爬虫之视频采集实战

视频采集实战1

import requests
from bs4 import BeautifulSoup


# 获取所有视频地址
def get_url():
    # 请求地址
    url = 'http://699pic.com/video-sousuo-0-2-1-200-0-0.html?sem=1&sem_kid=126640&sem_type=2'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    }  
    r = requests.get(url, headers)
    r.encoding = 'UTF-8'
    # print(r.text)   #初学很必要，至少可以看到成功获取了所有网页源代码
    all_video = BeautifulSoup(r.text, 'lxml').select('div.video-box')  # 找到所有属性为video-box的div节点
    j = 0
    num = 1
    for video in all_video:
        video_url = video.select('video')[0].attrs.get('data-original').strip()
        video_url = 'https:' + video_url  # 拼接视频url
        print("video_url=", video_url)
        name = str(num)
        savefile(video_url, name)
        num = num + 1


# 保存视频
def savefile(video_url, name):
    print("开始下载···")
    video = requests.get(video_url)
    file_name = name + '.mp4'
    f = open('E://spider_study//视频' + '/' +
             file_name, 'ab')
    f.write(video.content)
    f.close()
    print('视频下载完成', video_url)

if __name__ == '__main__':
    get_url()