【Python原创】requests-人人视频下载爬虫1.0

Pastwill

一.环境
windwos 10 Python 3.6 x86

二.调用模块

[Python] 纯文本查看 复制代码

import requests
import json
import re
import os

安装命令

[Python] 纯文本查看 复制代码

pip install  requests
pip install json
pip install re
pip install os

三.代码

[Python] 纯文本查看 复制代码

#windows 10 Python 3.6 x86
import requests
import json
import re
import os
headers = {
'Referer':'https://m.rr.tv/',#全局设置
'User-Agent':'Mozilla/5.0 (Linux; Android 11; Pixel 5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.91 Mobile Safari/537.36'
}
ep_list =[]
vod_list = []
def get_vod(url):
    response = requests.get(url = url,headers = headers)#请求url
    ep= re.compile(r'sid:"(.*?)",')#提取ep链接
    ep_list = re.findall(ep,response.text)
    vod= re.compile(r'data:\[{id:(.*?),title:"')#提取vod链接
    vod_list = re.findall(vod,response.text)
    vod= re.compile(r',title:"(.*?)",desc:"')#提取视频标题
    vod_name = re.findall(vod,response.text)
    ep = 1
    os.mkdir('./'+vod_name[0])#创建视频保存目录
    for i in ep_list:
        print("开始下载"+vod_name[0]+"第"+str(ep)+"集")
        url ="https://web-api.rr.tv/web/drama/play?webChannel=M_STATION&dramaId="+vod_list[0]+"&episodeId="+i+"&2-7-17xx"#拼接地址
        response = requests.get(url = url,headers = headers)#下载请求
        r = requests.get(str(json.loads(response.text)['data']['url']), stream=True)#解析出下载链接并发起下载请求
        f = open("./"+vod_name[0]+"/第"+str(ep)+"集.MP4", "wb")#保存视频
        for chunk in r.iter_content(chunk_size=512):
            if chunk:
                f.write(chunk)
        ep = ep+1
if __name__ == '__main__':
    url='https://m.rr.tv/detail/xxxxxx?snum=1&episode=1'#目标视频链接
    get_vod(url)

gusong125

谢谢大佬分享！！！建议搞成多线程，不然好慢！！

Pastwill

gusong125 发表于 2022-2-10 15:40
谢谢大佬分享！！！建议搞成多线程，不然好慢！！

有时间会更新的