1. import re
    2. from multiprocessing.dummy import Pool
    3. import requests
    4. from lxml import etree
    5. headers={
    6.     'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36 QIHU 360S'
    7. }
    9. url='https://www.pearvideo.com/category_5'
    10. page_text=requests.get(url=url,headers=headers).text
    11. tree=etree.HTML(page_text)
    12. li_list=tree.xpath('//ul[@id="listvideoListUl"]/li')
    13. urls=[]
    14. for li in li_list:
    15.     detail_url='https://www.pearvideo.com/'+li.xpath('./div/a/@href')[0]
    16.     name=li.xpath('./div/a/div[2]/text()')[0]+'.mp4'
    17.     detail_page_text=requests.get(url=detail_url,headers=headers).text
    18.     print(detail_page_text)
    19.     ex='srcUrl="(.*?)",vdoUrl'
    20.     video_url=re.findall(ex,detail_page_text)[0]
    21.     dic={
    22.         'name':name,
    23.         'url':video_url
    24.     }
    25.     urls.append(dic)
    26.     print(dic)
    28. def get_viedo_data(url):
    29.     url=dic['url']
    30.     print(dic['name'],'正在下载.......')
    31.     data=requests.get(url=url,headers=headers).content
    32.     with open(dic['name'],'wb') as fp:
    33.         fp.write(dic['name'],'下载成功！！！')
    36. pool=Pool(4)
    37. pool.map(get_viedo_data,urls)
    39. pool.close()
    40. pool.join()