Yuming Long 542d442699
chore CORE-4775: remove html page number metadata field (#2942)
### Summary

Rip off page_number metadata fields until we have page counting for all
kinds of html files (not just limited to news articles with multiple
`<article>` tag)

### Test
Unit tests
`test_add_chunking_strategy_on_partition_html_respects_multipage` and
`test_add_chunking_strategy_title_on_partition_auto_respects_multipage`
removed since they relay on the `page_number` fields from the SEC html
file - now test moved to mock test for chunk_by_title -> revisit those
tests when we find test file for this

Also changed the element ids from partition outputs for html files -
element id change due to page number change (in element id hashing) ->
todo ticket: update other deterministic element id tests per crag's
comment

---------

Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com>
Co-authored-by: yuming-long <yuming-long@users.noreply.github.com>
2024-04-30 15:20:26 +00:00

1025 lines
28 KiB
JSON

[
{
"element_id": "e1f5fcc433282a2fa999a1dec593f59a",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Welcome to your team space!",
"type": "Title"
},
{
"element_id": "c1a9308ef0747d4d4e4224516ecddb18",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "We've added some suggestions and placeholders. Everything is customizable.",
"type": "ListItem"
},
{
"element_id": "0541e1bcde4e7efd6de89e8920ca8080",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
],
"link_start_indexes": [
32,
55,
79
],
"link_texts": [
"Template - Project plan",
"Template - Meeting notes",
"Template - Weekly status report"
],
"link_urls": [
"/wiki/spaces/MFS/pages/1540126/Template+-+Project+plan",
"/wiki/spaces/MFS/pages/1605928/Template+-+Meeting+notes",
"/wiki/spaces/MFS/pages/1605942/Template+-+Weekly+status+report"
]
},
"text": "Get started with page templates:Template - Project planTemplate - Meeting notesTemplate - Weekly status report",
"type": "ListItem"
},
{
"element_id": "58d6e4f85d58b5d3e291326c1c5dafba",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
],
"link_start_indexes": [
10
],
"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": "171deecd78c76bbd89be75dd13342cc2",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "About",
"type": "Title"
},
{
"element_id": "e3f9b4aabce922efda54bfce0ff29aaa",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"What is your team all about?",
"What is your team all about?"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "What is your team all about?",
"type": "NarrativeText"
},
{
"element_id": "feda90682ffacf43bb009fd562c1206c",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Mission and vision",
"type": "Title"
},
{
"element_id": "da6021de78b8b943777414ff3ec94186",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"What is your team's mission? What is your vision?",
"What is your team's mission? What is your vision?"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "What is your team's mission? What is your vision?",
"type": "NarrativeText"
},
{
"element_id": "5b801b2fbeafefe2b1f2f5e00356f214",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Meet the team",
"type": "Title"
},
{
"element_id": "baffb88089e750a4b1b1209aa55d1410",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Add team members to your space.",
"Add team members to your space."
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Add team members to your space.",
"type": "Title"
},
{
"element_id": "7a4fddccf630b618da314c2a2ee45491",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Team member"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Team member",
"type": "Title"
},
{
"element_id": "55bdf090c6dac121668ac65a9a7f2bf9",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Role"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Role",
"type": "Title"
},
{
"element_id": "f926f3cf69185b202f8f868f0e8577dc",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Responsibility"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Responsibility",
"type": "Title"
},
{
"element_id": "93eecf0cb223bb9b38800c595a2c1ce2",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Team member"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Team member",
"type": "Title"
},
{
"element_id": "75ee4a303fc5ab8639c7bca973f29e30",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Role"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Role",
"type": "Title"
},
{
"element_id": "22731d9c17747fc4708fd7f418e9dd57",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Responsibility"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Responsibility",
"type": "Title"
},
{
"element_id": "c4327bb8ec4ea8444a6307fcdf6928cd",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Team member"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Team member",
"type": "Title"
},
{
