FilesExpand file tree

 master

/

quickstart_beta.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

62 lines (49 loc) · 2.22 KB

 master

/

quickstart_beta.py

Copy path

Top

File metadata and controls

• Code
• Blame

62 lines (49 loc) · 2.22 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

# Copyright 2020 Google LLC

#

# Licensed under the Apache License, Version 2.0 (the "License");

# you may not use this file except in compliance with the License.

# You may obtain a copy of the License at

#

# http://www.apache.org/licenses/LICENSE-2.0

#

# Unless required by applicable law or agreed to in writing, software

# distributed under the License is distributed on an "AS IS" BASIS,

# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

# See the License for the specific language governing permissions and

# limitations under the License.

# [START documentai_quickstart_beta]

from google.cloud import documentai_v1beta2 as documentai

def main(project_id='YOUR_PROJECT_ID',

input_uri='gs://cloud-samples-data/documentai/invoice.pdf'):

"""Process a single document with the Document AI API, including

text extraction and entity extraction."""

client = documentai.DocumentUnderstandingServiceClient()

gcs_source = documentai.types.GcsSource(uri=input_uri)

# mime_type can be application/pdf, image/tiff,

# and image/gif, or application/json

input_config = documentai.types.InputConfig(

gcs_source=gcs_source, mime_type='application/pdf')

# Location can be 'us' or 'eu'

parent = 'projects/{}/locations/us'.format(project_id)

request = documentai.types.ProcessDocumentRequest(

parent=parent,

input_config=input_config)

document = client.process_document(request=request)

# All text extracted from the document

print('Document Text: {}'.format(document.text))

def _get_text(el):

"""Convert text offset indexes into text snippets.

"""

response = ''

# If a text segment spans several lines, it will

# be stored in different text segments.

for segment in el.text_anchor.text_segments:

start_index = segment.start_index

end_index = segment.end_index

response += document.text[start_index:end_index]

return response

for entity in document.entities:

print('Entity type: {}'.format(entity.type))

print('Text: {}'.format(_get_text(entity)))

print('Mention text: {}\n'.format(entity.mention_text))

# [END documentai_quickstart_beta]