mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-06-27 02:30:08 +00:00

Currently we [filter img
tags](2addb19473/unstructured/partition/html/partition.py (L226-L229)
)
before tags are converted to Elements by the html partitioner. More
importantly we also don’t currently have a defined “block” / mapping to
support these. This adds these mappings and logic to process.
It also respects `extract_image_block_types` and
`extract_image_block_to_payload` (as we do with pdfs) to determine
whether base64 is included in the metadata.
The partitioned Image Elements sets the text to the img tag’s alt text
if available.
The partitioned Image Elements include the [url in the
metadata](https://github.com/Unstructured-IO/unstructured/blob/main/unstructured/documents/elements.py#L209)
(rather than image_base64) if the img tag src is a url.
## Testing
unit tests have been added for explicit coverage.
existing integration tests and other unit test fixtures have been
updated to account for `Image` elements now present
---------
Co-authored-by: ryannikolaidis <ryannikolaidis@users.noreply.github.com>
1052 lines
30 KiB
JSON
1052 lines
30 KiB
JSON
[
|
|
{
|
|
"element_id": "af28136055ec3b58ec92da684eabe972",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Welcome to your team space!",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "637226363ce2403ca3a797b8e400b470",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "We've added some suggestions and placeholders. Everything is customizable.",
|
|
"type": "NarrativeText"
|
|
},
|
|
{
|
|
"element_id": "f989bb0b49d75b6e175b5766f509b9b0",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Get started with page templates:",
|
|
"type": "NarrativeText"
|
|
},
|
|
{
|
|
"element_id": "438d234753fc6b24fb20650245799a11",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"link_texts": [
|
|
"Template - Project plan"
|
|
],
|
|
"link_urls": [
|
|
"/wiki/spaces/MFS/pages/1540126/Template+-+Project+plan"
|
|
]
|
|
},
|
|
"text": "Template - Project plan",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "f95925f116d374133160eecfd80b34eb",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"link_texts": [
|
|
"Template - Meeting notes"
|
|
],
|
|
"link_urls": [
|
|
"/wiki/spaces/MFS/pages/1605928/Template+-+Meeting+notes"
|
|
]
|
|
},
|
|
"text": "Template - Meeting notes",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "505c7b987150071b3f72fde7d84e5c12",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"link_texts": [
|
|
"Template - Weekly status report"
|
|
],
|
|
"link_urls": [
|
|
"/wiki/spaces/MFS/pages/1605942/Template+-+Weekly+status+report"
|
|
]
|
|
},
|
|
"text": "Template - Weekly status report",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "742589217c0ffe6219f61e1c99d097cf",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"link_texts": [
|
|
"Get the most out of your team space"
|
|
],
|
|
"link_urls": [
|
|
"/wiki/spaces/MFS/pages/1605956/Get+the+most+out+of+your+team+space"
|
|
]
|
|
},
|
|
"text": "Check out Get the most out of your team space for more tips.",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "be5e87d0785203ead2bf53c133549fa6",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "About",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "154616ca05a0f9c8f9cdd26bc858d1cd",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"emphasized_text_contents": [
|
|
"What is your team all about?"
|
|
],
|
|
"emphasized_text_tags": [
|
|
"i"
|
|
],
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "What is your team all about?",
|
|
"type": "NarrativeText"
|
|
},
|
|
{
|
|
"element_id": "c03b2ddbcb48fdad00247bd477fd8d91",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Mission and vision",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "0d93fb1d1d262eb4570573e0630db120",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"emphasized_text_contents": [
|
|
"What is your team's mission? What is your vision?"
|
|
],
|
|
"emphasized_text_tags": [
|
|
"i"
|
|
],
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "What is your team's mission? What is your vision?",
|
|
"type": "NarrativeText"
|
|
},
|
|
{
|
|
"element_id": "f4638a66942901e4533240afec32333a",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Meet the team",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "9d2ea8da0d1c12bb3616cd3cb4e56128",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"emphasized_text_contents": [
|
|
"Add team members to your space."
