convert all the tables in pdf to excels

pdf_to_excel.py

from ctypes.util import find_library
print(find_library("gs"))
import camelot

# pdf path
path3 = '/Users/paul/Code/2015年中册_small.pdf'

# data save path
data_path='/Users/paul/PycharmProjects/pythonProject/pdf2excel/data/'

# 输入pdf文件的页面数
num_total = 345

# 指定每一批次处理的页面数
batch_size=30

bath_str_list=[]
for i in range(num_total // batch_size):
    cur_before = i * batch_size + 1
    cur_end = i * batch_size + batch_size
    page_str = '{}-{}'.format(cur_before, cur_end)
    bath_str_list.append(page_str)

    if cur_end == (num_total-(num_total % batch_size)):
        # 尾部处理
        cur_before = cur_end + 1
        cur_end = num_total
        page_str = '{}-{}'.format(cur_before, cur_end)
        bath_str_list.append(page_str)


for each in bath_str_list:
    print('starting solve pages batch :'+each)

    dfs = camelot.read_pdf(path3, pages=page_str, flavor="stream")
    for j in range(len(dfs)):
        print(dfs[j])
        dfs[j].to_excel(data_path + page_str + "@" + str(j) + '.xlsx')

    print(each + ' complete!')