"element_id": "aa48062270f019242d68093284c4fa0c",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Role"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Role",
"type": "Title"
},
{
"element_id": "4bdb6fa86fd59b0729ecb9b6dbbf1ba7",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Responsibility"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Responsibility",
"type": "Title"
},
{
"element_id": "2c7f4046974b76def589634ebe2c0c47",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Contact us",
"type": "Title"
},
{
"element_id": "5939e388affdc9ab440c5c158478e6b5",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"How can someone reach out to your team?",
"How can someone reach out to your team?"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "How can someone reach out to your team?",
"type": "NarrativeText"
},
{
"element_id": "53e3a9c9214c1410cc0658cb871e8291",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"team@email.com"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"link_start_indexes": [
0
],
"link_texts": [
null
],
"link_urls": [
"mailto:team@email.com"
]
},
"text": "team@email.com",
"type": "ListItem"
},
{
"element_id": "1507ffa5704d588237bb94150d9cfd27",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Tickets"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Tickets",
"type": "ListItem"
},
{
"element_id": "ac32614a08d10f91199e9c6e1b3c4a20",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Jira board"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Jira board",
"type": "ListItem"
},
{
"element_id": "3c70a6c9abd4e0c53832503a04fd9772",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"#channel"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "#channel",
"type": "ListItem"
},
{
"element_id": "4f58203ca7333ae2f3ae45c62617425c",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Important Pages",
"type": "Title"
},
{
"element_id": "548d2e7b200eed8688e8eeeb1915c5e5",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"List them here",
"List them here"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "List them here",
"type": "NarrativeText"
},
{
"element_id": "cac81bd65cfc7098409c7a04ed50642b",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "",
"type": "ListItem"
},
{
"element_id": "3ccf13a948a19a1d2434fdd2fdd451ce",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "",
"type": "ListItem"
},
{
"element_id": "e38ebc13023b654efab1e71ca25aeec9",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "",
"type": "ListItem"
},
{
"element_id": "f4186b4e1cec5ef7009560d11cb74087",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Onboarding FAQs",
"type": "Title"
},
{
"element_id": "a27a3099dea44c05dfea1e0e125abac5",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Add resources for new hires",
"Add resources for new hires"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Add resources for new hires",
"type": "Title"
},
{
"element_id": "44d083c5ce62947d874c568db0dbc01b",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Meeting notes",
"type": "Title"
},
{
"element_id": "23d9d3b7eb1b506a1031e99b28243136",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Add links to meeting notes",
"Add links to meeting notes"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Add links to meeting notes",
"type": "NarrativeText"
},
{
"element_id": "5d12aca2ca2b8aba5c9dee48f1475f55",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Team goals",
"type": "Title"
},
{
"element_id": "70182a5acbdac0041ee51b85dfca692f",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"List them here",
"List them here"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "List them here",
"type": "NarrativeText"
},
{
"element_id": "243fc77b8eebdbcf00a6a108a8159b69",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Team news",
"type": "Title"
},
{
"element_id": "3014e5236eb14590a7c13e83c36b20ce",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"emphasized_text_contents": [
"Create a blog post to share team news. It will automatically appear here once it's published.",
"Create a blog post to share team news. It will automatically appear here once it's published."
],
"emphasized_text_tags": [
"em",
"span"
],
"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": "800f984e0d3456624dce9630abfd873a",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Blog stream",
"type": "Title"
},
{
"element_id": "800885acdda14ccb63621293f9a3aa2f",
"metadata": {
"data_source": {
"date_created": "2023-07-09T12:54:40.304000",
"date_modified": "2023-07-13T14:13:27.275000",
"record_locator": {
"page_id": "1605859",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1605859",
"version": "2"
},
"filetype": "text/html",
"languages": [
"eng"
]
},
"text": "Create a blog post to share news and announcements with your team and company.",
"type": "NarrativeText"
}
]