mirror of
https://github.com/semantica-agi/semantica.git
synced 2026-08-29 04:26:20 +00:00
KaifAhmad1
943be0c10f
The previous commit's fix to 03_Document_Parsing.ipynb collapsed the cell's source array into a single string and dropped the trailing newline. Restore the original array-of-lines formatting so the diff is limited to the corrected badge URL.
7.6 KiB
7.6 KiB
Document Parsing
Overview
This notebook demonstrates how to parse various document formats using Semantica's parsing modules. You'll learn to extract text, metadata, and structured data from PDFs, DOCX, CSV, JSON, XML, and HTML files.
Documentation: API Reference
Learning Objectives
- Use
DocumentParserfor general document parsing - Use format-specific parsers:
PDFParser,DOCXParser,CSVParser,JSONParser,XMLParser,HTMLParser - Extract text content and metadata from documents
- Parse structured data formats
Installation
Install Semantica from PyPI:
pip install semantica
# Or with all optional dependencies:
pip install semantica[all]
Step 1: Document Parser
Parse various document formats using the general DocumentParser.
In [ ]:
!pip install semantica
In [ ]:
from semantica.parse import DocumentParser
import tempfile
import os
document_parser = DocumentParser()
temp_dir = tempfile.mkdtemp()
sample_txt = os.path.join(temp_dir, "sample.txt")
with open(sample_txt, 'w') as f:
f.write("Apple Inc. is a technology company. Tim Cook is the CEO.")
text = document_parser.extract_text(sample_txt)
metadata = document_parser.extract_metadata(sample_txt)
text[:50], metadata
In [ ]:
from semantica.parse import CSVParser
csv_parser = CSVParser()
csv_file = os.path.join(temp_dir, "data.csv")
with open(csv_file, 'w') as f:
f.write("name,company,role\n")
f.write("Tim Cook,Apple Inc.,CEO\n")
f.write("Satya Nadella,Microsoft Corporation,CEO\n")
csv_data = csv_parser.parse(csv_file)
print(f"Parsed CSV with {len(csv_data.rows)} rows")
print(f"Columns: {csv_data.headers}")
for row in csv_data.rows[:2]:
print(f" {row}")
In [ ]:
from semantica.parse import JSONParser
import json
json_parser = JSONParser()
json_file = os.path.join(temp_dir, "data.json")
data = {
"companies": [
{"name": "Apple Inc.", "ceo": "Tim Cook"},
{"name": "Microsoft Corporation", "ceo": "Satya Nadella"}
]
}
with open(json_file, 'w') as f:
json.dump(data, f)
json_data = json_parser.parse(json_file)
print(f"Parsed JSON: {json_data.data}")
print(f"Companies: {len(json_data.data.get('companies', []))}")
In [ ]:
from semantica.parse import XMLParser
xml_parser = XMLParser()
xml_file = os.path.join(temp_dir, "data.xml")
xml_content = """<?xml version="1.0"?>
<companies>
<company name="Apple Inc." ceo="Tim Cook"/>
<company name="Microsoft Corporation" ceo="Satya Nadella"/>
</companies>"""
with open(xml_file, 'w') as f:
f.write(xml_content)
xml_data = xml_parser.parse(xml_file)
print(f"Parsed XML with {len(xml_data.root.children)} elements")
print(f"Root element: {xml_data.root.tag if xml_data.root else 'None'}")
In [ ]:
from semantica.parse import HTMLParser
html_parser = HTMLParser()
html_file = os.path.join(temp_dir, "page.html")
html_content = """<html>
<head><title>Sample Page</title></head>
<body>
<h1>Technology Companies</h1>
<p>Apple Inc. is a technology company.</p>
</body>
</html>"""
with open(html_file, 'w') as f:
f.write(html_content)
html_data = html_parser.parse(html_file)
print(f"Parsed HTML")
print(f"Title: {html_data.metadata.get('title', 'N/A')}")
print(f"Text content: {html_data.text[:50]}...")
In [ ]:
from semantica.parse import StructuredDataParser
structured_parser = StructuredDataParser()
parsed_json = structured_parser.parse_data(json_file, data_format="json")
parsed_csv = structured_parser.parse_data(csv_file, data_format="csv")
print(f"Structured parser parsed JSON: {len(parsed_json.get('data', {}).get('companies', []))} companies")
print(f"Structured parser parsed CSV: {len(parsed_csv.get('rows', []))} rows")