# Analyze a document at a URL:
url = "(https://github.com/Azure-Samples/document-intelligence-code-samples/blob/main/Data/add-on/add-on-highres.png?raw=true"
poller = document_analysis_client.begin_analyze_document_from_url(
"prebuilt-layout", document_url=url, features=[AnalysisFeature.OCR_HIGH_RESOLUTION] # Specify which add-on capabilities to enable.
)
result = poller.result()
# [START analyze_with_highres]
if any([style.is_handwritten for style in result.styles]):
print("Document contains handwritten content")
else:
print("Document does not contain handwritten content")
for page in result.pages:
print(f"----Analyzing layout from page #{page.page_number}----")
print(
f"Page has width: {page.width} and height: {page.height}, measured with unit: {page.unit}"
)
for line_idx, line in enumerate(page.lines):
words = line.get_words()
print(
f"...Line # {line_idx} has word count {len(words)} and text '{line.content}' "
f"within bounding polygon '{format_polygon(line.polygon)}'"
)
for word in words:
print(
f"......Word '{word.content}' has a confidence of {word.confidence}"
)
for selection_mark in page.selection_marks:
print(
f"Selection mark is '{selection_mark.state}' within bounding polygon "
f"'{format_polygon(selection_mark.polygon)}' and has a confidence of {selection_mark.confidence}"
)
for table_idx, table in enumerate(result.tables):
print(
f"Table # {table_idx} has {table.row_count} rows and "
f"{table.column_count} columns"
)
for region in table.bounding_regions:
print(
f"Table # {table_idx} location on page: {region.page_number} is {format_polygon(region.polygon)}"
)
for cell in table.cells:
print(
f"...Cell[{cell.row_index}][{cell.column_index}] has text '{cell.content}'"
)
for region in cell.bounding_regions:
print(
f"...content on page {region.page_number} is within bounding polygon '{format_polygon(region.polygon)}'"
)
# Analyze a document at a URL:
url = "https://github.com/Azure-Samples/document-intelligence-code-samples/blob/main/Data/add-on/layout-formulas.png?raw=true"
poller = document_analysis_client.begin_analyze_document_from_url(
"prebuilt-layout", document_url=url, features=[AnalysisFeature.FORMULAS] # Specify which add-on capabilities to enable
)
result = poller.result()
# [START analyze_formulas]
for page in result.pages:
print(f"----Formulas detected from page #{page.page_number}----")
inline_formulas = [f for f in page.formulas if f.kind == "inline"]
display_formulas = [f for f in page.formulas if f.kind == "display"]
print(f"Detected {len(inline_formulas)} inline formulas.")
for formula_idx, formula in enumerate(inline_formulas):
print(f"- Inline #{formula_idx}: {formula.value}")
print(f" Confidence: {formula.confidence}")
print(f" Bounding regions: {format_polygon(formula.polygon)}")
print(f"\nDetected {len(display_formulas)} display formulas.")
for formula_idx, formula in enumerate(display_formulas):
print(f"- Display #{formula_idx}: {formula.value}")
print(f" Confidence: {formula.confidence}")
print(f" Bounding regions: {format_polygon(formula.polygon)}")
# Analyze a document at a URL:
url = "https://github.com/Azure-Samples/document-intelligence-code-samples/blob/main/Data/receipt/receipt-with-tips.png?raw=true"
poller = document_analysis_client.begin_analyze_document_from_url(
"prebuilt-layout", document_url=url, features=[AnalysisFeature.STYLE_FONT] # Specify which add-on capabilities to enable.
)
result = poller.result()
# [START analyze_fonts]
# DocumentStyle has the following font related attributes:
similar_font_families = defaultdict(list) # e.g., 'Arial, sans-serif
font_styles = defaultdict(list) # e.g, 'italic'
font_weights = defaultdict(list) # e.g., 'bold'
font_colors = defaultdict(list) # in '#rrggbb' hexadecimal format
font_background_colors = defaultdict(list) # in '#rrggbb' hexadecimal format
if any([style.is_handwritten for style in result.styles]):
print("Document contains handwritten content")
else:
print("Document does not contain handwritten content")
print("\n----Fonts styles detected in the document----")
# Iterate over the styles and group them by their font attributes.
for style in result.styles:
if style.similar_font_family:
similar_font_families[style.similar_font_family].append(style)
if style.font_style:
font_styles[style.font_style].append(style)
if style.font_weight:
font_weights[style.font_weight].append(style)
if style.color:
font_colors[style.color].append(style)
if style.background_color:
font_background_colors[style.background_color].append(style)
print(f"Detected {len(similar_font_families)} font families:")
for font_family, styles in similar_font_families.items():
print(f"- Font family: '{font_family}'")
print(f" Text: '{get_styled_text(styles, result.content)}'")
print(f"\nDetected {len(font_styles)} font styles:")
for font_style, styles in font_styles.items():
print(f"- Font style: '{font_style}'")
print(f" Text: '{get_styled_text(styles, result.content)}'")
print(f"\nDetected {len(font_weights)} font weights:")
for font_weight, styles in font_weights.items():
print(f"- Font weight: '{font_weight}'")
print(f" Text: '{get_styled_text(styles, result.content)}'")
print(f"\nDetected {len(font_colors)} font colors:")
for font_color, styles in font_colors.items():
print(f"- Font color: '{font_color}'")
print(f" Text: '{get_styled_text(styles, result.content)}'")
print(f"\nDetected {len(font_background_colors)} font background colors:")
for font_background_color, styles in font_background_colors.items():
print(f"- Font background color: '{font_background_color}'")
print(f" Text: '{get_styled_text(styles, result.content)}'")
# Analyze a document at a URL:
url = "https://github.com/Azure-Samples/document-intelligence-code-samples/blob/main/Data/add-on/add-on-barcodes.jpg?raw=true"
poller = document_analysis_client.begin_analyze_document_from_url(
"prebuilt-layout", document_url=url, features=[AnalysisFeature.BARCODES] # Specify which add-on capabilities to enable.
)
result = poller.result()
# [START analyze_barcodes]
# Iterate over extracted barcodes on each page.
for page in result.pages:
print(f"----Barcodes detected from page #{page.page_number}----")
print(f"Detected {len(page.barcodes)} barcodes:")
for barcode_idx, barcode in enumerate(page.barcodes):
print(f"- Barcode #{barcode_idx}: {barcode.value}")
print(f" Kind: {barcode.kind}")
print(f" Confidence: {barcode.confidence}")
print(f" Bounding regions: {format_polygon(barcode.polygon)}")
# Analyze a document at a URL:
url = "https://github.com/Azure-Samples/document-intelligence-code-samples/blob/main/Data/add-on/add-on-fonts_and_languages.png?raw=true"
poller = document_analysis_client.begin_analyze_document_from_url(
"prebuilt-layout", document_url=url, features=[AnalysisFeature.LANGUAGES] # Specify which add-on capabilities to enable.
)
result = poller.result()
# [START analyze_languages]
print("----Languages detected in the document----")
print(f"Detected {len(result.languages)} languages:")
for lang_idx, lang in enumerate(result.languages):
print(f"- Language #{lang_idx}: locale '{lang.locale}'")
print(f" Confidence: {lang.confidence}")
print(f" Text: '{','.join([result.content[span.offset : span.offset + span.length] for span in lang.spans])}'")
v3.1 (GA)
