爬虫第一课

Posted 2020-10-28 慢慢来会比较快

 一、小说下载

小说网址是：http://www.biqukan.com

import requests
from bs4 import BeautifulSoup

class downloader(object):
    
    def __init__(self):
        self.url = ‘http://www.biqukan.com/1_1408/‘
        self.serve = ‘http://www.biqukan.com‘
        self.page_url = []
        self.page_name = []
 
    #获取每个章节的链接和章节名字
    def get_page_url(self):
        html = requests.get(self.url)
        soup = BeautifulSoup(html.text,‘lxml‘)
        url_list = soup.find_all(‘div‘,class_="listmain")
        url_list = BeautifulSoup(str(url_list[0]))
        a = url_list.find_all(‘a‘)
        for each in a[12:]:
            self.page_url.append(self.serve + each.get(‘href‘))
            self.page_name.append(each.string)
  
    #小说页面的内容
    def get_html(self,url):
        html = requests.get(url)
        soup = BeautifulSoup(html.text,‘lxml‘)
        content = soup.find_all(‘div‘,class_="showtxt")
        content = content[0].text
        content = content.replace(‘<br/><br/>‘,‘\n\n‘)
        return content
    
    #写入txt文件中
    def writer(self,path,name,text):
        with open(path,‘a‘,encoding=‘utf-8‘) as f:
            f.write(name+‘\n‘)
            f.write(text)
            f.write(‘\n\n‘)            
        
        
if __name__ == ‘__main__‘:
    dl = downloader()  #实例化类
    dl.get_page_url()   #运行获取章节名称，url的函数
    name = dl.page_name  #获取到的章节名称和url赋值给name，url
    url = dl.page_url
    for i in range(len(name)):
        dl.writer(‘小说.txt‘,name[i],dl.get_html(url[i]))