import requests
import parsel,re
import os
target = "https://www.pearvideo.com/videoStatus.jsp"

url = "https://www.pearvideo.com/category_loading.jsp"
res = requests.get(url)
res.encoding="utf-8"
html = parsel.Selector(res.text)
lists = html.xpath('/html/body/li/div/a/@href').getall()
for each in lists:

  print("https://www.pearvideo.com/"+each)

for each in lists:
  url_num = each.replace('video_',"")
  urls = target+url_num
  print(urls)
``

```python
output：
https://www.pearvideo.com/videoStatus.jsp"text-align: center">

恩，很明显，是遇到反爬机制了，这个好搞，要什么给什么就行，代码如下：


	headers = {
  'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36',
  'Referer': 'https://www.pearvideo.com/video_'+ str(url_num)
  }
  html = requests.get(urls,headers=headers).text
  print(html)





搞定！！
最后我们看一下MP4能不能播放：



西八！404！！恩，这里就稍微有点麻烦了，还得找数据，把里面的时间戳改成 ‘cont-数字‘，感觉写了好多，手都有点累了，我就直接上代码了：


import requests
import parsel,re
import os


 
target = "https://www.pearvideo.com/videoStatus.jsp"

url = "https://www.pearvideo.com/category_loading.jsp"
res = requests.get(url)
res.encoding="utf-8"
html = parsel.Selector(res.text)
lists = html.xpath('/html/body/li/div/a/@href').getall()
# print(lists[2:])
# 提取视频后面的数字，数字是最重要的，需要传给 Referer 和 urls
for each in lists:
  url_num = each.replace('video_',"")
  urls = target+url_num
  # print(urls)
  headers = {
  'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36',
  'Referer': 'https://www.pearvideo.com/video_'+ str(url_num)
  }
  html = requests.get(urls,headers=headers).text
  
  cont = 'cont-' + str(url_num)

  # 提取 mp4 视频
  srcUrl = re.findall(f'"srcUrl":"(.*"',html)[0]
  # 替换视频里面的时间戳，改为可以真正播放的数据
  new_url = srcUrl.replace(srcUrl.split("-")[0].split("/")[-1],cont)
  print(new_url)
  

  # 使用视频后缀当视频名称
  filename = srcUrl.split("/")[-1]

  # 保存到本地
  with open("./images/"+filename,"wb") as f:
    f.write(requests.get(new_url).content)



以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。