Skip to content
This repository has been archived by the owner on Sep 20, 2023. It is now read-only.

fix: added if statement to filter out dir blob files #63

Merged
merged 5 commits into from Dec 2, 2020
Merged

fix: added if statement to filter out dir blob files #63

Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
5c433c3
fix: added if statement to filter out dir blob files
munkhuushmgl Dec 1, 2020
59742e4
removed unncessary files
munkhuushmgl Dec 1, 2020
d22a3a7
fixed the lint
munkhuushmgl Dec 1, 2020
1f29bb0
made changes according to the feedback
munkhuushmgl Dec 2, 2020
4998b04
added helpful comment
munkhuushmgl Dec 2, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
35 changes: 18 additions & 17 deletions samples/snippets/batch_process_documents_sample_v1beta3.py
View file
Open in desktop
Expand Up @@ -78,23 +78,24 @@ def batch_process_documents(

for i, blob in enumerate(blob_list):
# Download the contents of this blob as a bytes object.
blob_as_bytes = blob.download_as_bytes()
document = documentai.types.Document.from_json(blob_as_bytes)

print(f"Fetched file {i + 1}")

# For a full list of Document object attributes, please reference this page: https://googleapis.dev/python/documentai/latest/_modules/google/cloud/documentai_v1beta3/types/document.html#Document

# Read the text recognition output from the processor
for page in document.pages:
for form_field in page.form_fields:
field_name = get_text(form_field.field_name, document)
field_value = get_text(form_field.field_value, document)
print("Extracted key value pair:")
print(f"\t{field_name}, {field_value}")
for paragraph in document.pages:
paragraph_text = get_text(paragraph.layout, document)
print(f"Paragraph text:\n{paragraph_text}")
if ".json" in blob.name:
munkhuushmgl marked this conversation as resolved.
Show resolved Hide resolved
blob_as_bytes = blob.download_as_bytes()

document = documentai.types.Document.from_json(blob_as_bytes)
print(f"Fetched file {i + 1}")

# For a full list of Document object attributes, please reference this page: https://googleapis.dev/python/documentai/latest/_modules/google/cloud/documentai_v1beta3/types/document.html#Document

# Read the text recognition output from the processor
for page in document.pages:
for form_field in page.form_fields:
field_name = get_text(form_field.field_name, document)
field_value = get_text(form_field.field_value, document)
print("Extracted key value pair:")
print(f"\t{field_name}, {field_value}")
for paragraph in document.pages:
paragraph_text = get_text(paragraph.layout, document)
print(f"Paragraph text:\n{paragraph_text}")


# Extract shards from the text field
Expand Down