Spaces:
Running
Running
File size: 7,858 Bytes
2621d77 8835144 2621d77 |
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 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 |
#! pip install spire.doc
#! pip install Spire.XLS
import pandas as pd
from spire.doc import *
from spire.doc.common import *
from spire.xls import *
from spire.xls.common import *
from NER import cleanText
import requests
class wordDoc(): # using python-docx
def __init__(self, wordDoc,saveFolder):
self.wordDoc = wordDoc
self.saveFolder = saveFolder
def openFile(self):
document = Document()
return document.LoadFromFile(self.wordDoc)
def extractTextByPage(self):
# reference: https://medium.com/@alice.yang_10652/extract-text-from-word-documents-with-python-a-comprehensive-guide-95a67e23c35c#:~:text=containing%20specific%20content.-,Spire.,each%20paragraph%20using%20the%20Paragraph.
json = {}
#doc = self.openFile()
# Create an object of the FixedLayoutDocument class and pass the Document object to the class constructor as a parameter
try:
doc = Document()
doc.LoadFromFile(self.wordDoc)
except:
response = requests.get(self.wordDoc)
name = self.wordDoc.split("/")[-1]
with open(self.saveFolder+"/" + name, "wb") as temp_file: # Create a temporary file to store the downloaded data
temp_file.write(response.content)
doc = Document()
doc.LoadFromFile(self.saveFolder+"/" + name)
text = doc.GetText()
return text
def extractTableAsText(self):
getDoc = ''
try:
# reference:
# https://www.e-iceblue.com/Tutorials/Python/Spire.Doc-for-Python/Program-Guide/Table/Python-Extract-Tables-from-Word-Documents.html?gad_source=1&gclid=Cj0KCQiA6Ou5BhCrARIsAPoTxrCj3XSsQsDziwqE8BmVlOs12KneOlvtKnn5YsDruxK_2T_UUhjw6NYaAtJhEALw_wcB
doc = Document()
doc.LoadFromFile(self.wordDoc)
getDoc = "have document"
except:
response = requests.get(self.wordDoc)
name = self.wordDoc.split("/")[-1]
with open(self.saveFolder+"/" + name, "wb") as temp_file: # Create a temporary file to store the downloaded data
temp_file.write(response.content)
doc = Document()
doc.LoadFromFile(self.saveFolder+"/" + name)
getDoc = "have document"
json = {}
if len(getDoc) > 0:
# Loop through the sections
for s in range(doc.Sections.Count):
# Get a section
section = doc.Sections.get_Item(s)
# Get the tables in the section
json["Section" + str(s)] = {}
tables = section.Tables
# Loop through the tables
for i in range(0, tables.Count):
# Get a table
table = tables.get_Item(i)
# Initialize a string to store the table data
tableData = ''
# Loop through the rows of the table
for j in range(0, table.Rows.Count):
# Loop through the cells of the row
for k in range(0, table.Rows.get_Item(j).Cells.Count):
# Get a cell
cell = table.Rows.get_Item(j).Cells.get_Item(k)
# Get the text in the cell
cellText = ''
for para in range(cell.Paragraphs.Count):
paragraphText = cell.Paragraphs.get_Item(para).Text
cellText += (paragraphText + ' ')
# Add the text to the string
tableData += cellText
if k < table.Rows.get_Item(j).Cells.Count - 1:
tableData += '\t'
# Add a new line
tableData += '\n'
json["Section" + str(s)]["Table"+str(i)] = tableData
return json
def extractTableAsList(self):
tables = []
try:
doc = Document()
doc.LoadFromFile(self.wordDoc)
except:
response = requests.get(self.wordDoc)
name = self.wordDoc.split("/")[-1]
with open(os.path.join(self.saveFolder, name), "wb") as f:
f.write(response.content)
doc = Document()
doc.LoadFromFile(os.path.join(self.saveFolder, name))
for s in range(doc.Sections.Count):
section = doc.Sections.get_Item(s)
for i in range(section.Tables.Count):
table = section.Tables.get_Item(i)
table_data = []
for row in range(table.Rows.Count):
row_data = []
for cell in range(table.Rows.get_Item(row).Cells.Count):
cell_obj = table.Rows.get_Item(row).Cells.get_Item(cell)
cell_text = ""
for p in range(cell_obj.Paragraphs.Count):
cell_text += cell_obj.Paragraphs.get_Item(p).Text.strip() + " "
row_data.append(cell_text.strip())
table_data.append(row_data)
tables.append(table_data)
return tables
def extractTableAsExcel(self):
getDoc = ''
try:
# reference:
# https://www.e-iceblue.com/Tutorials/Python/Spire.Doc-for-Python/Program-Guide/Table/Python-Extract-Tables-from-Word-Documents.html?gad_source=1&gclid=Cj0KCQiA6Ou5BhCrARIsAPoTxrCj3XSsQsDziwqE8BmVlOs12KneOlvtKnn5YsDruxK_2T_UUhjw6NYaAtJhEALw_wcB
doc = Document()
doc.LoadFromFile(self.wordDoc)
getDoc = "have document"
except:
response = requests.get(self.wordDoc)
name = self.wordDoc.split("/")[-1]
with open(self.saveFolder+"/" + name, "wb") as temp_file: # Create a temporary file to store the downloaded data
temp_file.write(response.content)
doc = Document()
doc.LoadFromFile(self.saveFolder+"/" + name)
getDoc = "have document"
if len(getDoc) > 0:
try:
# Create an instance of Workbook
wb = Workbook()
wb.Worksheets.Clear()
# Loop through sections in the document
for i in range(doc.Sections.Count):
# Get a section
section = doc.Sections.get_Item(i)
# Loop through tables in the section
for j in range(section.Tables.Count):
# Get a table
table = section.Tables.get_Item(j)
# Create a worksheet
ws = wb.Worksheets.Add(f'Table_{i+1}_{j+1}')
# Write the table to the worksheet
for row in range(table.Rows.Count):
# Get a row
tableRow = table.Rows.get_Item(row)
# Loop through cells in the row
for cell in range(tableRow.Cells.Count):
# Get a cell
tableCell = tableRow.Cells.get_Item(cell)
# Get the text in the cell
cellText = ''
for paragraph in range(tableCell.Paragraphs.Count):
paragraph = tableCell.Paragraphs.get_Item(paragraph)
cellText = cellText + (paragraph.Text + ' ')
# Write the cell text to the worksheet
ws.SetCellValue(row + 1, cell + 1, cellText)
# Save the workbook
name = self.wordDoc.split("/")[-1]
if self.saveFolder == None:
wb.SaveToFile('/content/drive/MyDrive/CollectData/NER/excel/TestExamples/output/'+name+".xlsx", FileFormat.Version2016)
nameFile = '/content/drive/MyDrive/CollectData/NER/excel/TestExamples/output/'+name+".xlsx"
else:
wb.SaveToFile(self.saveFolder+'/'+name+".xlsx", FileFormat.Version2016)
nameFile = self.saveFolder+'/'+name + ".xlsx"
doc.Close()
wb.Dispose()
return nameFile
except: return "No table found on word doc"
else:
return "No table found on word doc"
def getReference(self):
pass
def getSupMaterial(self):
pass |