yujunjun/unstructured
1
0
Fork 0
mirror of https://github.com/Unstructured-IO/unstructured.git synced 2025-10-31 18:14:51 +00:00
Code Issues Packages Projects Releases Wiki Activity
unstructured/test_unstructured_ingest/expected-structured-output/confluence-diff/testteamsp/1605859.json
Matt Robinson 6e852cbe70
feat: track links from anchor tags in partition_html (#959) 
* track tags in html

* pass through links as metadata

* add test for grabbing links

* one more link

* changelog and version

* update docs

* fix tests

* update empty link assertion

* ingest-test-fixtures-update

* Update ingest test fixtures (#961)
2023-07-24 18:28:56 +00:00

428 lines
9.7 KiB
JSON
Raw Blame History

[
{
"type": "Title",
"element_id": "8a15fc1eef0a58dbead47b882dbcdd24",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Welcome to your team space!"
},
{
"type": "ListItem",
"element_id": "a621b19bad2c2be0cfe54534c90ab126",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "We've added some suggestions and placeholders. Everything is customizable."
},
{
"type": "ListItem",
"element_id": "2a2f2d2dcdde9622cd6972a774138f61",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1,
"links": [
{
"text": "Template - Project plan",
"url": "/wiki/spaces/MFS/pages/1540126/Template+-+Project+plan"
},
{
"text": "Template - Meeting notes",
"url": "/wiki/spaces/MFS/pages/1605928/Template+-+Meeting+notes"
},
{
"text": "Template - Weekly status report",
"url": "/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": "84b8c34eea80326420f9b3e5b939497c",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1,
"links": [
{
"text": "Get the most out of your team space",
"url": "/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": "Title",
"element_id": "4efca0d10c5feb8e9b35eb1d994f2905",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "About"
},
{
"type": "NarrativeText",
"element_id": "7c7300ac1a16ec290de2442ba09763c1",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "What is your team all about?"
},
{
"type": "Title",
"element_id": "d416dc3ddd2f2ba48ad2bb784b808856",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Mission and vision"
},
{
"type": "NarrativeText",
"element_id": "0d9db833ea5d982786604025ab277aa6",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "What is your team's mission? What is your vision?"
},
{
"type": "Title",
"element_id": "ecfdb98aaa881aa6cff78b56f2b1e4bc",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Meet the team"
},
{
"type": "Title",
"element_id": "44a4aebe327cd902d50cc9462de55db4",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Add team members to your space."
},
{
"type": "Title",
"element_id": "8062dbb50d1094a8047ec09c9e013d4b",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Team member"
},
{
"type": "Title",
"element_id": "14736a2eb9f4159f4b6b86f192c3c222",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Role"
},
{
"type": "Title",
"element_id": "c91217be093ab3d9bc1ce3917ed89c8c",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Responsibility"
},
{
"type": "Title",
"element_id": "8062dbb50d1094a8047ec09c9e013d4b",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Team member"
},
{
"type": "Title",
"element_id": "14736a2eb9f4159f4b6b86f192c3c222",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Role"
},
{
"type": "Title",
"element_id": "c91217be093ab3d9bc1ce3917ed89c8c",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Responsibility"
},
{
"type": "Title",
"element_id": "8062dbb50d1094a8047ec09c9e013d4b",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Team member"
},
{
"type": "Title",
"element_id": "14736a2eb9f4159f4b6b86f192c3c222",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Role"
},
{
"type": "Title",
"element_id": "c91217be093ab3d9bc1ce3917ed89c8c",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Responsibility"
},
{
"type": "Title",
"element_id": "47aaf31b83d6bfd705b80bcd5b6269be",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Contact us"
},
{
"type": "NarrativeText",
"element_id": "1c3db10eee185bd74b4a3de5e3175939",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "How can someone reach out to your team?"
},
{
"type": "ListItem",
"element_id": "74abeee66eab3921cf03757abdb8d5e6",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1,
"links": [
{
"text": null,
"url": "mailto:team@email.com"
}
]
},
"text": "team@email.com"
},
{
"type": "ListItem",
"element_id": "3d131368b43397ff5fbe0a9bf62c0f79",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Tickets"
},
{
"type": "ListItem",
"element_id": "d54a2001284ac19f58ad73a62674244a",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Jira board"
},
{
"type": "ListItem",
"element_id": "195a10e63a336aa995e242c92f17b756",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "#channel"
},
{
"type": "Title",
"element_id": "c8b321a3bf39a57de24aac4cca6605a0",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Important Pages"
},
{
"type": "NarrativeText",
"element_id": "43770d73ac7c6d8d1a38dd0c13fa8607",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "List them here"
},
{
"type": "ListItem",
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": ""
},
{
"type": "ListItem",
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": ""
},
{
"type": "ListItem",
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": ""
},
{
"type": "Title",
"element_id": "86d353b1f4a6a63ab4577d94ba9d4fea",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Onboarding FAQs"
},
{
"type": "Title",
"element_id": "2dd5afc718ccdf97d484020d740d20ce",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Add resources for new hires"
},
{
"type": "Title",
"element_id": "9e6c24f51918063b7c8514b3040ef52b",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Meeting notes"
},
{
"type": "NarrativeText",
"element_id": "518cd477daaec831ad223c1d2e6b790f",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Add links to meeting notes"
},
{
"type": "Title",
"element_id": "f47e8394cbf0d8338b3dad5f95bcac3e",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Team goals"
},
{
"type": "NarrativeText",
"element_id": "43770d73ac7c6d8d1a38dd0c13fa8607",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "List them here"
},
{
"type": "Title",
"element_id": "c3a1dd0877d734e8ec68983d0cf737ce",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Team news"
},
{
"type": "NarrativeText",
"element_id": "b2c91194db5ddc5e5b30240fbe5386d5",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Create a blog post to share team news. It will automatically appear here once it's published."
},
{
"type": "Title",
"element_id": "903f4f48016cafdf332e01f2d004487f",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Blog stream"
},
{
"type": "NarrativeText",
"element_id": "cfe366b5f8c8991d1e2af6e507e35a4e",
"metadata": {
"data_source": {},
"filetype": "text/html",
"page_number": 1
},
"text": "Create a blog post to share news and announcements with your team and company."
}
]
Reference in New Issue View Git Blame Copy Permalink