import re

import csv

# data = open('tieba01.txt', 'r', encoding='UTF-8').readlines()

# print(len(data))

with open('tieba01.txt', 'r', encoding='UTF-8') as f:

? ? source= f.read()

#search函數(shù)只能從左至右找出第一個(gè)最大的匹配，findall函數(shù)可以找出所有的匹配，并返回一個(gè)list列表

# findall(pattern, string, flags=0)? re.S忽略換行

result_list= []

username_list= re.findall('username="(.*?)"',source,re.S)#

content_list= re.findall('d_post_content j_d_post_content " style="display:;">(.*?)</div>', source, re.S)

reply_time_list=re.findall('class="tail-info">(2020.*?)<', source, re.S)

def clear_content(src):

? ? newstr= re.sub(r'(<img class.*?>)', '', src) #sub是substitute的所寫(xiě)，表示替換；re.sub(pattern, repl, string, count=0, flags=0)

? ? return newstr

print(username_list[0],content_list[12])

for iin range(len(username_list)):

? ? clearstr= clear_content(content_list[i])

? ? result= {'username':username_list[i],

? ? ? ? ? ? ? 'content':clearstr,

? ? ? ? ? ? ? 'time': reply_time_list[i]}

? ? result_list.append(result)

with open('tieba01.csv','w',newline='',encoding='utf-8-sig') as f:

? ? csv_write= csv.writer(f)

? ? writer= csv.DictWriter(f,fieldnames=['username','content','time'])

? ? writer.writeheader()

? ? writer.writerows(result_list)

# with open('E:/dst.csv', 'wb') as dstfile:? # 寫(xiě)入方式選擇wb，否則有空行

#? ? writer = csv.DictWriter(dstfile, fieldnames=['username','content','time'])

#? ? writer.writeheader()? # 寫(xiě)入表頭

#? ? writer.writerows(data)? # 批量寫(xiě)入