I'm trying to setup the sample code used for pdf data extract using the python sdk for Adobe PDF API service on a databricks environment. This cluster has just one driver node. But i'm facing issue while accessing the configuration files uploaded to DBFS folder.
Please let me know how do i fix the issue.
Here is the code snippet
import logging
import os.path
from adobe.pdfservices.operation.auth.credentials import Credentials
from adobe.pdfservices.operation.exception.exceptions import ServiceApiException, ServiceUsageException, SdkException
from adobe.pdfservices.operation.pdfops.options.extractpdf.extract_pdf_options import ExtractPDFOptions
from adobe.pdfservices.operation.pdfops.options.extractpdf.extract_element_type import ExtractElementType
from adobe.pdfservices.operation.pdfops.options.extractpdf.extract_renditions_element_type import \
ExtractRenditionsElementType
from adobe.pdfservices.operation.pdfops.options.extractpdf.table_structure_type import TableStructureType
from adobe.pdfservices.operation.execution_context import ExecutionContext
from adobe.pdfservices.operation.io.file_ref import FileRef
from adobe.pdfservices.operation.pdfops.extract_pdf_operation import ExtractPDFOperation
#logging.basicConfig(level=os.environ.get("LOGLEVEL", "INFO"))
credentials = Credentials.service_account_credentials_builder() \
.from_file("/dbfs/FileStore/pdfservices_api_credentials.json") \
.build()
execution_context = ExecutionContext.create(credentials)
extract_pdf_operation = ExtractPDFOperation.create_new()
source = FileRef.create_from_local_file("/dbfs/FileStore/form.pdf")
extract_pdf_operation.set_input(source)
# Build ExtractPDF options and set them into the operation
extract_pdf_options: ExtractPDFOptions = ExtractPDFOptions.builder() \
.with_elements_to_extract([ExtractElementType.TEXT, ExtractElementType.TABLES]) \
.with_element_to_extract_renditions(ExtractRenditionsElementType.TABLES) \
.with_table_structure_format(TableStructureType.CSV) \
.build()
extract_pdf_operation.set_options(extract_pdf_options)
# Execute the operation.
result: FileRef = extract_pdf_operation.execute(execution_context)
result.save_as(base_path + "/output/ExtractTextInfoFromPDF.zip")
Here is the error details:
INFO:adobe.pdfservices.operation.pdfops.extract_pdf_operation:All validations successfully done. Beginning ExtractPDF operation execution
INFO:py4j.java_gateway:Received command c on object id p0
INFO:py4j.java_gateway:Received command c on object id p0
INFO:py4j.java_gateway:Received command c on object id p0
INFO:py4j.java_gateway:Received command c on object id p0
SdkException: description =Exception in fetching access token, requestTrackingId=(<class 'AttributeError'>, AttributeError("'str' object has no attribute 'get'"), <traceback object at 0x7f7572a3fd00>)
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
/local_disk0/.ephemeral_nfs/envs/pythonEnv-150d96ca-003d-4671-a6d9-ab8e566616d1/lib/python3.8/site-packages/adobe/pdfservices/operation/internal/auth/jwt_authenticator.py in refresh_token(self)
62 data=access_token_request_payload, headers={})
---> 63 response = http_client.process_request(http_request=http_request, success_status_codes=[HTTPStatus.OK],
64 error_response_handler=self.handle_ims_failure)
/local_disk0/.ephemeral_nfs/envs/pythonEnv-150d96ca-003d-4671-a6d9-ab8e566616d1/lib/python3.8/site-packages/adobe/pdfservices/operation/internal/http/http_client.py in process_request(http_request, success_status_codes, error_response_handler)
37 response = _execute_request(http_request)
---> 38 if _handle_response_and_retry(response, success_status_codes,
39 error_response_handler, not http_request.authenticator, http_request.request_key) and http_request.retryable:
/local_disk0/.ephemeral_nfs/envs/pythonEnv-150d96ca-003d-4671-a6d9-ab8e566616d1/lib/python3.8/site-packages/adobe/pdfservices/operation/internal/http/http_client.py in _handle_response_and_retry(response, success_status_codes, error_response_handler, is_ims_api, request_key)
94 "Failure response code {error_code} encountered from backend".format(error_code=response.status_code))
---> 95 should_retry = ResponseUtil.handle_api_failures(response, request_key, is_ims_api)
96 return should_retry if should_retry else error_response_handler(response)
It looks like you're missing forward slash in the file name, so the file is considered as path relative to the current directory /databricks/driver/. Instead of dbfs/tmp/pdf/pdfservices-api-credentials.json try /dbfs/tmp/pdf/pdfservices-api-credentials.json.
