BeautifulSoup之诗词名句网站中三国演义小说内容抓取

#导包
import requests
from bs4 import BeautifulSoup



#指定url
url = 'http://www.shicimingju.com/book/sanguoyanyi.html'

#发起请求
headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
    }

#此方法用来获取具体章节的具体内容
def get_content(url):
    #发起请求
    response = requests.get(url=url,headers=headers)
    #获取页面数据
    page_text = response.text
    
    #创建BeatufulSoup对象
    soup = BeautifulSoup(page_text,'lxml')
    content = soup.find('div',class_="chapter_content").text
    return content
    
    
    
    
    
response = requests.get(url=url,headers=headers)

#获取页面数据
page_text = response.text

#数据分析
#创建BeatufulSoup对象
soup = BeautifulSoup(page_text,'lxml')
contents = soup.select('.book-mulu > ul > li > a')

#持久化存储
fp=open('./三国演义.txt','w',encoding='utf-8')
num = 1
for content in contents:
    content_url='http://www.shicimingju.com'+content['href']
    title = content.string
    print("开始下载第%d章：%s"%(num,title))
    content_detail = get_content(content_url)
    fp.write(title+':'+content_detail +"\n\n\n")
    print("开始下载第%d章下载完毕"%num)
    num+=1
    
    
print("全部数据写入完毕")

注：此代码仅供学习参阅