|
|
],
|
|
"emphasized_text_tags": [
|
|
"i"
|
|
],
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Add team members to your space.",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "11d63c2d51214128c8caebb58f2bf06d",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "",
|
|
"type": "Image"
|
|
},
|
|
{
|
|
"element_id": "3d68b97296629da6f56dbee7226fb9ea",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Team member",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "b14012a7e1df00e14688673e6836af91",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Role",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "2ee3fe067727e804a8089f8c0131cd7e",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Responsibility",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "e206acc35c25cd275875533feb308ecf",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "",
|
|
"type": "Image"
|
|
},
|
|
{
|
|
"element_id": "e9f3973e622aaacb42556e6f29d140c0",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Team member",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "2b43cb7e0a29b1411d109e9a682940fa",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Role",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "3560a31004a2e271125262ae3435cd80",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Responsibility",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "48a5d1f209c8025b1cfb1d882658743e",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "",
|
|
"type": "Image"
|
|
},
|
|
{
|
|
"element_id": "64c696a8ba912e8c86e3dacc55bcfd09",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Team member",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "60781a8a6086a335e6ef8efa6e767f74",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Role",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "47137487152e9d98851e213658f3b212",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Responsibility",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "5189c62c2edeed476df22eaa2bb5af21",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Contact us",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "43e843feeaed82e03996b90693f9c8eb",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"emphasized_text_contents": [
|
|
"How can someone reach out to your team?"
|
|
],
|
|
"emphasized_text_tags": [
|
|
"i"
|
|
],
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "How can someone reach out to your team?",
|
|
"type": "NarrativeText"
|
|
},
|
|
{
|
|
"element_id": "0bae84d0e5cdc716a1dce4f739b86469",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"link_texts": [
|
|
"team@email.com"
|
|
],
|
|
"link_urls": [
|
|
"mailto:team@email.com"
|
|
]
|
|
},
|
|
"text": "team@email.com",
|
|
"type": "EmailAddress"
|
|
},
|
|
{
|
|
"element_id": "4d103f0c3f7f3527c37f34a8c4e86782",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Tickets",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "deda95e4491b693fdb7bb978868beefd",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Jira board",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "e35c7cd3ecffe9ca0e65935f3feebfbd",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "#channel",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "f953d1e45bf1cf4cd4985b61255a41e3",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Important Pages",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "53c5427b05c4256bd7c7e03346e58b9f",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"emphasized_text_contents": [
|
|
"List them here"
|
|
],
|
|
"emphasized_text_tags": [
|
|
"i"
|
|
],
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "List them here",
|
|
"type": "NarrativeText"
|
|
},
|
|
{
|
|
"element_id": "6e5310473567927ff094c33ba42ff201",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "",
|
|
"type": "Image"
|
|
},
|
|
{
|
|
"element_id": "a139fb30a2382364053eb57aa180550f",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Onboarding FAQs",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "eb784ba0d48bf9e06b53aed2ac3fbd72",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"emphasized_text_contents": [
|
|
"Add resources for new hires"
|
|
],
|
|
"emphasized_text_tags": [
|
|
"i"
|
|
],
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Add resources for new hires",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "768cfb8a51125da06add3109e7d155b3",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "",
|
|
"type": "Image"
|
|
},
|
|
{
|
|
"element_id": "67503783d98953e33cdc2846b90c21fd",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Meeting notes",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "27194483431e4365b86572cbc73b9af5",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"emphasized_text_contents": [
|
|
"Add links to meeting notes"
|
|
],
|
|
"emphasized_text_tags": [
|
|
"i"
|
|
],
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Add links to meeting notes",
|
|
"type": "NarrativeText"
|
|
},
|
|
{
|
|
"element_id": "c941c078ee573a2bbca654a7b5ce68f4",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "",
|
|
"type": "Image"
|
|
},
|
|
{
|
|
"element_id": "885ad7169d419802971c64780c7a7968",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Team goals",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "4d12c0c0f2d8211bc2b3eae35ac4f854",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"emphasized_text_contents": [
|
|
"List them here"
|
|
],
|
|
"emphasized_text_tags": [
|
|
"i"
|
|
],
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "List them here",
|
|
"type": "NarrativeText"
|
|
},
|
|
{
|
|
"element_id": "019ded9026166e1794b589358870fe60",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Team news",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "7cdd15b42c50cc95a64aa83149e72aec",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"emphasized_text_contents": [
|
|
"Create a blog post to share team news. It will automatically appear here once it's published."
|
|
],
|
|
"emphasized_text_tags": [
|
|
"i"
|
|
],
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Create a blog post to share team news. It will automatically appear here once it's published.",
|
|
"type": "NarrativeText"
|
|
},
|
|
{
|
|
"element_id": "008813f1d7a4380879ff001294f8bc6e",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Blog stream",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "2a28d14ef4ba44c8f0098df26a520f23",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-30T17:25:25.504000",
|
|
"date_modified": "2023-06-30T17:25:30.898000",
|
|
"record_locator": {
|
|
"page_id": "229477",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Create a blog post to share news and announcements with your team and company.",
|
|
"type": "NarrativeText"
|
|
}
|
|
] |