Update for community edition: There is no support for /dbfs mount on the community edition, so you need to copy file from DBFS to the local file system for use. You can do it using dbutils.fs.cp command:
# copy file to local disk
dbutils.fs.cp("/tmp/pdf/pdfservices-api-credentials.json",
"file:/tmp/pdfservices-api-credentials.json")
# use it
credentials = Credentials.service_account_credentials_builder() \
.from_file("/tmp/pdfservices-api-credentials.json") \
.build()
Related
The following code snippet is from a Google tutorial, it simply prints the names of files on GCP in a given bucket:
from google.cloud import storage
def list_blobs(bucket_name):
"""Lists all the blobs in the bucket."""
# bucket_name = "your-bucket-name"
storage_client = storage.Client()
# Note: Client.list_blobs requires at least package version 1.17.0.
blobs = storage_client.list_blobs(bucket_name)
for blob in blobs:
print(blob.name)
list_blobs('sn_project_data')
No from the command line I can run:
$ python path/file.py
And in my terminal the files in said bucket are printed out. Great, it works!
However, this isn't quite my goal. I'm looking to open a file and act upon it. For example:
df = pd.read_excel(filename)
print(df.iloc[0])
However, when I pass the path to the above, the error returned reads "invalid file path." So I'm sure there is some sort of GCP specific function call to actually access these files...
What command(s) should I run?
Edit: This video https://www.youtube.com/watch?v=ED5vHa3fE1Q shows a trick to open files and needs to use StringIO in the process. But it doesn't support excel files, so it's not an effective solution.
read_excel() does not support google cloud storage file path as of now but it can read data in bytes.
pandas.read_excel(io, sheet_name=0, header=0, names=None,
index_col=None, usecols=None, squeeze=False, dtype=None, engine=None,
converters=None, true_values=None, false_values=None, skiprows=None,
nrows=None, na_values=None, keep_default_na=True, na_filter=True,
verbose=False, parse_dates=False, date_parser=None, thousands=None,
comment=None, skipfooter=0, convert_float=True, mangle_dupe_cols=True,
storage_options=None)
Parameters: io : str, bytes, ExcelFile, xlrd.Book, path object, or
file-like object
What you can do is use the blob object and use download_as_bytes() to convert the object into bytes.
Download the contents of this blob as a bytes object.
For this example I just used a random sample xlsx file and read the 1st sheet:
from google.cloud import storage
import pandas as pd
bucket_name = "your-bucket-name"
blob_name = "SampleData.xlsx"
storage_client = storage.Client()
bucket = storage_client.bucket(bucket_name)
blob = bucket.blob(blob_name)
data_bytes = blob.download_as_bytes()
df = pd.read_excel(data_bytes)
print(df)
Test done:
I am trying to read a config file from S3 bucket via python script run by AWS glue. But the file is not read.
from __future__ import print_function
from pyspark import SparkContext
from awsglue.utils import getResolvedOptions
import sys
import ConfigParser
from os import path
sc = SparkContext.getOrCreate()
print("My New Job")
args = getResolvedOptions(sys.argv, ['config_path', 'section_type'])
config_path = args["config_path"]
print("config_path")
print(config_path)
config = ConfigParser.ConfigParser()
filenameread = config.read(['s3://temp-bucket/config/myconfig.ini','s3://temp-bucket/config/myconfig.config','s3://temp-bucket/config/myconfig.txt'])
print("filenameread")
print(filenameread)
print("sections")
print(config.sections())
The log appears as below. The config sections is empty.
