哈哈网本帖最后由 micfy 于 2022-10-23 09:11 编辑
本代码参考了Quincy_007的帖子
https://www.52pojie.cn/thread-1431173-1-1.html
原代码正常运行，但是一个月的视频最多只有36个，猜测是抖音的返回包限制了数量，因此改进了，以一天为粒度
代码
timepool=list(pd.date_range(start='2022-10-22 00:00:00', end='2022-10-23 00:00:00', freq='D'))
中的start 和end就是起止时间，用的时候记得改一下
应粉丝要求：打包成exe可执行文件，请去
链接：https://pan.baidu.com/s/1vujVg-tylaVIjeFzu3BZ5Q
提取码：52pj
[Python] 纯文本查看 复制代码
import requests[/size]import jsonimport osimport timeimport reimport pandas as pd"""1.根据用户页面分享的字符串提取短url2.根据短url加上302获取location,提取sec_id3.拼接视频列表请求urlparams = { 'sec_uid' : 'MS4wLjABAAAAbtSlJK_BfUcuqyy8ypNouqEH7outUXePTYEcAIpY9rk', 'count' : '200', 'min_cursor' : '1612108800000', 'max_cursor' : '1619251716404', 'aid' : '1128', '_signature' : 'PtCNCgAAXljWCq93QOKsFT7QjR'}"""def delete_boring_characters(sentence): return re.sub('[0-9’!"#$%&\'()*+,-./:;<=>?@，。?★、…【】《》？“”‘’！[\\]^_`{|}~\s]+', "", sentence)headers = {"user-agent": "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Mobile Safari/537.36"}#string = 'https://v.douyin.com/ekkTsYw/' string = input('粘贴分享链接：') shroturl = re.findall('[a-z]+://[\S]+', string, re.I|re.M)[0]print(shroturl)startpage = requests.get(url=shroturl, headers=headers, allow_redirects=False)location = startpage.headers['location']sec_uid = re.findall('(?<=sec_uid=)[a-z，A-Z，0-9, _, -]+', location, re.M|re.I)[0]getname = requests.get(url='https://www.iesdouyin.com/web/api/v2/user/info/?sec_uid={}'.format(sec_uid), headers=headers).textuserinfo = json.loads(getname)name = userinfo['user_info']['nickname']print(userinfo['user_info']['nickname'])Path = nameif os.path.exists(path=Path) == False: os.mkdir(path=Path)else: print('directory exist')os.chdir(path=Path) """new function"""timepool=list(pd.date_range(start='2022-10-22 00:00:00', end='2022-10-23 00:00:00', freq='D'))timepool=list(map(str,timepool))#print(timepool)k = len(timepool)for i in range(k-1) : print('begintime='+timepool[i]) print('endtime='+timepool[i+1]) numstr=timepool[i][0:8] beginarray = time.strptime(timepool[i], "%Y-%m-%d %H:%M:%S") endarray = time.strptime(timepool[i+1], "%Y-%m-%d %H:%M:%S") t1 = int(time.mktime(beginarray) * 1000) t2 = int(time.mktime(endarray) * 1000) #print(t1,t2) params = { 'sec_uid' : sec_uid, 'count' : 200, 'min_cursor' : t1, 'max_cursor' : t2, 'aid' : 1128, '_signature' : 'PtCNCgAAXljWCq93QOKsFT7QjR' } awemeurl = 'https://www.iesdouyin.com/web/api/v2/aweme/post/?' awemehtml = requests.get(url=awemeurl, params=params, headers=headers).text data = https://www.52pojie.cn/json.loads(awemehtml)'aweme_list']) print(awemenum) for j in range(awemenum): print(j) videotitle = data['aweme_list'][j]['desc'].replace("?", "").replace("\"","").replace(":","") videoid = data['aweme_list'][j]['aweme_id'] videourl = data['aweme_list'][j]['video']['play_addr']['url_list'][0] start = time.time() print('{} ===>downloading'.format(videotitle)) print(videoid) with open(videoid+'-'+delete_boring_characters(videotitle)+'.mp4', 'wb') as v: try: v.write(requests.get(url=videourl, headers=headers).content) end = time.time() cost = end - start print('{} ===>downloaded ===>cost {}s'.format(videotitle, cost)) except Exception as e: print('download error')
