Python爬虫之线程池的使用

import time

def func(url):
    print("正在下载：", url)
    time.sleep(2)
    print("下载完成：", url)

if __name__ == '__main__':
    start = time.time() # 开始时间

    url_list = [
        "a", "b", "c"
    ]

    for url in url_list:
        func(url)

    end = time.time() # 结束时间

    print(end - start)

import time
from multiprocessing import Pool

def func(url):
    print("正在下载：", url)
    time.sleep(2)
    print("下载完成：", url)

if __name__ == '__main__':
    start = time.time() # 开始时间

    url_list = [
        "a", "b", "c"
    ]

    pool = Pool(len(url_list)) # 实例化一个线程池对象，并且设定线程池的上限数量为列表长度。不设置上限也可以。

    pool.map(func, url_list)

    end = time.time() # 结束时间

    print(end - start)

import requests
import time
import os
from lxml import etree

def save_photo(url, title):
    # UA伪装
    header = {
        "User-Agent": "Mozilla/5.0 (windows NT 10.0; Win64; x64) AppleWEBKit/537.36 (Khtml, like Gecko) Chrome/90.0.4430.93 Safari/537.36"
    }

    # 发送请求
    photo = requests.get(url=url, headers=header).content

    # 创建路径，避免重复下载
    if not os.path.exists("C:\\Users\\ASUS\\Desktop\\CSDN\\高性能异步爬虫\\线程池\\同步爬虫爬取4K美女图片\\" + title + ".jpg"):
        with open("C:\\Users\\ASUS\\Desktop\\CSDN\\高性能异步爬虫\\线程池\\同步爬虫爬取4K美女图片\\" + title + ".jpg", "wb") as fp:
            print(title, "开始下载！！！")
            fp.write(photo)
            print(title, "下载完成！！！")

if __name__ == '__main__':
    start = time.time()

    # 创建文件夹
    if not os.path.exists("C:\\Users\\ASUS\\Desktop\\CSDN\\高性能异步爬虫\\线程池\\同步爬虫爬取4K美女图片"):
        os.mkdir("C:\\Users\\ASUS\\Desktop\\CSDN\\高性能异步爬虫\\线程池\\同步爬虫爬取4K美女图片")

    # UA伪装
    header = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36"
    }

    # 指定url
    url = "https://pic.netbian.com/4kmeinv/"

    # 发送请求，获取源码
    page = requests.get(url = url, headers = header).text

    # xpath 解析，获取图片的下载地址的列表
    tree = etree.HTML(page)
    url_list = tree.xpath('//*[@id="main"]/div[3]/ul/li/a/@href')
    # 通过下载地址获取高清图片的地址和图片名称
    for href in url_list:
        new_url = "Https://pic.netbian.com" + href
        # 再一次发送请求
        page = requests.get(url = new_url, headers = header).text
        # 再一次 xpath 解析
        new_tree = etree.HTML(page)
        src = "https://pic.netbian.com" + new_tree.xpath('//*[@id="img"]/img/@src')[0]
        title = new_tree.xpath('//*[@id="img"]/img/@title')[0].split(" ")[0]
        # 编译文字
        title = title.encode("iso-8859-1").decode("gbk")
        # 下载，保存
        save_photo(src, title)

    end = time.time()
    print(end - start)

import requests
import time
import os
from lxml import etree
from multiprocessing import Pool

def save_photo(src_title):
    # UA伪装
    header = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36"
    }

    # 发送请求
    url = src_title[0]
    title = src_title[1]
    photo = requests.get(url=url, headers=header).content

    # 创建路径，避免重复下载
    if not os.path.exists("C:\\Users\\ASUS\\Desktop\\CSDN\\高性能异步爬虫\\线程池\\异步爬虫爬取4K美女图片\\" + title + ".jpg"):
        with open("C:\\Users\\ASUS\\Desktop\\CSDN\\高性能异步爬虫\\线程池\\异步爬虫爬取4K美女图片\\" + title + ".jpg", "wb") as fp:
            print(title, "开始下载！！！")
            fp.write(photo)
            print(title, "下载完成！！！")

if __name__ == '__main__':
    start = time.time()

    # 创建文件夹
    if not os.path.exists("C:\\Users\\ASUS\\Desktop\\CSDN\\高性能异步爬虫\\线程池\\异步爬虫爬取4K美女图片"):
        os.mkdir("C:\\Users\\ASUS\\Desktop\\CSDN\\高性能异步爬虫\\线程池\\异步爬虫爬取4K美女图片")

    # UA伪装
    header = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36"
    }

    # 指定url
    url = "https://pic.netbian.com/4kmeinv/"

    # 发送请求，获取源码
    page = requests.get(url = url, headers = header).text

    # xpath 解析，获取图片的下载地址的列表
    tree = etree.HTML(page)
    url_list = tree.xpath('//*[@id="main"]/div[3]/ul/li/a/@href')
    # 存储最后的网址和标题的列表
    src_list = []
    title_list = []
    # 通过下载地址获取高清图片的地址和图片名称
    for href in url_list:
        new_url = "https://pic.netbian.com" + href
        # 再一次发送请求
        page = requests.get(url = new_url, headers = header).text
        # 再一次 xpath 解析
        new_tree = etree.HTML(page)
        src = "https://pic.netbian.com" + new_tree.xpath('//*[@id="img"]/img/@src')[0]
        src_list.append(src)
        title = new_tree.xpath('//*[@id="img"]/img/@title')[0].split(" ")[0]
        # 编译文字
        title = title.encode("iso-8859-1").decode("gbk")
        title_list.append(title)

    # 下载，保存。使用线程池
    pool = Pool()
    src_title = zip(src_list, title_list)
    pool.map(save_photo, list(src_title))

    end = time.time()
    print(end - start)