Python爬虫:fiddler抓取快手
2020-07-25 本文已影响0人
轻语风
Fiddler脚本
if (oSession.uriContains("https://apissl.ksapisrv.com/rest/n/feed/")){
var strBody=oSession.GetResponseBodyAsString()
var timestamp=new Date().getTime()
var filename = "G://software//ks" + "/" + timestamp + ".json";
var curDate = new Date();
var sw : System.IO.StreamWriter;
if (System.IO.File.Exists(filename)){
sw = System.IO.File.AppendText(filename);
sw.Write(strBody);
}
else{ sw = System.IO.File.CreateText(filename);
sw.Write(strBody);
}
sw.Close();
sw.Dispose();
}
注:oSession.uriContains("此处需要修改")
源码奉上
import os,json,requests
# 请求头
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'}
videos_list = os.listdir('G:/software/ks/') #获取文件夹内所有json包名
count = 1 #计数,用来作为视频名字
for videos in videos_list: #循环json列表,对每个json包进行操作
a = open('G:/software/ks/{}'.format(videos),encoding='utf-8') #打开json包
content = json.load(a)['feeds'] #取出json包中所有视频
for video in content: #循环视频列表,选取每个视频
video_url = video['main_mv_urls'][0]['url']
print(video_url)
videoMp4 = requests.get(video_url,headers=headers).content #获取视频二进制代码
with open('G:/software/ks_video/{}.mp4'.format(count),'wb') as f: #以二进制方式写入路径,记住要先创建路径
f.write(videoMp4) #写入
print('视频{}下载完成'.format(count)) #下载提示
count += 1 #计数+1