{
"timestamp": 1551705899133,
"message": "Container: container_somenumber on ip-somenumber.ec2.internal_somenumber\nLogType:stdout\nLog Upload Time:Mon Mar 04 13:24:51 +0000 2019\nLogLength:175\nLog Contents:\nMy New Job\nconfig_path\ns3://temp-bucket/config/myconfig.ini\nfilenameread\n[]\nsections\n[]\nEnd of LogType:stdout\n",
"ingestionTime": 1551705899785
},
Can anybody help on this. Using Python 2.7.15 .
This can be achieved by defining the --extra-files key in the job parameters section.
Due to this, the filepath(s)(comma separated in case of multiple files) mentioned in the value of this key are brought to the run time environment during execution.
Then using configparser, one can easily access the file as a conventional config file.
For more detailed info, refer https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html
IOPub data rate exceeded.
The notebook server will temporarily stop sending output
to the client in order to avoid crashing it.
To change this limit, set the config variable
--NotebookApp.iopub_data_rate_limit.
Current values:
NotebookApp.iopub_data_rate_limit=1000000.0 (bytes/sec)
NotebookApp.rate_limit_window=3.0 (secs)
An IOPub error usually occurs when you try to print a large amount of data to the console. Check your print statements - if you're trying to print a file that exceeds 10MB, its likely that this caused the error. Try to read smaller portions of the file/data.
I faced this issue while reading a file from Google Drive to Colab.
I used this link https://colab.research.google.com/notebook#fileId=/v2/external/notebooks/io.ipynb
and the problem was in this block of code
# Download the file we just uploaded.
#
# Replace the assignment below with your file ID
# to download a different file.
#
# A file ID looks like: 1uBtlaggVyWshwcyP6kEI-y_W3P8D26sz
file_id = 'target_file_id'
import io
from googleapiclient.http import MediaIoBaseDownload
request = drive_service.files().get_media(fileId=file_id)
downloaded = io.BytesIO()
downloader = MediaIoBaseDownload(downloaded, request)
done = False
while done is False:
# _ is a placeholder for a progress object that we ignore.
# (Our file is small, so we skip reporting progress.)
_, done = downloader.next_chunk()
downloaded.seek(0)
#Remove this print statement
#print('Downloaded file contents are: {}'.format(downloaded.read()))
I had to remove the last print statement since it exceeded the 10MB limit in the notebook - print('Downloaded file contents are: {}'.format(downloaded.read()))
Your file will still be downloaded and you can read it in smaller chunks or read a portion of the file.
The above answer is correct, I just commented the print statement and the error went away. just keeping it here so someone might find it useful. Suppose u are reading a csv file from google drive just import pandas and add pd.read_csv(downloaded) it will work just fine.
file_id = 'FILEID'
import io
from googleapiclient.http import MediaIoBaseDownload
request = drive_service.files().get_media(fileId=file_id)
downloaded = io.BytesIO()
downloader = MediaIoBaseDownload(downloaded, request)
done = False
while done is False:
# _ is a placeholder for a progress object that we ignore.
# (Our file is small, so we skip reporting progress.)
_, done = downloader.next_chunk()
downloaded.seek(0)
pd.read_csv(downloaded);
Maybe this will help..
from via sv1997
IOPub Error on Google Colaboratory in Jupyter Notebook
IoPub Error is occurring in Colab because you are trying to display the output on the console itself(Eg. print() statements) which is very large.
The IoPub Error maybe related in print function.
So delete or annotate the print function. It may resolve the error.
