简单的小爬虫———爬取第一视频网站的视频

直接上代码（pycharm）：

import requests

import os

import re

import urllib.request

from lxmlimport etree

#抓取网页

def get_page(url):

headers={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36'}

response=requests.get(url,headers=headers)

return response.text

#获取视频地址

def get_video_urls(page):

html=etree.HTML(page)

video_urls=html.xpath('//div[@class="tit"]/a/@href')

return video_urls

#下载视频

def download_video(real_url,video_name):

path='E:/py_workspace/video/v1/{}.mp4'.format(video_name)

if not os.path.exists(path):

print('正在下载：{}'.format(video_name))

urllib.request.urlretrieve(real_url,path)

print('{}下载完毕'.format(video_name))

else:

print('已经存在')

pass

if __name__=='__main__':

url='http://www.v1.cn'

    page=get_page(url)

video_urls=get_video_urls(page)

for video_urlin video_urls:

if str(video_url).endswith('.shtml'):

video_url=url+video_url

page=get_page(video_url)

#获取视频的真正地址

            real_url=re.compile(' <param name="FlashVars" value=".*?videoUrl=(.*?)">')

real_url=re.findall(real_url,page)[0]

#获取视频名称

            video_name=re.compile('<h2>(.*?)</h2>')

video_name=re.findall(video_name,page)[0]

#下载视频

            download_video(real_url,video_name)