python爬取网页视频

#coding=gbk
from lxml import etree
import requests
from multiprocessing.dummy import Pool
import random
#@starttime:2021/11/25 10:21
#@endtime:2021/11/25 15:20
if __name__=='__main__':
    # video_down_url = []
    url='https://www.pearvideo.com/'
    header={
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36 Edg/95.0.1020.53'

    }
    respon1=requests.get(url=url,headers=header)
    page_1=respon1.text.encode('utf-8')
    # print(page_1)
    # 写得不太不顺
    page_1_xpa=etree.HTML(page_1)
    # 坚信自己开始的想法并反复尝试(3~4次左右再改变)
    page_1_list=page_1_xpa.xpath('//div[@class="vervideo-bd"]')
    urls = []
    # print(page_1_list)
    for li in page_1_list:
        str1=''.join(li.xpath('./a//@href'))
        # 视频的访问地址
        vedio_adress_1='https://www.pearvideo.com/'+  str1
        header2 = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36 Edg/95.0.1020.53',
            'referer': vedio_adress_1
        }
        id=str1.split('_')[-1]
        #不断地分析网页,得到了它请求时发了两个参数
     
#https://www.pearvideo.com/videoStatus.jsp?contId=1581126mrd=0.09969085979493786
        params={
            'contId':id,
            'mrd':str(random.random())
        }
        vedio_name=''.join(li.xpath('./a/div[2]/text()'))
        # print(vedio_adress_1)
        vedio_page= requests.get(url='https://www.pearvideo.com/videoStatus.jsp',params=params,headers=header2).json()
        url1=vedio_page['videoInfo']['videos']['srcUrl']
        key='cont-'+id
        video_down_url = url1.replace(url1.split('/')[-1].split('-')[0],key)
        # print(video_down_url)
        dic={
            'name':vedio_name,
            'url':video_down_url
        }
        urls.append(dic)
    def get_vedio_data(dic):
        url=dic['url']
        vedio = requests.get(url=url, headers=header).content
        with open(dic['name']+ '.mp4', 'wb') as fp:
            fp.write(vedio)
            print(dic['name'],'下载成功')
    pool=Pool(5)
    pool.map(get_vedio_data,urls)

献给还在梨视频爬取苦苦挣扎的小伙伴,我先往前走了.


上一篇:web-操作方法二次封装


下一篇:spring boot 基于正则的url映射