Python如何根据关键字逐行提取文本内容问题

2018-09-06 16:42 - INFO - Coordinate: [-285.444793701, 1958.66479492, 175.649078369], End of execution.
2018-09-06 16:43 - INFO - Coordinate: [-301.866485596, 1959.87561035, 175.649200439], End of execution.
2018-09-06 16:44 - INFO - Coordinate: [-318.365051275, 1960.27978516, 175.646804815], End of execution.
2018-09-06 16:45 - INFO - Coordinate: [-334.736816406, 1961.48742676, 176.991455078], End of execution.
2018-09-06 16:46 - INFO - Coordinate: [-356.053833008, 1962.49230957, 176.991180429], End of execution.
2018-09-06 16:47 - INFO - Coordinate: [-370.848907471, 1962.69274902, 176.989471436], End of execution.
2018-09-06 16:48 - INFO - Coordinate: [-388.050415039, 1963.19372559, 178.462493896], End of execution.

# key words to extract the coordinate
str_start = "[" 
str_end   = "]"
f_orig = open('/home/yasin/test_coordinate.txt') # original file
f_coord = open('coordinate_save.txt', 'w')  # target file used to save
line = f_orig.readline()
while line:
    # find index according to the key words
    index_start = line.find(str_start)
    index_end = line.find(str_end)
    text = line[index_start : index_end]
    if text != '':
        # If there is more than one [], we can use "Coordinate" and "End" as str_start and str_end
        f_coord.write(str(line[index_start + 1 : index_end]) + '\n')
    line = f_orig.readline()
f_orig.close()
f_coord.close()

-285.444793701, 1958.66479492, 175.64907836
-301.866485596, 1959.87561035, 175.64920043
-318.365051275, 1960.27978516, 175.64680481
-334.736816406, 1961.48742676, 176.99145507
-356.053833008, 1962.49230957, 176.99118042
-370.848907471, 1962.69274902, 176.98947143
-388.050415039, 1963.19372559, 178.46249389

f_in = open('test.txt')  #源文件
f_out = open('out.txt', 'w')  #重写文件
line = f_in.readlines()    #整个文件读入
key_word = "hello"
line_split = line[0].split(key_word)   #按指定单词分割
for i in range(len(line_split)):
    if len(line_split[i])>0:
        f_out.write(key_word+":"+line_split[i].strip(",")+"\n") # 去掉逗号再加上换行即可

import pandas as pd
import re
# 读取原始 Excel 文件
df = pd.read_excel(r"C:\Users\win10\Desktop\1.xlsx")
# 定义正则表达式
pattern = re.compile(r'.*Conclusion.*', re.IGNORECASE)
# 遍历每一行数据
for index, row in df.iterrows():
    if isinstance(row["art_content"], str) and pd.notna(row["art_content"]):
        # 获取包含 "Conclusion" 的段落所在行号
        conclusion_line_index = -1
        for i, line in enumerate(row["art_content"].split("\n")):
            if pattern.match(line):
                conclusion_line_index = i
                break
        if conclusion_line_index != -1:
            # 获取从 "Conclusion" 行开始的所有段落
            conclusion_paragraphs = row["art_content"].split("\n")[conclusion_line_index + 1 :]
            # 将所有段落连接为一个字符串，并去掉首尾空格
            conclusion_section = " ".join(conclusion_paragraphs).strip()
            # 将结果赋值给对应的 conclusion 列
            df.at[index, "conclusion"] = conclusion_section
# 将处理后的数据写入新的 Excel 文件
df.to_excel(r"C:\Users\win10\Desktop\工作簿1.xlsx", index=False)