python爬取梨视频生活板块最热视频-巨人网络通讯

python爬取梨视频生活板块最热视频

完整代码如下：

import requests
from lxml import etree
import random
import os
from multiprocessing.dummy import Pool
 
 
if not os.path.exists('./视频'):
  os.mkdir('./视频')
 
urls=[]
url='https://www.pearvideo.com/category_5'
headers={'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.72 Safari/537.36 Edg/89.0.774.45'}
 
page_text=requests.get(url=url,headers=headers).text
tree=etree.HTML(page_text)
 
li_list=tree.xpath('//ul[@id="listvideoListUl"]/li')
 
for li in li_list:
  a_url='https://www.pearvideo.com/'+li.xpath('./div/a/@href')[0]
  name=li.xpath('./div/a/div[2]/text()')[0]+'.mp4'
 
  mrd=random.random()
  code=li.xpath('./div/a/@href')[0][-7:]  
  new_headers={'Referer': a_url,
         'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36 Edg/89.0.774.50'
         }
  new_url='https://www.pearvideo.com/videoStatus.jsp?contId='+str(code)+'mrd='+str(mrd)
 
  r=requests.get(url=new_url,headers=new_headers) 
  video_url=eval(r.text)['videoInfo']['videos']['srcUrl']
 
    
  old=video_url.split('/')[-1].split('-')[0]  
  new='cont-'+str(code)
  true_video_url=video_url.replace(old,new)
 
 
  dic={'name':name,
     'my_url':true_video_url}
  urls.append(dic)
  
  
#使用线程池对数据视频进行请求
def get_video_data(dic):
  print(dic['name']+'开始下载'+'\n')
  data_url=dic['my_url']
  data=requests.get(url=data_url,headers=headers).content
  with open('./视频/'+dic['name'],'wb') as f:
    f.write(data)
    print(dic['name']+'下载成功')
  
pool=Pool(4)
pool.map(get_video_data,urls)
 
pool.close()
pool.join()

说明：

当前日期（2021/3/14）版本的梨视频的视频伪url由ajax获取。

部分代码解释:

1：模块

import requests                #网路爬虫标准库（代替urllib)
from lxml import etree            #用于解析页面信息
import random                 #梨视频的url中有一段需要随机数
import os                   #主要用于生成文件夹存放视频
from multiprocessing.dummy import Pool    #导入线程池对应类

2：获取视频伪url

#参数准备
mrd=random.random()
code=li.xpath('./div/a/@href')[0][-7:]  
new_headers={
'Referer': a_url,
'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36     (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36 Edg/89.0.774.50'
      }
 
#获取url
new_url='https://www.pearvideo.com/videoStatus.jsp?contId='+str(code)+'mrd='+str(mrd)
r=requests.get(url=new_url,headers=new_headers) 
video_url=eval(r.text)['videoInfo']['videos']['srcUrl']

3：获取真正url

经本人实验，使用上文获得的url爬取视频下载内容为空。

由于本人也是菜鸟，所以百思不得其解，恰巧看到B站用户”_千户”的留言才得知真伪url的差异：

此处视频地址做了加密即ajax中得到的地址需要加上cont-,并且修改一段数字为id才是真地址
真地址："https://video.pearvideo.com/mp4/third/20201120/cont-1708144-10305425-222728-hd.mp4"
伪地址："https://video.pearvideo.com/mp4/third/20201120/1606132035863-10305425-222728-hd.mp4"

#仅需要做几个简单的截取切片操作就可以替换相关内容
 
old=video_url.split('/')[-1].split('-')[0]  
new='cont-'+str(code)
true_video_url=video_url.replace(old,new)

4：存储

#使用线程池对数据视频进行请求
def get_video_data(dic):
  print(dic['name']+'开始下载'+'\n')
  data_url=dic['my_url']
  data=requests.get(url=data_url,headers=headers).content
  with open('./视频/'+dic['name'],'wb') as f:
    f.write(data)
    print(dic['name']+'下载成功')
  
pool=Pool(4)
pool.map(get_video_data,urls)
 
pool.close()
pool.join()

5：结果