WordPress Posts and Pages Scraper: Export Public Content

{
  "sourceUrl": "https://wordpress.org/news",
  "recordType": "POST",
  "id": 21731,
  "type": "post",
  "status": "publish",
  "link": "https://wordpress.org/news/2026/09/wordpress-7-1-2-release/",
  "date": "2026-09-22T14:01:20",
  "date_gmt": "2026-09-22T14:01:20",
  "title": {
    "rendered": "WordPress 7.1.2 Release"
  },
  "titleText": "WordPress 7.1.2 Release",
  "categories": [
    14,
    15
  ],
  "tags": [],
  "categoryDetails": [
    {
      "id": 14,
      "name": "Releases",
      "slug": "releases",
      "link": "https://wordpress.org/news/category/releases/"
    },
    {
      "id": 15,
      "name": "Security",
      "slug": "security",
      "link": "https://wordpress.org/news/category/security/"
    }
  ],
  "tagDetails": [],
  "extractionStatus": "complete",
  "content": {
    "rendered": "\n<p class=\"wp-block-paragraph\">This security release features a fix for a critical severity security vulnerability.</p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong",
    "protected": false
  },
  "contentText": "This security release features a fix for a critical severity security vulnerability.\n\nBecause this is a security release, it is recommended that you update your"
}

from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("cliqtomedia/wordpress-posts-pages-scraper").call(run_input={
    "siteUrls": [
        "https://wordpress.org/news"
    ],
    "contentTypes": [
        "posts",
        "pages"
    ]
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

curl -X POST "https://api.apify.com/v2/acts/cliqtomedia~wordpress-posts-pages-scraper/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"siteUrls": ["https://wordpress.org/news"], "contentTypes": ["posts", "pages"]}'

# pip install langchain-apify
# set APIFY_TOKEN in your environment
from langchain_apify import ApifyActorsTool

tool = ApifyActorsTool("cliqtomedia/wordpress-posts-pages-scraper")
result = tool.invoke({"run_input": {"siteUrls": ["https://wordpress.org/news"], "contentTypes": ["posts", "pages"]}})
print(result)