try:
c.value = dict_to_print[key].strip()
except:
#Using this area to keep track of encoding errors
print "This text caused an error"
print dict_to_print[key]
c.value = "Raw text contained bad chars, see intepreter."
#c.value=dict_to_print[key]
i = i + 1
wb.save(book_name)
return book_name
## Gets the user to select the document containing the OCR'ed text
ocr_text_path = useful.getPath(get_default_directory())
## Uses that path to extract the data.
document_list = get_document_list(ocr_text_path)
## Retrieves the utility library from the utility dictionary for the specified utility
## which is currently determined with a function (That just returns "Consolidated Edison"
utility_library = get_utility_library(get_current_utility(),
get_utility_library_directory())
## Sample of using def get raw chars
#library_entry_sample=utility_library['extraction_parameters']['G&T Demand1']
#raw_chars=get_raw_chars(document_list[0],library_entry_sample)
## Collecting the raw characters, but I would also like to collect
## the flags found by the regular expressions.
filename=useful.getFilenameFromPath(target_pdf)
filehandle=file(outputFile,'a')
filehandle.write("TEXT FROM "+str(filename)+" PAGE "+str(i))
filehandle.write("\n")
filehandle.write(text_string)
filehandle.write('\n')
return outputFile
##----THE ACTUAL PROGRAM----##
## Ask user for the target pdf, in the future I plan to have it
## be able to get all the pdfs in a directory! Or maybe I'll have
## the user make the PDF themselves? because this program still doesn't really
## know how to handle blank pages.
target_pdf = useful.getPath(default_directory)[0]
#print target_pdf
print "---------------------------------------------------"
print "THE TARGET PDF FILENAME IS: "+target_pdf[target_pdf.rindex('/')+1:]
#print "---------------------------------------------------"
## Initializations for Tess
#print "Importing Tess"
api = tesseract.TessBaseAPI()
api.SetOutputName("outputName");
api.Init(".","eng",tesseract.OEM_DEFAULT)
api.SetPageSegMode(tesseract.PSM_AUTO)
#print "made tess decs"
## Other Initializations
c=ws.cell(row=last_occ_row, column=i)
try:
c.value=dict_to_print[key].strip()
except:
#Using this area to keep track of encoding errors
print "This text caused an error"
print dict_to_print[key]
c.value="Raw text contained bad chars, see intepreter."
#c.value=dict_to_print[key]
i=i+1
wb.save(book_name)
return book_name
## Gets the user to select the document containing the OCR'ed text
ocr_text_path=useful.getPath(get_default_directory())
## Uses that path to extract the data.
document_list=get_document_list(ocr_text_path)
## Retrieves the utility library from the utility dictionary for the specified utility
## which is currently determined with a function (That just returns "Consolidated Edison"
utility_library=get_utility_library(get_current_utility(),get_utility_library_directory())
## Sample of using def get raw chars
#library_entry_sample=utility_library['extraction_parameters']['G&T Demand1']
#raw_chars=get_raw_chars(document_list[0],library_entry_sample)
## Collecting the raw characters, but I would also like to collect
## the flags found by the regular expressions.
match_dict={}
refined_results.append(result)
return refined_results
###--------------------------------------------------------------------------------------------
###--------START OF PROGRAM---------------------------------------------------------------
import os
import useful
## Testing directory
default_directory="C:\Users\James McGlynn\My Programs\Python Programs\pdf2txt\WorkRelated"
## Choose library here
library=refined_ConEd_Lib
## Have user navigate to text file
text_file=useful.getPath(default_directory)
## Open the text file and put every line in a list
with open(text_file,'r') as fh:
lines=fh.readlines()
## Pull every other line from the list (That's just how I made the document)
document_list=get_document_list(lines)
## Use the library and the text to try and get the data you want
refined_results=extract_information(library, document_list)
def print_by_account_number(library,refined_results,text_file):
## Openpyxl library imports
