# fields = ['Unnamed: 0', 'Unnamed: 1', '合计:', '人民币元', '美元', '合计:.1', '美元.1', '沙特里亚尔', '合计:.2', '人民币元.1', '美元.2', # '沙特里亚尔.1', '合计:.3', '美元.3', '沙特里亚尔.2'] cleaned_sentence = [] a = 0 while a < len(fields): current_word = fields[a] if current_word == "Unnamed: 0" and len(cleaned_sentence) == 0: print("0") cleaned_sentence.append(fields[0:fields.index("合计:")]) a += 1 elif current_word == "合计:" and len(cleaned_sentence) > 0: print("1") cleaned_sentence.append(fields[fields.index("合计:"):fields.index("合计:.1")]) a += 1 elif current_word == "合计:.1" and len(cleaned_sentence) > 0: print("2") sub_list = fields[fields.index("合计:.1"):fields.index("合计:.2")] # sub_list.append(fields[-1]) cleaned_sentence.append(sub_list) a += 1 elif current_word == "合计:.2" and len(cleaned_sentence) > 0: print("3") sub_list = fields[fields.index("合计:.2"):fields.index("合计:.3")] # sub_list.append(fields[-1]) cleaned_sentence.append(sub_list) a += 1 elif current_word == "合计:.3" and len(cleaned_sentence) > 0: print("4") sub_list = fields[fields.index("合计:.3"):] # sub_list.append(fields[-1]) cleaned_sentence.append(sub_list) a += 1 else: a += 1 print(cleaned_sentence) for each in cleaned_sentence: if each[0] == "Unnamed: 0": print("find") # each = str(each).replace("Unnamed: 0","单位编号") each[0] = "单位编号" # each = str(each).replace("Unnamed: 1","单位名称") each[1] = "单位名称" print(each) if each[0] == "合计:": for i in range(0, len(each)): if "合计:" in each[i]: # each = str(each).replace("合计:.1", "期初合计") each[i] = "期初合计" elif "人民币元" in each[i]: # each = str(each).replace("人民币元", "期初人民币元") each[i] = "期初人民币元" elif "美元" in each[i]: each[i] = "期初美元" elif "沙特里亚尔" in each[i]: # each = str(each).replace("沙特里亚尔", "期初沙特里亚尔") each[i] = "期初沙特里亚尔" print(each) if each[0] == "合计:.1": for i in range(0, len(each)): if "合计:.1" in each[i]: # each = str(each).replace("合计:.1", "期初合计") each[i] = "本期增加合计" elif "人民币元" in each[i]: # each = str(each).replace("人民币元", "期初人民币元") each[i] = "本期增加人民币元" elif "美元" in each[i]: each[i] = "本期增加美元" elif "沙特里亚尔" in each[i]: # each = str(each).replace("沙特里亚尔", "期初沙特里亚尔") each[i] = "本期增加沙特里亚尔" print(each) if each[0] == "合计:.2": for i in range(0, len(each)): if "合计:.2" in each[i]: # each = str(each).replace("合计:.1", "期初合计") each[i] = "本期减少合计" elif "人民币元" in each[i]: # each = str(each).replace("人民币元", "期初人民币元") each[i] = "本期减少人民币元" elif "美元" in each[i]: each[i] = "本期减少美元" elif "沙特里亚尔" in each[i]: # each = str(each).replace("沙特里亚尔", "期初沙特里亚尔") each[i] = "本期减少沙特里亚尔" print(each) if each[0] == "合计:.3": for i in range(0, len(each)): if "合计:.3" in each[i]: # each = str(each).replace("合计:.1", "期初合计") each[i] = "期末合计" elif "人民币元" in each[i]: # each = str(each).replace("人民币元", "期初人民币元") each[i] = "期末人民币元" elif "美元" in each[i]: each[i] = "期末美元" elif "沙特里亚尔" in each[i]: # each = str(each).replace("沙特里亚尔", "期初沙特里亚尔") each[i] = "期末沙特里亚尔" print(each) print(cleaned_sentence) list = [] for each in cleaned_sentence: list.extend(each) print(list) # 整理好的表头