMbytes": {
                    "type": "integer",
                    "example": 1024
                  },
                  "diskMbytes": {
                    "type": "integer",
                    "example": 2048
                  }
                }
              },
              "buildId": {
                "type": "string"
              },
              "defaultKeyValueStoreId": {
                "type": "string"
              },
              "defaultDatasetId": {
                "type": "string"
              },
              "defaultRequestQueueId": {
                "type": "string"
              },
              "buildNumber": {
                "type": "string",
                "example": "1.0.0"
              },
              "containerUrl": {
                "type": "string"
              },
              "usage": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "integer",
                    "example": 1
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "usageTotalUsd": {
                "type": "number",
                "example": 0.00005
              },
              "usageUsd": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "number",
                    "example": 0.00005
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}

Web to Markdown API for LLMs – Japanese & Chinese OpenAPI definition

OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.

OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.

By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.

You can download the OpenAPI definitions for Web to Markdown for AI – Japanese & Chinese Ready from the options below:

OpenAPI.json

If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.

You can also check out our other API clients:

Web to Markdown for AI – Japanese & Chinese Ready API in Python

Web to Markdown for AI – Japanese & Chinese Ready API in JavaScript

Web to Markdown for AI – Japanese & Chinese Ready API through CLI

Web to Markdown for AI – Japanese & Chinese Ready API

Download Images from URLs: Bulk Image & File Downloader

data-done-right/image-downloader

Download images from URLs in bulk: an image downloader API for lists of direct image or file links and for images found on web pages. Dedupe by content hash, convert to JPG, PNG or WebP, resize, filter by size and get public links plus one ZIP.

Data Done Right

WeChat Article to Clean Markdown & JSON Extractor

knightwwang/wechat-article-to-markdown

Convert WeChat Official Account articles (mp.weixin.qq.com) into clean Markdown with embedded images, author info, publish date, and AI-ready tokens.

knightwwang Wang

Website Content Crawler (Anti-Bot) - $1.20 / 1000 Pages

scrapeunblocker/website-content-crawler

Crawl any website, even behind Cloudflare, DataDome, PerimeterX or Akamai, and get clean Markdown and text of every page for LLMs, RAG and AI agents. Main-content extraction, URL globs, sitemaps, depth and page limits. $1.20 per 1000 pages; failed pages are free.

Scrapeunblocker

The Guardian Scraper

theo/the-guardian-scraper

Scrape news data from theguardian.com with this unofficial API. Extract articles, monitor their popularity and performance and automate the fight against fake news. Filter the results by authors, topics, categories, or publication dates. Preview or download the results in your preferred format.

Theo Vasilis

Substack Scraper: Posts, Full Text, Newsletters & Leaderboards

winterlock/substack-scraper

Export every post of any Substack newsletter (custom domains too) with likes, comments, restacks and dates; full text and HTML of free posts; publication info with subscriber counts and prices; and category bestseller lists. No login.

Alex Burton

RSS Feed Reader & Feed Finder – RSS/Atom to JSON, Full Text

openharvest/rss-feed-reader

RSS feed reader for any RSS, Atom or JSON Feed: clean items with title, link, date, author, categories, summary, image and podcast enclosures. Paste a website, YouTube channel, Substack, Medium or GitHub URL and the feed finder discovers its feeds. Optional full article text. No start fee.

Enes Bulanık

WeChat Official Account Scraper: 公众号 Articles & Full Text

serenido/wechat-official-account-scraper

Search WeChat Official Account (微信公众号) articles by keyword and get full text, account, author, publish time, province, original label and images. Or paste article links. No login, no cookies. Deleted or blocked articles are free.

Serenido

Website to Markdown Crawler for LLM, RAG & AI Context

physealabs/website-markdown-crawler

Crawl any website and get each page as clean Markdown with title, description, word count and token estimate. Menus, footers and cookie banners removed. Built by Physea Labs (Liminal). Launch Sale: 90% OFF for the first week. $0.001 per page.

jay casey

Website to LLM-Ready Dataset - Markdown & Chunks for RAG

atesen-software/llm-dataset-builder

Crawl a website or docs site and get clean Markdown, token-sized semantic chunks and metadata for every page. Ready for vector databases and RAG pipelines. $1.50 per 1,000 pages.

Atesen Software

Substack Scraper: Posts, Full Text & Newsletter Data

green_trousers/substack-scraper

Scrape any Substack newsletter, custom domains too: every post with full text as clean Markdown, likes, comments, restacks, tags, authors, paid/free flag and subscriber counts. Optional comments and Substack-wide keyword search. Fast JSON, no browser. Built for AI/RAG and research.