基于線程池提升request模塊效率的方法

import re
import time
import random
import requests
from lxml import etree

start_time = time.time()

url = "https://www.pearvideo.com/category_3"
headers = {
  "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36"
}

ex = 'srcUrl="(.*?)",vdoUrl=srcUrl'

def request_video(url):
  """
  向視頻鏈接發(fā)送請求
  """
  return requests.get(url=url, headers=headers).content

def save_video(content):
  """
  將視頻的二進(jìn)制數(shù)據(jù)保存到本地
  """
  video_name = str(random.randint(100, 999)) + ".mp4"
  with open(video_name, 'wb') as f:
    f.write(content)

    
# 獲取首頁源碼
page_text = requests.get(url=url, headers=headers).text

tree = etree.HTML(page_text)
li_list = tree.xpath('//ul[@class="listvideo-list clearfix"]/li')

video_url_list = list()
for li in li_list:
  detail_url = "https://www.pearvideo.com/" + li.xpath('./div/a/@href')[0]
  
  # 獲取該視頻頁面的源碼
  detail_page_text = requests.get(url=detail_url, headers=headers).text
  
  # 正則匹配視頻的URL
  video_url = re.findall(ex, detail_page_text, re.S)[0]
  video_url_list.append(video_url)
  
  content = request_video(video_url)
  save_video(content)


print("執(zhí)行耗時: ", time.time() - start_time)

# 使用線程池爬去梨視頻的
import re
import time
import random
import requests
from lxml import etree
from multiprocessing.dummy import Pool


start_time = time.time()

url = "https://www.pearvideo.com/category_3"
headers = {
  "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36"
}

ex = 'srcUrl="(.*?)",vdoUrl=srcUrl'

def request_video(url):
  """
  向視頻鏈接發(fā)送請求
  """
  return requests.get(url=url, headers=headers).content

def save_video(content):
  """
  將視頻的二進(jìn)制數(shù)據(jù)保存到本地
  """
  video_name = str(random.randint(100, 999)) + ".mp4"
  with open(video_name, 'wb') as f:
    f.write(content)

    
# 獲取首頁源碼
page_text = requests.get(url=url, headers=headers).text

tree = etree.HTML(page_text)
li_list = tree.xpath('//ul[@class="listvideo-list clearfix"]/li')

video_url_list = list()
for li in li_list:
  detail_url = "https://www.pearvideo.com/" + li.xpath('./div/a/@href')[0]
  
  # 獲取該視頻頁面的源碼
  detail_page_text = requests.get(url=detail_url, headers=headers).text
  
  # 正則匹配視頻的URL
  video_url = re.findall(ex, detail_page_text, re.S)[0]
  video_url_list.append(video_url)
  
pool = Pool(4)
  
#使用線程池將視頻的二進(jìn)制數(shù)據(jù)下載下來
content_list = pool.map(request_video, video_url_list)
  
# 使用線程池將視頻的二進(jìn)制數(shù)據(jù)保存到本地
pool.map(save_video, content_list)  

print("執(zhí)行耗時: ", time.time() - start_time)