import time

def get_page(str):
? ? print("正在下載：",str)
? ? time.sleep(2)
? ? print('下載成功：',str)

name_list = ['aa','bb','cc','dd']

start_time = time.time()

for i in range(len(name_list)):
? ? get_page(name_list[i])
end_time = time.time()
print('%d second'% (end_time-start_time))

import time
# 導(dǎo)入線程池模塊對應(yīng)的類
from multiprocessing.dummy import Pool

start_time = time.time()
def get_page(str):
? ? print("正在下載：",str)
? ? time.sleep(2)
? ? print('下載成功：',str)

name_list = ['aa','bb','cc','dd']

# 實(shí)例化一個線程池對象
pool = Pool(4)
# 將列表中每一個列表元素傳遞給get_page進(jìn)行處理
pool.map(get_page,name_list)

end_time = time.time()
print(end_time-start_time)

# 多線爬蟲示例
import requests
from lxml import etree
import re
from multiprocessing.dummy import Pool

headers = {
? ? 'User-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:80.0) Gecko/20100101 Firefox/80.0',
? ? 'Content-type':'application/json',
}
# 對下述url發(fā)起請求解析出視頻詳情頁的url和視頻的名稱
url = "https://pearvideo.com/category_5"
page_text = requests.get(url=url,headers=headers).text
tree = etree.HTML(page_text)
li_list = tree.xpath('//ul[@id="listvideoListUl"]/li')
urls = [] #存儲所有視頻的鏈接
for li in li_list:
? ? detail_url = 'https://pearvideo.com/' + li.xpath('./div/a/@href')[0]
? ? name = li.xpath('./div/a/div[2]/text()')[0]+'.mp4'
? ? # 對詳情頁的url發(fā)起請求
? ? detail_page_text = requests.get(url=detail_url,headers=headers).text
? ? # print(detail_url,name)
? ? # 從詳情頁中解析出視頻的地址（url）
? ? id = re.findall(r'\d+', detail_url)[0]
# ? ? https://pearvideo.com/videoStatus.jsp?contId=1751458&mrd=0.32392817067398805
? ? detail_vedio_url = 'https://pearvideo.com/videoStatus.jsp?contId='+id

? ? header1s = {
? ? ? ? 'User-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:80.0) Gecko/20100101 Firefox/80.0',
? ? ? ? 'Content-type': 'application/json',
? ? ? ? 'referer':detail_url
? ? }
? ? vedio_text = requests.get(url=detail_vedio_url,headers=header1s).json()
? ? # print(vedio_text)
? ? vedio_url = vedio_text['videoInfo']['videos']['srcUrl']
? ? dic = {
? ? ? ? 'name': name,
? ? ? ? 'url': vedio_url
? ? }
? ? urls.append(dic)
? ? print(vedio_url)
def get_video_data(dic):
? ? url = dic['url']
? ? print(dic['name'],'正在下載......')
? ? data = requests.get(url=url,headers=header1s).content
# ? 持久化存儲操作
? ? with open(dic['name'],'wb') as fp:
? ? ? ? fp.write(data)
? ? ? ? print(dic['name'],'下載成功')
# 使用線程池對視頻數(shù)據(jù)進(jìn)行請求(較為耗時的阻塞操作)
pool = Pool(4)
pool.map(get_video_data,urls)

pool.close()
pool.join()