Python之爬虫-酷6视频

Python之爬虫-酷6视频

import re
import requests

"""
@author RansySun
@create 2019-07-20-19:00
"""
# 网站地址
response = requests.get('https://www.ku6.com/index')
data = response.text
"""
<div class="video-image-container">
                    <a class="video-image-warp" target="_blank" href="/video/detail?id=R24vWnh_XhAVchmEcqxVaElqM_o.">
                        <img src="https://rbv01.ku6.com/wifi/o_1dg1e86u616g42te1lhj13ncvptc"></a>
                </div>
"""
# 查找视频链接
result_list = re.findall('<a class="video-image-warp" target="_blank" href="(.*?)">', data)

count = 0
for result in result_list:
    
    # result = result.split(" ")[-1].split('"')[-2] # 单个视频爬
    # print(result)
    if result.startswith('/video'):
        result = f"https://www.ku6.com{result}"
        print(result)
        # 请求视频链接
        result_data = requests.get(result)

        video_data = result_data.text
#       flvURL: "https://rbv01.ku6.com/wifi/o_1dg1e86u6ugk18k69b43ut19kibkvs"
        # 查找视频播放链接
        video_url = re.findall('flvURL: "(.*?)"', video_data)

        for result_url in video_url:
 #          print(result_url)
            # videl_res_url = result_url.split('"')[1] 单个视频
#             print(videl_res_url)
            # 请求视频播放链接
            video_response = requests.get(result_url)
            # 获取视频编码
            video_data = video_response.content
#            # print(video_data)
            # 保存视频
            with open(f"{count}_video.mp4", "wb") as fw:
                fw.write(video_data)
                fw.flush()
                count += 1
                print("成功")

结果：