#需要安装的模块：pdfplumber, pandas, openpyxl
#可从清华大学的镜像中进行安装，速度会非常快，成功率也较高
#pip install pdfplumber -i https://pypi.tuna.tsinghua.edu.cn/simple
import pdfplumber
import pandas as pd
#本代码从STC的规格书中读取对应的引脚定义表格，并把（LQFP64）对应部分存储到Excel中。
#包含路径和文件名（不含后缀），默认后缀必须为pdf，最后存为对应文件名的xlsx
# mypath = r"G:\CPU\stm32f401cb-956305"
# page_start = 37
# page_end = 43
# first_name = 'Pin Number'.lower()
# mycol = ['UQFN48','WLCSP49','LQFP64','LQFP100','UFBGA100','Pin name','Pin type','I/O St','Notes','Alternate functions','Additional functions']
# redundance_col = ['UQFN48','WLCSP49','LQFP100','UFBGA100', 'Notes']
# mypath = r"G:\CPU\stm32f410cb-956320"
# page_start = 35
# page_end = 39
# first_name = 'Pin Number'.lower()
# mycol = ['WLCSP36','LQFP48','UFQFPN48','LQFP64','UFBGA64','Pin name','Pin type','I/O St','Notes','Alternate functions','Additional functions']
# redundance_col = ['WLCSP36','LQFP48','UFQFPN48','UFBGA64', 'Notes']
# mypath = r"G:\CPU\stm32f411ce-956237"
# page_start = 38
# page_end = 46
# first_name = 'Pin Number'.lower()
# mycol = ['UFQFPN48','LQFP64','WLCSP49','LQFP100','UFBGA100','Pin name','Pin type','I/O St','Notes','Alternate functions','Additional functions']
# redundance_col = ['UFQFPN48','WLCSP49','LQFP100','UFBGA100', 'Notes']
mypath = r"G:\CPU\stm32f446mc-956216"
page_start = 46
page_end = 58
first_name = 'Pin Number'.lower()
mycol = ['LQFP64','LQFP100','WLCSP81','UFBGA144','LQFP144','Pin name','Pin type','I/O St','Notes','Alternate functions','Additional functions']
redundance_col = ['LQFP100','WLCSP81','UFBGA144','LQFP144', 'Notes']
used_col = 'LQFP64'
pdf = pdfplumber.open(mypath+".pdf")
PdfPages = pdf.pages[(page_start-1):page_end]
df = pd.DataFrame()
for page in PdfPages:
#print("page:",page.page_number)
for table in page.extract_tables():
#print(table[0][0].lower())
if table[0][0].lower() == first_name:
df = df.append(pd.DataFrame(table[2:], columns = mycol), ignore_index=True)
#print("table[2]",table[2])
#删除多余的列
df = df.drop(columns=redundance_col)
#删除多余的行
df = df[~df[used_col].isin(['-'])]
#重排行号
df = df.reset_index(drop=True)
print(df)
print(df.columns)
writer = pd.ExcelWriter(mypath+".xlsx")
df.to_excel(writer,index=None)
writer.save()
pdf.close()
print('finished')
评论0