У меня в CSV-файле есть примерно HTML код.
import pandas as pd
import numpy as np
import csv
import seaborn as sns
import re
import os
pd.set_option("display.max_rows",1000000000)
pd.set_option("display.max_columns",1000000000)
dirs = os.listdir('DataCollectionCA/')
for i in dirs:
if os.path.splitext(i)[1] == ".csv":
print(i)
dirss = 'DataCollectionCA/'
print("<div class=\"\"ContentGrid\"\">")
df = pd.read_csv(dirss+"7197409.csv") #導入資料
df_num = len(df) #計算有多少行
print(df_num)
real_df_num = df_num+1
with open ('719740999999.csv', 'a' ,newline='', encoding="utf-8") as csvfile:
writer = csv.writer(csvfile)
writer.writerow(['互動作者','發表時間','互動內容'])
for post in range(1,real_df_num):
with open (dirss+'7197409.csv', newline='', encoding="utf-8") as csvfile:
reader = csv.reader(csvfile)
column0 = [row[0] for row in reader]
for i, rows in enumerate(column0):
if i == post:
row000 = rows
with open (dirss+'7197409.csv', newline='', encoding="utf-8") as csvfile:
reader = csv.reader(csvfile)
column1 = [row[1] for row in reader]
for j, rows in enumerate(column1):
if j == post:
row001 = rows
with open (dirss+'7197409.csv', newline='', encoding="utf-8") as csvfile:
reader = csv.reader(csvfile)
column2 = [row[2] for row in reader]
for k, rows in enumerate(column2):
if k == post:
row002 = rows
author = row000
res_time = row001
original_html_code = row002
new_html_code_01 = original_html_code.replace('"<div class=""ContentGrid"">', " ")
new_html_code_02 = new_html_code_01.replace('<br>', " ")
print(new_html_code_02)
print("======")
with open ('719740999999.csv', 'a' ,newline='', encoding="utf-8") as csvfile:
writer = csv.writer(csvfile)
writer.writerow([author,res_time,new_html_code_02])
Я хочу использовать Python для замены следующей строки (это HTML код):
и так на.
Я пытался использовать следующий код для этого, но это не удалось. Я хочу заменить на пустой.
new_html_code_02 = re.sub('<div class=\"\"ContentGrid\"\">', " ", new_html_code_01)
new_html_code_02 = re.sub('<div class=""ContentGrid"">', " ", new_html_code_01)
В новом файле по-прежнему отображается эта строка. Не знаю, что решать.