Spaces:
Sleeping
Sleeping
File size: 3,557 Bytes
ec6dd69 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 |
# MIT License
#
# Copyright (c) 2024 dataforgood
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
# Standard imports
import logging
# External imports
import os
import uuid
from io import StringIO
from pathlib import Path
import pandas as pd
from unstructured_client import UnstructuredClient
from unstructured_client.models import shared
class UnstructuredAPI:
def __init__(self, **kwargs: dict) -> dict:
"""
Builds a pdf page parser, looking for tables using
the unstructured.io api.
The kwargs given to the constructor are directly propagated
to the partition_pdf function.
You are free to define any parameter partition_pdf recognizes
"""
self.kwargs = kwargs
self.type = "unstructured_api"
def __call__(self, pdf_filepath: str) -> dict:
logging.info("\nKicking off extraction stage...")
logging.info(f"Extraction type: {self.type}, with params: {self.kwargs}")
s = UnstructuredClient(api_key_auth=os.getenv("UNSTRUCTURED_API_KEY"))
with Path(pdf_filepath).open("rb") as f:
# Note that this currently only supports a single file
files = shared.Files(
content=f.read(),
file_name=pdf_filepath,
)
req = shared.PartitionParameters(
files=files,
strategy="hi_res",
pdf_infer_table_structure="True",
**self.kwargs,
)
try:
resp = s.general.partition(req)
except Exception as e:
print(e)
else:
tables_list = []
for el in resp.elements:
if el["type"] == "Table":
# Enclose in try block to ignore case when pandas can't read the table
# Happens when the html is incorrectly formatted
try:
table = pd.read_html(StringIO(el["metadata"]["text_as_html"]))[
0
]
except Exception:
logging.info(
"Html table discarded. Pandas couldn't read the table.",
)
else:
tables_list.append(table)
# Create asset
new_asset = {
"id": uuid.uuid4(),
"type": "unstructured_api",
"params": self.kwargs,
"tables": tables_list,
}
return new_asset
|