2020-08-28扒视频使用Jupyter notebook+xpathHelper

今日扒取某站成功，使用Jupyter notebook

 

import requests

res=requests.get("someSite/category_8")  

from lxml import etree

res_xpath=etree.HTML(res.text)

import re   

for li in res_xpath.xpath('//ul[@id="categoryList"]/li/div/a/@href'):
    url='https://www.pearvideo.com/' + li
    res=requests.get(url)
    video=re.findall('srcUrl="(.*?)"',res.text,re.S)[0]
    subpage=etree.HTML(res.text)
    title=subpage.xpath('//div[@id="poster"]/img/@alt')[0]
    response=requests.get(video)
    with open( str(title).replace('？','_').replace(' ','').strip()+ '.mp4',mode='wb') as videoFile:
        videoFile.write(response.content)
        print("DownLoad 1 item")  
print("everything done!")