python获取笔趣阁最近更新小说列表

 目标数据：

代码：

import requests
from lxml import etree


headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36'}

web_Source_Code = requests.get("http://www.yuetutu.com", headers=headers)

print(web_Source_Code.status_code)

html = etree.HTML(web_Source_Code.text)
block_1 = html.xpath('//div[@id="newscontent"]/div[@class="l"]/ul/li')

return_Date = []


for block_2 in block_1:
    novel_Classification = block_2.xpath('span[@class="s1"]/a/text()')
    name_Of_The_Novel = block_2.xpath('span[@class="s2"]/a/text()')
    novel_Chapter = block_2.xpath('span[@class="s3"]/a/text()')
    author_Of_The_Novel = block_2.xpath('span[@class="s4"]/a/text()')
    update_Time = block_2.xpath('span[@class="s5"]/text()')
    return_Date.append({
        "novel_Classification": novel_Classification,
        "name_Of_The_Novel": name_Of_The_Novel,
        "novel_Chapter": novel_Chapter,
        "author_Of_The_Novel": author_Of_The_Novel,
        "update_Time": update_Time
    })


for date_s in return_Date:
    print(date_s)

 

输出截图：

来源：CSDN

作者：Ferencz

链接：https://blog.csdn.net/Ferencz/article/details/104088066