不要犹豫国语版全集,如何当好一把手,今日美丽官网
本文实例为大家分享了python实现抖音视频批量下载的具体代码，供大家参考，具体内容如下
这里就拿最近很火的抖音视频为例，利用api来实现用户抖音视频的批量下载
主要用到的模块有
1、requests模块；
2、bs4模块；
我要评论
import requests
import bs4
import os
import json
import re
import sys
import time
from contextlib import closing
requests.packages.urllib3.disable_warnings()
class spider():
def __init__(self):
self.headers = {
'user-agent': 'mozilla/5.0 (windows nt 10.0; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/65.0.3325.146 safari/537.36'
}
print('[info]:douyin app video downloader...')
print('[version]: v1.0')
print('[author]: charles')
# 外部调用运行
def run(self):
user_id = input('enter the id:')
try:
int(user_id)
except:
print('[error]:id error...')
return
video_names, video_urls, nickname = self._parse_userid(user_id)
if nickname not in os.listdir():
os.mkdir(nickname)
print('[info]:number of videos <%s>' % len(video_urls))
for num in range(len(video_names)):
print('[info]:parsing <no.%d> <url:%s>' % (num+1, video_urls[num]))
temp = video_names[num].replace('\\', '')
video_name = temp.replace('/', '')
self._downloader(video_urls[num], os.path.join(nickname, video_name))
print('\n')
print('[info]:all done...')
# 视频下载
def _downloader(self, video_url, path):
size = 0
download_url = self._get_download_url(video_url)
with closing(requests.get(download_url, headers=self.headers, stream=true, verify=false)) as response:
chunk_size = 1024
content_size = int(response.headers['content-length'])
if response.status_code == 200:
sys.stdout.write('[file size]: %0.2f mb\n' % (content_size/chunk_size/1024))
with open(path, 'wb') as f:
for data in response.iter_content(chunk_size=chunk_size):
f.write(data)
size += len(data)
f.flush()
sys.stdout.write('[progress]: %0.2f%%' % float(size/content_size*100) + '\r')
sys.stdout.flush()
# 获得视频下载地址
def _get_download_url(self, video_url):
res = requests.get(url=video_url, verify=false)
soup = bs4.beautifulsoup(res.text, 'lxml')
script = soup.find_all('script')[-1]
video_url_js = re.findall('var data = \[(.+)\];', str(script))[0]
html = json.loads(video_url_js)
return html['video']['play_addr']['url_list'][0]
# 通过user_id获取该用户发布的所有视频
def _parse_userid(self, user_id):
video_names = []
video_urls = []
unique_id = ''
while unique_id != user_id:
search_url = 'https://api.amemv.com/aweme/v1/discover/search/?keyword={}&count=10&type=1&aid=1128'.format(user_id)
res = requests.get(url=search_url, verify=false)
res_dic = json.loads(res.text)
uid = res_dic['user_list'][0]['user_info']['uid']
aweme_count = res_dic['user_list'][0]['user_info']['aweme_count']
nickname = res_dic['user_list'][0]['user_info']['nickname']
unique_id = res_dic['user_list'][0]['user_info']['unique_id']
user_url = 'https://www.douyin.com/aweme/v1/aweme/post/?user_id={}&max_cursor=0&count={}'.format(uid, aweme_count)
res = requests.get(url=user_url, verify=false)
res_dic = json.loads(res.text)
i = 1
for each in res_dic['aweme_list']:
share_desc = each['share_info']['share_desc']
if '抖音-原创音乐短视频社区' == share_desc:
video_names.append(str(i) + '.mp4')
i += 1
else:
video_names.append(share_desc + '.mp4')
video_urls.append(each['share_info']['share_url'])
return video_names, video_urls, nickname
if __name__ == '__main__':
sp = spider()
sp.run()
以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持移动技术网。
如对本文有疑问，请在下面进行留言讨论，广大热心网友会与你互动！！ 点击进行留言回复
新手学习Python2和Python3中print不同的用法
Python基于os.environ从windows获取环境变量
网友评论