xpath+多进程爬取八零电子书百合之恋分类下所有小说。

 

代码

# 需要的库
import requests
from lxml import etree
from multiprocessing import pool
import os
# 请求头
headers = {
    'user-agent': 'mozilla/5.0 (windows nt 6.1; wow64) applewebkit/537.36 (khtml, like gecko) chrome/65.0.3325.181 safari/537.36'
}
# 创建存储路径
pathname = './八零电子书/'
if not os.path.exists(pathname):
    os.mkdir(pathname)
# 获取书籍列表
def get_booklist(url):
    try:
        response = requests.get(url=url,headers=headers)
        etrees = etree.html(response.text)
        sum = etrees.xpath('//a[@class="last"]/text()')[0]
        booklist = etrees.xpath('//div[@class="book_bg"]/a/@href')
        pool.map(get_book,booklist)
        urls = ['http://www.quanshuwang.com/list/3_{}.html'.format(i) for i in range(2,int(sum)+1)]
        pool.map(get_booklist,urls)
    except exception:
        print('get_booklist failed')
# 获取具体书籍
def get_book(url):
    try:
        response = requests.get(url=url, headers=headers)
        etrees = etree.html(response.text)
        mulu = etrees.xpath('//a[@id="read_book"]/@href')[1]
        get_mulu(mulu)
    except  exception:
        print('get_book failed')
# 获取书籍目录
def get_mulu(url):
    try:
        response = requests.get(url=url, headers=headers)
        etrees = etree.html(response.text)
        zhangjie = etrees.xpath('//div[@id="yulan"]/li/a/@href')
        for i in zhangjie:
            get_content(i)
    except exception:
        print('get_mulu failed')
# 获取书籍内容
def get_content(url):
    try:
        response = requests.get(url=url, headers=headers)
        etrees = etree.html(response.text.encode(response.encoding).decode(response.apparent_encoding))
        book_name = etrees.xpath('//p[@class="text"]/a/text()')[1]
        zhangjie = etrees.xpath('//div[@class="date"]/h1/text()')[0]
        contents = etrees.xpath('//div[@id="content"]/text()')
        print(zhangjie+'..正在下载')
        f = open(pathname+book_name+'.txt','a+',encoding='utf-8')
        f.write(zhangjie+'\n\n')
        for con in contents:
            f.write(con+'\n')
        f.close()
    except exception:
        print('get_content failed')



# 程序入口
if __name__ == '__main__':
    url = 'https://www.80txt.la/sort5/1.html'
    # 创建进程池
    pool = pool()
    # 启动函数
    get_booklist(url)

控制台输出

e:\anaconda\python.exe e:/练习/最后阶段/0809/八零电子书.py
1第一章 捡到个小雌性..正在下载
01 遗嘱..正在下载
第一章 捡了东西不一定能换到钱..正在下载
2第二章 摔出了地球..正在下载
02 异变..正在下载
3第三章 这是个高科技世界..正在下载
第二章 爷爷！您是我的亲爷爷..正在下载
03 手镯..正在下载
第三章 不在新手村混的新手..正在下载
4第四章 所谓杌力..正在下载
第一章 我会打架..正在下载
04长生..正在下载

打开文件夹查看是否下载成功

done。