-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathPDF数据提取代码
116 lines (96 loc) · 3.85 KB
/
PDF数据提取代码
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
import docx
from docx import Document #导入库
#把doc文档转换为docx文档才能读取
# import win32com.client as wc
# word = wc.Dispatch("Word.Application")
# doc = word.Documents.Open(r"G:\\接单工作\\2020-12-29-煤矿产能地图\\全国煤炭企业产能分布.doc")
# doc.SaveAs(r"G:\\接单工作\\2020-12-29-煤矿产能地图\\全国煤炭企业产能分布.docx", 12, False, "", True, "", False, False, False, False)
# doc.Close()
# word.Quit()
import xlsxwriter
# 写excel
workbook = xlsxwriter.Workbook('全国煤炭企业产能分布1.xlsx') # 创建一个excel文件
worksheet = workbook.add_worksheet(u'sheet1') # 在文件中创建一个名为TEST的sheet,不加名字默认为sheet1
# # worksheet.set_column('A:A', 20) # 设置第一列宽度为20像素
# # bold = workbook.add_format({'bold': True}) # 设置一个加粗的格式对象
# # worksheet.write('A1', 'HELLO') # 在A1单元格写上HELLO
# # worksheet.write('A2', 'WORLD', bold) # 在A2上写上WORLD,并且设置为加粗
# # worksheet.write('B2', U'中文测试', bold) # 在B2上写上中文加粗
# # worksheet.write(2, 0, 32) # 使用行列的方式写上数字32,35,5
# # worksheet.write(3, 0, 35.5) # 使用行列的时候第一行起始为0,所以2,0代表着第三行的第一列,等价于A4
# # worksheet.write(4, 0, '=SUM(A3:A4)') # 写上excel公式
#
worksheet.write(0, 0, U'序号')
worksheet.write(0, 1, U'省份')
worksheet.write(0, 2, U'城市')
worksheet.write(0, 3, U'煤矿名称')
worksheet.write(0, 4, U'生产能力（万吨/年）')
sfList = ['河北省','山西省','辽宁省','吉林省','黑龙江省','江苏省','浙江省','安徽省','福建省','江西省','山东省','河南省','湖北省','湖南省','广东省','海南省','四川省','贵州省','云南省','陕西省','甘肃省','青海省','台湾省','内蒙古自治区','广西壮族自治区','西藏自治区','宁夏回族自治区','新疆维吾尔自治区','北京市','天津市','上海市','重庆市','香港特别行政区','澳门特别行政区']
rowH = []
rowH2 = []
rowH3 = []
cs = 0
sf = ''
xq = ''
id = ''
name = ''
cn = ''
row = 1
path = "全国煤炭企业产能分布.docx" #文件路径
document = Document(path) #读入文件
tables = document.tables #获取文件中的表格集
for i in tables:
# print(len(i.rows))
for j in range(0,len(i.rows)):
row_cells = i.rows[j].cells
for cell in row_cells:
# print(cell.text)
rowH.append(cell.text)
#处理数据
rowH = [i for i in rowH if i != '']
rowH2 = list(set(rowH))
rowH2.sort(key=rowH.index)
rowH = []
if rowH2 == []:
continue
a = '序号'
b = '（万吨/年）'
if a in rowH2:
continue
elif b in rowH2:
continue
if len(rowH2)==1 and rowH2[0] not in sfList:
continue
if len(rowH2) > 3:
rowH2 = rowH2[0:3]
if len(rowH2)==1:
sf = rowH2[0]
continue
if len(rowH2)==2:
xq = rowH2[1]
cs = 0
continue
if len(rowH2) == 3:
if cs%2 == 0:
id = rowH2[0]
name = rowH2[1]
cn = rowH2[2]
else:
if name != rowH2[1]:
name = name + rowH2[1]
rowH3.append(id)
rowH3.append(sf)
rowH3.append(xq)
rowH3.append(name)
rowH3.append(cn)
cs = cs + 1
print(rowH3)
if len(rowH3) != 0:
worksheet.write(row, 0, rowH3[0])
worksheet.write(row, 1, rowH3[1])
worksheet.write(row, 2, rowH3[2])
worksheet.write(row, 3, rowH3[3])
worksheet.write(row, 4, rowH3[4])
row = row + 1
rowH3 = []
workbook.close()