# _*_ encoding：utf-8 _*_ import pdfplumber from openpyxl import load_workbook from os import scandir, remove from os.path import exists from sys import argv def traversal_files(path, w2t): # 功能：以列表的形式分别返回指定路径下的文件和文件夹，不包含子目录 # 参数：路径 # 返回值：路径下的文件夹列表 路径下的文件列表 if not exists(path): msg = f'数据文件夹{path}不存在，请确认后重试......' w2t(msg, 0, 1, 'red') else: dirs = files = [] for item in scandir(path): if item.is_dir(): dirs.append(item.path) elif item.is_file(): files.append(item.path) return dirs, files def p_iso(file, p_files, ws, tmpfile): p_files.append(file) pdf = pdfplumber.open(file) with open(tmpfile, mode='w', encoding='utf-8') as fb: for page in pdf.pages: fb.write(page.extract_text()) with open(tmpfile, mode='r', encoding='utf-8') as fb: lines = fb.readlines() lines = [line for line in lines if not line.startswith('Page ')] for line in lines: if line.strip() == "Pose Accuracy and Repeatability": index = lines.index(line) ws.cell(row=3, column=7).value = float(lines[index+4].split()[1]) ws.cell(row=4, column=7).value = float(lines[index+5].split()[1]) ws.cell(row=5, column=7).value = float(lines[index+6].split()[1]) ws.cell(row=6, column=7).value = float(lines[index+7].split()[1]) ws.cell(row=7, column=7).value = float(lines[index+8].split()[1]) ws.cell(row=8, column=7).value = float(lines[index+4].split()[2]) ws.cell(row=9, column=7).value = float(lines[index+5].split()[2]) ws.cell(row=10, column=7).value = float(lines[index+6].split()[2]) ws.cell(row=11, column=7).value = float(lines[index+7].split()[2]) ws.cell(row=12, column=7).value = float(lines[index+8].split()[2]) elif line.strip() == 'Pose Accuracy Variation': index = lines.index(line) ws.cell(row=13, column=7).value = float(lines[index+4].split()[1]) ws.cell(row=14, column=7).value = float(lines[index+5].split()[1]) ws.cell(row=15, column=7).value = float(lines[index+6].split()[1]) elif line.strip() == 'Distance Accuracy': index = lines.index(line) ws.cell(row=16, column=7).value = float(lines[index + 4].split()[1]) ws.cell(row=17, column=7).value = float(lines[index + 4].split()[2]) elif line.strip() == 'Stabilisation Time and Overshoot': index = lines.index(line) ws.cell(row=18, column=7).value = float(lines[index + 7].split()[3]) ws.cell(row=19, column=7).value = float(lines[index + 7].split()[2]) elif line.strip() == 'Velocity Accuracy and Repeatability': index = lines.index(line) ws.cell(row=20, column=7).value = float(lines[index + 4].split()[1]) ws.cell(row=21, column=7).value = float(lines[index + 4].split()[2]) ws.cell(row=22, column=7).value = float(lines[index + 4].split()[3]) elif line.strip()[:31] == 'Path Accuracy and Repeatability': index = lines.index(line) ws.cell(row=29, column=7).value = float(lines[index + 4].split()[1]) ws.cell(row=30, column=7).value = float(lines[index + 4].split()[2]) elif line.strip() == 'Corner Overshoot and Roundoff': index = lines.index(line) ws.cell(row=35, column=7).value = float(lines[index + 4].split()[1]) ws.cell(row=36, column=7).value = float(lines[index + 4].split()[2]) elif line.strip() == 'Robot Weaving': index = lines.index(line) ws.cell(row=41, column=7).value = float(lines[index + 4].split()[2]) ws.cell(row=42, column=7).value = float(lines[index + 4].split()[3]) ws.cell(row=43, column=7).value = float(lines[index + 4].split()[4]) else: pass def p_iso_100(file, p_files, ws, tmpfile): p_files.append(file) pdf = pdfplumber.open(file) with open(tmpfile, mode='w', encoding='utf-8') as fb: for page in pdf.pages: fb.write(page.extract_text()) with open(tmpfile, mode='r', encoding='utf-8') as