Python爬虫实例多进程下载金庸网小说

Posted 2020-10-12

目标任务：使用多进程下载金庸网各个版本（旧版、修订版、新修版）的小说

代码如下：

 

# -*- coding: utf-8 -*-
import requests
from lxml import etree
from multiprocessing import Pool
import os
import sys
reload(sys)
sys.setdefaultencoding(‘utf-8‘)

headers = {‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0‘}

def download(title,url, filename):
    response = requests.get(url, headers=headers).text
    html = etree.HTML(response)
    pages = html.xpath(‘//div//p/text()‘)[2:]
    with open(filename, ‘a‘) as f:
            f.write(title+‘\\n‘)
    for page in pages:
        with open(filename, ‘a‘) as f:
            f.write(page+‘\\n‘)


def main(url):
    start_url = ‘http://www.jinyongwang.com‘+url
    sname = start_url.split(‘/‘)[-2]
    if sname.startswith(‘o‘):
        folder = ‘old/‘
        if(not os.path.exists(folder)):
            os.makedirs(folder)
    elif sname.startswith(‘n‘):
        folder = ‘new/‘
        if(not os.path.exists(folder)):
            os.makedirs(folder)
    else:
        folder = ‘now/‘
        if(not os.path.exists(folder)):
            os.makedirs(folder)
    filename = folder+sname+‘.txt‘
    base_url = ‘http://www.jinyongwang.com‘
    response = requests.get(start_url, headers=headers).text
    html = etree.HTML(response)
    urls = html.xpath(‘//ul[@class="mlist"]/li/a/@href‘)
    titles = html.xpath(‘//ul[@class="mlist"]/li//text()‘)
    for index,url in enumerate(urls):
        full_url = base_url+url
        title = titles[index]
        download(title, full_url, filename)

if __name__ == ‘__main__‘:
    url01 = ‘http://www.jinyongwang.com/‘
    response = requests.get(url01, headers=headers).text
    html = etree.HTML(response)
    urls = html.xpath(‘//li[@class="book_li"]/p[3]//a/@href‘)
    pool = Pool()
    pool.map(main,urls)
    pool.close()
    pool.join()

 

结果展示：