Queries LibraryImport HTML from URLs as new posts in WordPress
Import HTML from URLs as new posts in WordPress
This query imports the HTML pages from the given URLs as new posts in WordPress.
From each URL, it retrieves the title from <title>...</title>
in the meta, and the content from <body>...</body>
, or customized to some specific inner HTML element using the $contentMatchInnerRegex
variable.
With $contentMatchInnerRegex
, we can target what specific subportion of the <body>
's HTML to capture.
For instance, if the content must be extracted from:
<article class="main">...</article>
...we can capture it with:
{
"contentMatchInnerRegex": ".*?<\\s*?article\\b[^>]*>(.*?)<\\/article\\b[^>]*>.*?"
}
query GenerateURLInputs(
$urls: [URL!]!
$contentMatchInnerRegex: String! = "(.*?)"
) {
urlInputs: _echo(value: $urls)
@underEachArrayItem(
passValueOnwardsAs: "url"
)
@applyField(
name: "_echo",
arguments: {
value: {
url: $url,
method: GET
}
},
setResultInResponse: true
)
@export(as: "urlInputs")
@remove
contentMatchRegex: _sprintf(
string: "/(?:<!DOCTYPE html>)?<\\s*?html\\b[^>]*>.*?<\\s*?body\\b[^>]*>%s<\\/body\\b[^>]*>.*?<\\/html\\b[^>]*>/sim",
values: [$contentMatchInnerRegex]
)
@export(as: "contentMatchRegex")
}
query RequestPages
@depends(on: "GenerateURLInputs")
{
urlContents: _sendHTTPRequests(inputs: $urlInputs, async: false) {
statusCode
body
@remove
title: _strRegexReplace(
searchRegex: "/(?:<!DOCTYPE html>)?<\\s*?html\\b[^>]*>.*?<head\\b[^>]*>.*?<\\s*?title\\b[^>]*>(.*?)<\\/title\\b[^>]*>.*?<\\/head\\b[^>]*>(.*?)<\\/html\\b[^>]*>/sim"
replaceWith: "$1"
in: $__body
)
content: _strRegexReplace(
searchRegex: $contentMatchRegex
replaceWith: "$1"
in: $__body
)
createPostInput: _echo(value: {
status: publish,
title: $__title
contentAs: {
html: $__content
}
})
@export(as: "createPostInputs", type: LIST)
}
}
mutation CreatePostsFromURLs
@depends(on: "RequestPages")
{
createPosts(inputs: $createPostInputs) {
status
errors {
__typename
...on ErrorPayload {
message
}
}
post {
id
status
title
content
}
}
}