fb: lines = fb.readlines() lines = [line for line in lines if not line.startswith('Page ')] for line in lines: if line.strip() == 'Velocity Accuracy and Repeatability': index = lines.index(line) ws.cell(row=26, column=7).value = float(lines[index + 4].split()[1]) ws.cell(row=27, column=7).value = float(lines[index + 4].split()[2]) ws.cell(row=28, column=7).value = float(lines[index + 4].split()[3]) elif line.strip()[:31] == 'Path Accuracy and Repeatability': index = lines.index(line) ws.cell(row=33, column=7).value = float(lines[index + 4].split()[1]) ws.cell(row=34, column=7).value = float(lines[index + 4].split()[2]) elif line.strip() == 'Corner Overshoot and Roundoff': index = lines.index(line) ws.cell(row=39, column=7).value = float(lines[index + 4].split()[1]) ws.cell(row=40, column=7).value = float(lines[index + 4].split()[2]) elif line.strip() == 'Robot Weaving': index = lines.index(line) ws.cell(row=47, column=7).value = float(lines[index + 4].split()[2]) ws.cell(row=48, column=7).value = float(lines[index + 4].split()[3]) ws.cell(row=49, column=7).value = float(lines[index + 4].split()[4]) else: pass def p_iso_1000(file, p_files, ws, tmpfile): p_files.append(file) pdf = pdfplumber.open(file) with open(tmpfile, mode='w', encoding='utf-8') as fb: for page in pdf.pages: fb.write(page.extract_text()) with open(tmpfile, mode='r', encoding='utf-8') as fb: lines = fb.readlines() lines = [line for line in lines if not line.startswith('Page ')] for line in lines: if line.strip() == 'Velocity Accuracy and Repeatability': index = lines.index(line) ws.cell(row=23, column=7).value = float(lines[index + 4].split()[1]) ws.cell(row=24, column=7).value = float(lines[index + 4].split()[2]) ws.cell(row=25, column=7).value = float(lines[index + 4].split()[3]) elif line.strip()[:31] == 'Path Accuracy and Repeatability': index = lines.index(line) ws.cell(row=31, column=7).value = float(lines[index + 4].split()[1]) ws.cell(row=32, column=7).value = float(lines[index + 4].split()[2]) elif line.strip() == 'Corner Overshoot and Roundoff': index = lines.index(line) ws.cell(row=37, column=7).value = float(lines[index + 4].split()[1]) ws.cell(row=38, column=7).value = float(lines[index + 4].split()[2]) elif line.strip() == 'Robot Weaving': index = lines.index(line) ws.cell(row=44, column=7).value = float(lines[index + 4].split()[2]) ws.cell(row=45, column=7).value = float(lines[index + 4].split()[3]) ws.cell(row=46, column=7).value = float(lines[index + 4].split()[4]) else: pass def main(path, w2t): dirs, files = traversal_files(path, 1) try: wb = load_workbook(path + "/iso-results.xlsx") ws = wb.active for i in range(3, 50): ws.cell(row=i, column=7).value = None tmpfile = f"{path}\\data.txt" except Exception as Err: w2t(f"发生错误：{Err}", 0, 2, 'red') p_files = [] for file in files: if file.endswith('.pdf') and file.split('\\')[-1] == 'ISO.pdf': w2t(f"正在处理{file}......") p_iso(file, p_files, ws, tmpfile) w2t(f"文件{file}已处理完毕。\n") elif file.endswith('.pdf') and file.split('\\')[-1] == 'ISO-V100.pdf': w2t(f"正在处理{file}......") p_iso_100(file, p_files, ws, tmpfile) w2t(f"文件{file}已处理完毕。\n") elif file.endswith('.pdf') and file.split('\\')[-1] == 'ISO-V1000.pdf': w2t(f"正在处理{file}......") p_iso_1000(file, p_files, ws, tmpfile) w2t(f"文件{file}已处理完毕。\n") else: pass wb.save(path + '/iso-results.xlsx') wb.close() if len(p_files) == 0: w2t(f"目录 {path} 下没有需要处理的文件，需要确认......", 0, 3, 'red') else: remove(tmpfile) w2t("------------------------------------------") w2t("所有文件均已处理完毕！") if __name__ == '__main__': main(path=argv[1], w2t=argv[2])