#注意事项,记得这地视频地址是隐藏的,要在浏览器中打开源码
import urllib.request
import urllib
import re
def getVideo(page):
url = "http://www.budejie.com/video/%s"
req = urllib.request.build_opener()
headers=("User-Agent",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36")
req.addheaders = [headers]
urllib.request.install_opener(req)
html = urllib.request.urlopen(url%page).read()
html = str(html)
reg = r'data-mp4="(.*?)"' #r目的是以原生字符串转义,不会改变类似于"\n"这样的字符串,记得这地视频地址是隐藏的,要在浏览器中打开源码
for i in re.findall(reg, html): #找到视频地址
filename = i.split("/")[-1] #提取出文件名
print ("正在下载%s" %filename)
urllib.request.urlretrieve(i, "D://Test//shipin/%s" %filename) #下载
for i in range(1,21): #以下载前20页为例
getVideo(i)
爬取多页视频并保存本地
最新推荐文章于 2025-04-15 01:45:06 发布