HomeWorkDay05---下载小说

最新推荐文章于 2022-11-29 22:13:52 发布

23岁右前卫想进国足

最新推荐文章于 2022-11-29 22:13:52 发布

阅读量140

点赞数

分类专栏： DFZY

本文链接：https://blog.csdn.net/houwenhan123/article/details/99974365

版权

DFZY 专栏收录该内容

13 篇文章 0 订阅

订阅专栏

import multiprocessing
from lxml import etree
import requests
import re
def novel():
    response = requests.get('https://www.17k.com/list/3015690.html')   #请求网页 <Response [200]>
    response.encoding = 'utf8'
    tree = etree.HTML(response.text)    #调用HTML类进行初始化，这样就成功构造了一个XPath解析对象
    w_list = tree.xpath('//html/body/div[@class="Main List"]/dl[@class="Volume"]/dd/a')   #提取每一个a标签的内容
    #<a target="_blank" href="/chapter/3015690/38259921.html" title="第一章 和龙王谈交易
    url = []
    for i in w_list:
        href = i.xpath('./@href')[0]    #提取href标签的内容
        a  = 'http://www.17k.com/'
        html = a + href
        url.append(html)
    return url
html_list = novel()
def write_(html_list):
    b = 0
    for html in html_list:
        res = requests.get(html)
        res.encoding = 'utf8'
        #red = re.compile('<p>(.*?)</p>')
        #result = re.findall(red,rec)
        tree1 = etree.HTML(res.text)
        #b_list = tree1.xpath('//html/body/div[@class="area"]/div[@class="read"]/div[@class="readArea"]/div[@class="readAreaBox content"]/div[@class="p"]/p/text()')  
        b_list = tree1.xpath('//html/body/div[@class="area"]/div[2]/div[2]/div[1]/div[2]/p/text()')  
        txt = str(b_list)
        #print(txt)
        b += 1
        with open('D:\\novel\\'+str(b)+'.txt',mode='w') as f:
            f.write(txt) 

if __name__ == "__main__":
    x = int(len(html_list)/2)
    p1 = multiprocessing.Process(target=write_,args=(html_list[0:x],))
    p2 = multiprocessing.Process(target=write_,args=(html_list[x:],))
    p1.start()
    p2.start()
    p1.join()
    p2.join()
    print("Over")