mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-10-04 12:57:55 +00:00
a501d1d18f
Adding table extraction to HTML partitioning.
This PR utilizes 'table' HTML elements to extract and parse HTML tables
and return them in partitioning.
```
# checkout this branch, go into ipython shell
In [1]: from unstructured.partition.html import partition_html
In [2]: path_to_html = "{html sample file with table}"
In [3]: elements = partition_html(path_to_html)
```
you should see the table in the elements list!
165 lines
5.0 KiB
JSON
165 lines
5.0 KiB
JSON
[
|
||
{
|
||
"type": "Table",
|
||
"element_id": "10b5ef18a3c7fb1d7436b2e1b256e5b9",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1,
|
||
"text_as_html": "<table><br><tbody><br><tr><td>Driver </td><td> </td><td> </td><td> </td><td> </td><td> </td></tr><br><tr><td>Approver </td><td> </td><td> </td><td> </td><td> </td><td> </td></tr><br><tr><td>Contributors</td><td> </td><td> </td><td> </td><td> </td><td> </td></tr><br><tr><td>Informed </td><td> </td><td> </td><td> </td><td> </td><td> </td></tr><br><tr><td>Objective </td><td> </td><td> </td><td> </td><td> </td><td> </td></tr><br><tr><td>Due date </td><td> </td><td> </td><td> </td><td> </td><td> </td></tr><br><tr><td>Key outcomes</td><td> </td><td> </td><td> </td><td> </td><td> </td></tr><br><tr><td>Status </td><td>NOT STARTED</td><td>/</td><td>IN PROGRESS</td><td>/</td><td>COMPLETE</td></tr><br></tbody><br></table>"
|
||
},
|
||
"text": "Driver Approver Contributors Informed Objective Due date Key outcomes Status NOT STARTED / IN PROGRESS / COMPLETE"
|
||
},
|
||
{
|
||
"type": "Title",
|
||
"element_id": "4e2022d4483a407d85060675f64fbe17",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1
|
||
},
|
||
"text": "\\uD83E\\uDD14 Problem Statement"
|
||
},
|
||
{
|
||
"type": "Title",
|
||
"element_id": "81163675915a75217e4116686fdca412",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1
|
||
},
|
||
"text": "🎯 Scope"
|
||
},
|
||
{
|
||
"type": "Table",
|
||
"element_id": "f1f364fbde77afa0e99e8ea7ab4f7c3f",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1,
|
||
"text_as_html": "<table><br><tbody><br><tr><td>Must have: </td></tr><br><tr><td>Nice to have:</td></tr><br><tr><td>Not in scope:</td></tr><br></tbody><br></table>"
|
||
},
|
||
"text": "Must have: Nice to have: Not in scope:"
|
||
},
|
||
{
|
||
"type": "Title",
|
||
"element_id": "e8b61a28d07e977379b42df455a1cde4",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1
|
||
},
|
||
"text": "\\uD83D\\uDDD3 Timeline"
|
||
},
|
||
{
|
||
"type": "Title",
|
||
"element_id": "5043f71fbc70e35c0be413d4135be99f",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1
|
||
},
|
||
"text": "Lane 1"
|
||
},
|
||
{
|
||
"type": "Title",
|
||
"element_id": "d5a2e177c588bf0c4f914baa4fae85b6",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1
|
||
},
|
||
"text": "Lane 2"
|
||
},
|
||
{
|
||
"type": "Title",
|
||
"element_id": "c98ba1acbd22a15ddddfc244cbd8a2db",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1
|
||
},
|
||
"text": "Feature 1"
|
||
},
|
||
{
|
||
"type": "Title",
|
||
"element_id": "e04620c8b3b611b3fefecef89baa63a9",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1
|
||
},
|
||
"text": "Feature 2"
|
||
},
|
||
{
|
||
"type": "Title",
|
||
"element_id": "82e522a86692cc50ee5c020c8e6ce6a0",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1
|
||
},
|
||
"text": "Feature 3"
|
||
},
|
||
{
|
||
"type": "Title",
|
||
"element_id": "822f7c45ea725c535970aab819a8ff10",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1
|
||
},
|
||
"text": "Feature 4"
|
||
},
|
||
{
|
||
"type": "Title",
|
||
"element_id": "6e0f6eca4ff17d3377c1c3e8e1f73457",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1
|
||
},
|
||
"text": "iOS app"
|
||
},
|
||
{
|
||
"type": "Title",
|
||
"element_id": "0b60fe04b3c5c3c76371b6eca8b19c8e",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1
|
||
},
|
||
"text": "Android app"
|
||
},
|
||
{
|
||
"type": "Title",
|
||
"element_id": "e1cc184f345d146586fb12527c4fa696",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1
|
||
},
|
||
"text": "\\uD83D\\uDEA9 Milestones and deadlines"
|
||
},
|
||
{
|
||
"type": "Table",
|
||
"element_id": "3f4ea3840d79521680c89a91dcd883cf",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1,
|
||
"text_as_html": "<table><br><tbody><br><tr><td>Milestone</td><td>Owner</td><td>Deadline</td><td>Status</td></tr><br><tr><td> </td><td> </td><td> </td><td> </td></tr><br><tr><td> </td><td> </td><td> </td><td> </td></tr><br><tr><td> </td><td> </td><td> </td><td> </td></tr><br></tbody><br></table>"
|
||
},
|
||
"text": "Milestone Owner Deadline Status"
|
||
},
|
||
{
|
||
"type": "Title",
|
||
"element_id": "890c9b6d8d69ca1de5fd7a8b83fe78ff",
|
||
"metadata": {
|
||
"data_source": {},
|
||
"filetype": "text/html",
|
||
"page_number": 1
|
||
},
|
||
"text": "\\uD83D\\uDD17 Reference materials"
|
||
}
|
||
] |