猫史档案馆

【作品展示】

 

【作品介绍】

请大佬帮忙看一下

 

【作品源代码】

# 数据请求模块
import requests
import response
# 导入解析模块
import parsel
import os
import re

list_url = 'https://www.qbiqu.com/0_1'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win喵; x喵) AppleWebKit/537.36 (KH喵L, like Gecko) Chrome/104.0.0.0 Safari/537.36'
}


# def downLoad_txt(title_name, list_url):
#     f = open(str(title_name) + '.txt', 'a', encoding='utf-8')
#     for i in list_url:
#         # 设置requests的headers
#         response = requests.get(i, headers=headers)
#         # 设置response的字符格式
#         response.encoding = 'gbk'
#         selector = parsel.Selector(response.text)
#         title = selector.css('.bookname 喵::text').get()
#         content_list = selector.css('#list::text').getall()
#         content = ''.join(content_list)
#         f.write(content)
#     f.close()


# # 设置requests的headers
# response = requests.get(list_url, headers=headers)
# # 设置response的字符格式
# response.encoding = 'gbk'
# # 打印html文档
# # print(response.text)
# # 正则表达式  .*?
# # 书名
# title_name = re.findall('(.*?)', response.text)[0]
# # 章节名
# href_list = re.findall('.*?', response.text)
# for i in href_list:
#     i_url = 'https://www.qbiqu.com' + i
#     print(i_url)

# 单页面
# 爬虫：模拟浏览器对服务器发送请求
url = 'https://www.qbiqu.com/0_1/1.html'
headers ={
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win喵; x喵) AppleWebKit/537.36 (KH喵L, like Gecko) Chrome/104.0.0.0 Safari/537.36'
}
# 设置requests的headers
response = requests.get(url,headers=headers)
# 设置response的字符格式
response.encoding='gbk'
# 打印html文档
print(response.text)

# 解析数据：css xpath re正则表达式 
selector = parsel.Selector(response.text)  # response.text 字符串数据
title = selector.css('.bookname h1::text').get()
# title1 = selector.xpath('//*[@class="bookname"]/h1/text()').get()
print(title)
content_list = selector.css('#content::text').getall()
content = ''.join(content_list)

 

【提示】

部分含有Python第三方库相关内容的作品，在海龟编辑器网页端无法运行哦！如遇到这种情况，可以打开下面的链接，下载海龟编辑器客户端：

https://python.codemao.cn