线程池 爬取一本小说

#  本例子 开100线程

import requests
from lxml import etree
from multiprocessing.dummy import Pool  # 线程类
import time

start  = time.time()

url = "https://www.biquge.info/41_41486/"
headers = {
    "user-agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36"
}
page = requests.get(url=url, headers=headers)
page.encoding = 'utf-8'
page_text = page.text
tree = etree.HTML(page_text)
book_name = tree.xpath("//div[@id='info']/h1/text()")[0]  #小说书名
author = tree.xpath("//div[@id='info']/p[1]/text()")[0].replace(' ', '').strip()
book_type = tree.xpath("//div[@id='info']/p[2]/text()")[0].replace(' ', '')
last_update_time = tree.xpath("//div[@id='info']/p[3]/text()")[0].replace(' ', '')
book_info = tree.xpath("//div[@id='intro']/p[1]/text()")[0].replace(' ', '')
info = book_name + '\n' + author + '\n' + book_type + '\n' + last_update_time + '\n' + book_info + '\n'
dd_list = tree.xpath("//div[@id='list']/dl/dd/a/@href")


def func(a):
    res = requests.get(url=f"https://www.biquge.info/41_41486/{a}",headers=headers)
    res.encoding = 'utf-8'
    res = res.text
    tree1 = etree.HTML(res)
    content_data = tree1.xpath('//div[@id="content"]//text()')
    name = tree1.xpath('//*[@id="wrapper"]/div[4]/div/div[2]/h1/text()')[0]  #小说章节
    content = '    ' + '\n'.join(content_data).lstrip()  #小说内容
    return name,content 


f = open(f'./{book_name}.txt','w',encoding='utf-8')
def write_xs(lst):
    for i in lst:
        print(i[0])
        f.write(i[0]+'\n'+i[1])
    f.close()

pool = Pool(100)  #线程池
lst = pool.map(func,dd_list)  #线程池访问页面
write_xs(lst)  #调用写的函数


print(time.time()-start)
print('结束')

 

import requests
from lxml import etree
from multiprocessing.dummy import Pool  # 线程
import time

start  = time.time()

url = "https://www.biquge.info/41_41486/"
headers = {
"user-agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36"
}
page = requests.get(url=url, headers=headers)
page.encoding = 'utf-8'
page_text = page.text
tree = etree.HTML(page_text)
book_name = tree.xpath("//div[@id='info']/h1/text()")[0]
author = tree.xpath("//div[@id='info']/p[1]/text()")[0].replace(' ', '').strip()
book_type = tree.xpath("//div[@id='info']/p[2]/text()")[0].replace(' ', '')
last_update_time = tree.xpath("//div[@id='info']/p[3]/text()")[0].replace(' ', '')
book_info = tree.xpath("//div[@id='intro']/p[1]/text()")[0].replace(' ', '')
info = book_name + '\n' + author + '\n' + book_type + '\n' + last_update_time + '\n' + book_info + '\n'
dd_list = tree.xpath("//div[@id='list']/dl/dd/a/@href")


def func(a):
    res = requests.get(url=f"https://www.biquge.info/41_41486/{a}",headers=headers)
    res.encoding = 'utf-8'
res = res.text
    tree1 = etree.HTML(res)
    content_data = tree1.xpath('//div[@id="content"]//text()')
    name = tree1.xpath('//*[@id="wrapper"]/div[4]/div/div[2]/h1/text()')[0]
    content = '    ' + '\n'.join(content_data).lstrip()
return name,content


f = open(f'./{book_name}.txt','w',encoding='utf-8')
def write_xs(lst):
for i in lst:
print(i[0])
        f.write(i[0]+'\n'+i[1])
    f.close()

pool = Pool(100)
lst = pool.map(func,dd_list)
write_xs(lst)


print(time.time()-start)
print('结束')

转载于:https://www.cnblogs.com/zhangchen-sx/p/10877343.html