When we partition a document, the output is a list of document ``Element`` objects.
These element objects represent different components of the source document. Currently, the ``unstructured`` library supports the following element types:
Other element types that we will add in the future include tables and figures.
Different partitioning functions use different methods for determining the element type and extracting the associated content.
Document elements have a ``str`` representation. You can print them using the snippet below.
..code:: python
elements = partition(filename="example-10k.html")
for element in elements[:5]:
print(element)
print("\n")
One helpful aspect of document elements is that they allow you to cut a document down to the elements that you need for your particular use case.
For example, if you're training a summarization model you may only want to include narrative text for model training.
You'll notice that the output above includes a lot of titles and other content that may not be suitable for a summarization model.
The following code shows how you can limit your output to only narrative text with at least two sentences. As you can see, the output now only contains narrative text.
..code:: python
from unstructured.documents.elements import NarrativeText
from unstructured.partition.text_type import sentence_count
for element in elements[:100]:
if isinstance(element, NarrativeText) and sentence_count(element.text) > 2:
For ``Table`` elements, the raw text of the table will be stored in the ``text`` attribute for the Element, and HTML representation
of the table will be available in the element metadata under ``element.metadata.text_as_html``. For most documents where
table extraction is available, the ``partition`` function will extract tables automatically if they are present.
For PDFs and images, table extraction requires a relatively expensive call to a table recognition model, and so for those
document types table extraction is an option you need to enable. If you would like to extract tables for PDFs or images,
pass in ``infer_table_structured=True``. Here is an example:
..code:: python
from unstructured.partition.pdf import partition_pdf
filename = "example-docs/layout-parser-paper.pdf"
elements = partition_pdf(filename=filename, infer_table_structure=True)
tables = [el for el in elements if el.category == "Table"]
print(tables[0].text)
print(tables[0].metadata.text_as_html)
The text will look like this:
..code:: python
Dataset Base Model1 Large Model Notes PubLayNet [38] F / M M Layouts of modern scientific documents PRImA [3] M - Layouts of scanned modern magazines and scientific reports Newspaper [17] F - Layouts of scanned US newspapers from the 20th century TableBank [18] F F Table region on modern scientific and business document HJDataset [31] F / M - Layouts of history Japanese documents
And the ``text_as_html`` metadata will look like this:
..code:: html
<table><thead><th>Dataset</th><th>| Base Model’</th><th>| Notes</th></thead><tr><td>PubLayNet</td><td>[38] F/M</td><td>Layouts of modern scientific documents</td></tr><tr><td>PRImA [3]</td><td>M</td><td>Layouts of scanned modern magazines and scientific reports</td></tr><tr><td>Newspaper</td><td>F</td><td>Layouts of scanned US newspapers from the 20th century</td></tr><tr><td>TableBank</td><td>F</td><td>Table region on modern scientific and business document</td></tr><tr><td>HJDataset [31]</td><td>F/M</td><td>Layouts of history Japanese documents</td></tr></table>