%cd darknet
!sed -i 's/OPENCV=0/OPENCV=1/' Makefile
!sed -i 's/GPU=0/GPU=1/' Makefile
!sed -i 's/CUDNN=0/CUDNN=1/' Makefile
!sed -i 's/CUDNN_HALF=0/CUDNN_HALF=1/' Makefile
!apt update
!apt-get install libopencv-dev
its important to update your make file. and also, keep your input file name correct
I want to convert my pdf files to txt files and used pdfminer3k module & pdf2txt.py, however, I got an error.
pdf2txt.py -o file.txt -t tag file.pdf
This is my code at cmd screen.
Traceback (most recent call last):
File "C:\Python36\lib\site.py", line 67, in
import os
File "C:\Python36\lib\os.py", line 409
yield from walk(new_path, topdown, onerror, followlinks)
^
SyntaxError: invalid syntax
This is an error message that I got.
Could you help me to fix this problem??
Added for reference: Great resourse:
http://www.degeneratestate.org/posts/2016/Jun/15/extracting-tabular-data-from-pdfs/
The -t flag is the type of output. The options are text, tag, xml, and html.
Tag refers to generating a tag for xml. Replace tag with text in your command and try it.
The order of optional input also matters.
You also must invoke python, your command line does'nt know what import means, yet some of your environment seems to be setup. My example is for windows cmd from Anaconda3\Scripts directory. If your in juptyer notebook or a console, you should be able to run import pdf2txt with the .py
To setup your environment you need to append the os.path.append(yourpdfdirectory) otherwise file.pdf will not be found.
Try python pdf2txt.py -t text -o file.txt file.pdf
Or if you are brave...this is how to do programmatically. The trouble with xml is if you want to get the text, each character from xml tree is returned in an arbitrary order. You can get it to work but you need to build the string character by character which is not that hard, its just logically time consuming.
fp = open(filesin,'rb')
parser = PDFParser(fp)
doc = PDFDocument()
parser.set_document(doc)
doc.set_parser(parser)
doc.initialize('')
rsrcmgr = PDFResourceManager(caching=False)
laparams = LAParams(all_texts=True)
laparams.boxes_flow = -0.2
laparams.paragraph_indent = 0.2
laparams.detect_vertical = False
#laparams.heuristic_word_margin = 0.03
laparams.word_margin = 0.2
laparams.line_margin = 0.3
outfp = open(filesin+".out.tag" ,'wb')
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
#process_pdf(rsrcmgr, device, pdfparse, pagenos,caching=c, check_extractable=True)
for p,page in enumerate(doc.get_pages()):
if p == 0: #temporary for page 1
interpreter.process_page(page)
layout = device.get_result()
alltextinbox = ''
#This is a rich environment so categorization of this object hierarchy is needed
for c,lt_obj in enumerate(layout):
#print(type(lt_obj),"This is type ",c,"th object on the ",p,"th page")
if isinstance(lt_obj,LTTextBoxHorizontal) or isinstance(lt_obj,LTTextBox) or isinstance(lt_obj,LTTextLine):
print("Type ,",type(lt_obj)," and text ..",lt_obj.get_text())
obj_textbox_line.update({lt_obj:lt_obj.get_text()})
elif p != 0:
pass
fp.close()
#print(obj_textbox_line)
#call the column finder here
#check_matching("example", "example1")
#text_doc_df = pd.DataFrame(obj_textbox_line,columns=['text'])
#print (text_doc_df)
pass
I'm working on a generic row/column matcher. If you don't want to bother, you can buy this software already for like 150 bucks for a pro converter.
I'm not getting the Google example work
https://cloud.google.com/hadoop/examples/bigquery-connector-spark-example
PySpark
There are a few mistakes in the code i think, like:
'# Output Parameters
'mapred.bq.project.id': '',
Should be: 'mapred.bq.output.project.id': '',
and
'# Write data back into new BigQuery table.
