爬取视频网站视频并下载

Posted 2021-02-28

import requests import os import json import time import re from retrying import retry """ 爬虫*six room """ def change_title(file): """替换非法字符""" pattern = re.compile(r"[/\:*?"<>|]") file_name = re.sub(pattern,"_",file) return file_name def mp4_download_json(): for pages in range(1,101): print("33[31;1m==========正在抓取第{}页的数据==========33[0m".format(str(pages))) url = "https://v.6.cn/minivideo/getlist.php?act=recommend&page={}&pagesize=20".format(pages) headers = { ‘user-agent‘: ‘Mozilla/5.0 (Linux; android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/78.0.3904.108 Mobile Safari/537.36‘ } response = requests.get(url,headers=headers) html = response.text # print(html) dict_data = json.loads(html) data_list = dict_data[‘content‘][‘list‘] # print(data_list) for data in data_list: time.sleep(1) mp4_url = data[‘playurl‘] response = requests.get(mp4_url,headers=headers) file_name = data[‘title‘] new_filename = change_title(file_name) # print(file_name) if not os.path.exists(new_filename): os.mkdir(new_filename) print("33[31;1m正在下载33[0m %s"%(new_filename)) with open(new_filename +‘/‘+new_filename+‘.mp4‘,‘wb‘) as f: f.write(response.content) print("33[32;1m%s~~~下载完成。33[m "%(new_filename)) if __name__ == "__main__": mp4_download_json()