爬取抖音视频评论

#fiddlerScript
    static function OnBeforeResponse(oSession: Session) {
        if (m_Hide304s && oSession.responseCode == 304) {
            oSession["ui-hide"] = "true";
        }
        
        
        if (oSession.uriContains("https://www.douyin.com/aweme/v1/web/comment/list")){
            var strBody=oSession.GetResponseBodyAsString();
            //var sps = oSession.PathAndQuery.slice(-58,);
            //FiddlerObject.alert(sps)
            var timestamp=new Date().getTime();
            var filename = "D:/抖音评论资料" + "/"  + 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(); 
        }
        
        
    }

注意需提前建好目录

#python
import os
import json
import csv


class Douyin(object):

    def __init__(self):
        pass

        self.add = 'D:\抖音评论资料'
        self.videos_list = os.listdir('D:\抖音评论资料')

    def parse(self):
        lists = []
        for vid in self.videos_list:
            a = open('D:\抖音评论资料\{}'.format(vid), encoding='utf-8')
            content = json.load(a)
            for con in content['comments']:
                meta = {}
                try:
                    meta['nickname'] = con['user']['nickname']
                    meta['text'] = con['text']
                except:
                    meta['nickname'] = ''
                    meta['text'] = ''
                lists.append(meta)
                # print(meta)
        return lists

    def save_data(self, meta):
        header = ['nickname', 'text']
        print(meta)
        with open('test.csv', 'a', newline='', encoding='utf-8-sig') as f:
            writer = csv.DictWriter(f, fieldnames=header)
            writer.writeheader()  # 写入列名
            writer.writerows(meta)

    def run(self):
        meta = self.parse()
        self.save_data(meta)


if __name__ == '__main__':
    douyin = Douyin()
    douyin.run()

附件地址：

附件为zip压缩包源文件