Analyzing_COP_Files/Notes at master · ephraim888sun/Analyzing_COP_Files · GitHub

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
# #Now give the pdf name
# #pdfFileObj = open(r'C:\Users\Ephraim.Sun\Desktop\proj2\test\ALE 1\ALE 1 - CURRENT SCHEMATIC.pdf', 'rb')
# #pdfFileObj = 'C:\\Users\\Ephraim.Sun\\Desktop\\proj2\\test\\ABADAN 1\\ABADAN 1T - CURRENT SCHEMATIC.pdf'
# pdfFileObj = open(r'C:\Users\Ephraim.Sun\Desktop\proj2\test\ADA 1\ADA 1 - CURRENT SCHEMATIC.pdf', 'rb')
#
#
# pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
# #print(pdfReader.numPages) # will give total number of pages in pdf
#
# #extract all texts from page1
# pageObj = pdfReader.getPage(0)
# page_content = pageObj.extractText()
#
# """get a list from the pdf"""
# list = page_content.splitlines()
# #print(list)
#
# # index_date = list.index('Original Spud Date')
# # date = index_date+1
# # #print(list[date])
# #
# # index_API = list.index('API / UWI')
# # API = index_API+1
# # #print(list[API])
#
# def follow(x):
#     if(x in list):
#         y = list.index(x)
#         return list[y+1]
#     else:
#         return "Not in list"
#
# API = follow('API / UWI')
# #print(API)
# DATE = follow('Original Spud Date')
# #print(DATE)
#
# """take the contents from list and put the good stuff into list_content"""
# start = list.index("al)",)
# end  = list.index("0District")
# list_content = []
# list_content = list[start+1:end]
# #print(list_content)
#
# """Make all list_content into one big string test"""
# test = ''
# for i in list_content:
#     x = i
#     test = test + x
# #print(" ")
# #print(test)
#
# # TODO Come Back later!
# list_org = test.split()
# #print(" ")
# #print(list_org)
#
# """EXCEL TIME"""
# wb = load_workbook(filename = r"C:\Users\Ephraim.Sun\Desktop\proj2\practice.xlsx")
# ws = wb.active
#
# row_cell = ' '
# cell_Date = ' '
#
# for row in ws.iter_rows():
#     for cell in row:
#         if cell.value == API:
#             row_cell = cell.row
# #print(row_cell)
#
# for row in ws.iter_rows():
#     for cell in row:
#         if cell.value == 'Spud Date':
#             cell_Date = cell.coordinate
# #print(cell_Date)
#
# # print(type(row_cell))
# # print(type(cell_Date))
# cell_col = cell_Date.rstrip(cell_Date[1])
# #print(cell_col)
# coordinates = str(cell_col) + str(row_cell)
# #print(coordinates)
# ws[coordinates] = DATE
# #print(DATE)
#
# wb.save(filename = r'C:\Users\Ephraim.Sun\Desktop\proj2\practice.xlsx')

# """DIRECTORY"""
# rootdir = r'C:\Users\Ephraim.Sun\Desktop\proj2\test'
#
# for subdir, dirs, files in os.walk(rootdir):
#     for file in files:
#         if file.endswith("CURRENT SCHEMATIC.pdf"):
#             pdfFileObj = os.path.join(subdir, file)