python 多線程爬取壁紙網站的示例

import threading
import parsel
import requests

def get_html(html_url):
 '''
 獲取網頁源代碼
 :param html_url: 網頁url
 :return:
 '''
 response = requests.get(url=html_url, headers=headers)
 return response


def get_par(html_data):
 '''
 把 response.text 轉換成 selector 對象 解析提取數(shù)據(jù)
 :param html_data: response.text
 :return: selector 對象
 '''
 selector = parsel.Selector(html_data)
 return selector

def download(img_url, title):
 '''
 保存數(shù)據(jù)
 :param img_url: 圖片地址
 :param title: 圖片標題
 :return:
 '''
 content = get_html(img_url).content
 path = '壁紙\\' + title + '.jpg'
 with open(path, mode='wb') as f:
  f.write(content)
  print('正在保存', title)

def main(url):
 '''
 主函數(shù)
 :param url: 列表頁面 url
 :return:
 '''
 html_data = get_html(url).text
 selector = get_par(html_data)
 lis = selector.css('.wb_listbox div dl dd a::attr(href)').getall()
 for li in lis:
  img_data = get_html(li).text
  img_selector = get_par(img_data)
  img_url = img_selector.css('.wb_showpic_main img::attr(src)').get()
  title = img_selector.css('.wb_pictitle::text').get().strip()
  download(img_url, title)
 end_time = time.time() - s_time
 print(end_time)

if __name__ == '__main__':
 for page in range(1, 11):
  url = 'http://www.deskbizhi.com/min/list-{}.html'.format(page)
  main_thread = threading.Thread(target=main, args=(url,))
  main_thread.start()