'# BigQueryOutputFormat discards keys, so set key to None.
(word_counts
.map(lambda pair: None, json.dumps(pair))
.saveAsNewAPIHadoopDataset(conf))
will give an error message. If I change it to:
(word_counts
.map(lambda pair: (None, json.dumps(pair)))
.saveAsNewAPIHadoopDataset(conf))
I get the error message:
org.apache.hadoop.io.Text cannot be cast to com.google.gson.JsonObject
And whatever I try I can not make this work.
There is a dataset created in BigQuery with the name I gave it in the 'conf' with a trailing '_hadoop_temporary_job_201512081419_0008'
And a table is created with '_attempt_201512081419_0008_r_000000_0' on the end. But are always empty
Can anybody help me with this?
Thanks
We are working to update the documentation because, as you noted, the docs are incorrect in this case. Sorry about that! While we're working to update the docs, I wanted to get you a reply ASAP.
Casting problem
The most important problem you mention is the casting issue. Unfortunately,PySpark cannot use the BigQueryOutputFormat to create Java GSON objects. The solution (workaround) is to save the output data into Google Cloud Storage (GCS) and then load it manually with the bq command.
Code example
Here is a code sample which exports to GCS and loads the data into BigQuery. You could also use subprocess and Python to execute the bq command programatically.
#!/usr/bin/python
"""BigQuery I/O PySpark example."""
import json
import pprint
import pyspark
sc = pyspark.SparkContext()
# Use the Google Cloud Storage bucket for temporary BigQuery export data used
# by the InputFormat. This assumes the Google Cloud Storage connector for
# Hadoop is configured.
bucket = sc._jsc.hadoopConfiguration().get('fs.gs.system.bucket')
project = sc._jsc.hadoopConfiguration().get('fs.gs.project.id')
input_directory ='gs://{}/hadoop/tmp/bigquery/pyspark_input'.format(bucket)
conf = {
# Input Parameters
'mapred.bq.project.id': project,
'mapred.bq.gcs.bucket': bucket,
'mapred.bq.temp.gcs.path': input_directory,
'mapred.bq.input.project.id': 'publicdata',
'mapred.bq.input.dataset.id': 'samples',
'mapred.bq.input.table.id': 'shakespeare',
}
# Load data in from BigQuery.
table_data = sc.newAPIHadoopRDD(
'com.google.cloud.hadoop.io.bigquery.JsonTextBigQueryInputFormat',
'org.apache.hadoop.io.LongWritable',
'com.google.gson.JsonObject',
conf=conf)
# Perform word count.
word_counts = (
table_data
.map(lambda (_, record): json.loads(record))
.map(lambda x: (x['word'].lower(), int(x['word_count'])))
.reduceByKey(lambda x, y: x + y))
# Display 10 results.
pprint.pprint(word_counts.take(10))
# Stage data formatted as newline delimited json in Google Cloud Storage.
output_directory = 'gs://{}/hadoop/tmp/bigquery/pyspark_output'.format(bucket)
partitions = range(word_counts.getNumPartitions())
output_files = [output_directory + '/part-{:05}'.format(i) for i in partitions]
(word_counts
.map(lambda (w, c): json.dumps({'word': w, 'word_count': c}))
.saveAsTextFile(output_directory))
# Manually clean up the input_directory, otherwise there will be BigQuery export
# files left over indefinitely.
input_path = sc._jvm.org.apache.hadoop.fs.Path(input_directory)
input_path.getFileSystem(sc._jsc.hadoopConfiguration()).delete(input_path, True)
print """
###########################################################################
# Finish uploading data to BigQuery using a client e.g.
bq load --source_format NEWLINE_DELIMITED_JSON \
--schema 'word:STRING,word_count:INTEGER' \
wordcount_dataset.wordcount_table {files}
# Clean up the output
gsutil -m rm -r {output_directory}
###########################################################################
""".format(
files=','.join(output_files),
output_directory=output_directory)