• 需求：爬取某个帖子的内容以及回复。
• 步骤：

import re import csv with open('./data/半自动化爬虫-抗压背锅吧.txt','r',encoding='utf-8') as f: source=f.read()

result_list=[] username_list=re.findall('username="(.*?)"',source,re.S) content_list=re.findall('class="d_post_content j_d_post_content " style="display:;">\s+(.*?)<',source, re.S) reply_time_list=re.findall('class="tail-info">(2022.*?)<',source, re.S)

for i in range(len(username_list)): result={'username': username_list[i], 'content': content_list[i], 'reply_time': reply_time_list[i]} result_list.append(result) with open('半自动化爬虫-抗压背锅吧.csv','w',encoding='utf-8') as f: writer=csv.DictWriter(f,fieldnames=['username','content','reply_time']) writer.writeheader() writer.writerows(result_list)

• 最终得到的结果是一个表格，由于有些部分是图片，所以提取不出来，这里只能提取出文字部分。
• 修改后的代码

import re import csv with open('./data/半自动化爬虫-抗压背锅吧.txt','r',encoding='utf-8') as f: source=f.read()

# 获得包含每一层所有信息的大块文本 every_reply=re.findall('class="l_post l_post_bright j_l_post clearfix "(.*?)p_props_tail props_appraise_wrap',source, re.S)

# 从每一个大文本快里面提取出各个楼层的发帖人姓名，发帖时间和发帖内容 for each in every_reply: result={} result['username'] = re.findall('username="(.*?)"',source,re.S)[0] result['content'] = re.findall('class="d_post_content j_d_post_content " style="display:;">\s+(.*?)<',source, re.S) result['reply_time'] = re.findall('class="tail-info">(2022.*?)<',source, re.S)

with open('半自动化爬虫-抗压背锅吧1.csv','w',encoding='utf-8') as f: writer=csv.DictWriter(f,fieldnames=['username','content','reply_time']) writer.writeheader() writer.writerows(result_list)