Python批量爬取抖音主页视频

Python批量爬取抖音主页视频

枫
2023-02-28 / 5 评论 / 237 阅读 / 耗时 202ms / 正在检测是否收录...

介绍

保存路径修改

保存路径自己在这里修改
C[K_{HOL`@F9)WMPLH~)D3D.png

模块导入

所需模块:

cmd 复制输入下面安装命令回车:

浏览器驱动

使用的是谷歌浏览器,查看你自己的浏览器版本,下载对应的驱动器,

驱动器链接:https://registry.npmmirror.com/binary.html?path=chromedriver

效果

K6W}[LSSGX}NIG8HGP1%MT4.png

CW95S0E86E0WARKTY`YZH8T.png

代码

import re
import requests
import time
import os
from selenium import webdriver
#引用模块 selenium==3.141.0

data_url = input('输入你要爬取抖音博主主页链接')
driver= webdriver.Chrome(r'D:\python\chromedriver.exe')
# 引用chromedriver.exe程序,填你自己的路径

driver.get(f'{data_url}')

def drop_down():
    for x in range(1, 30, 4):
        time.sleep(2)
        #延时
        j = x / 9
        js = 'document.documentElement.scrollTop=document.documentElement.scrollHeight * %f'%j
        #下滑
        driver.execute_script(js)

drop_down()


lis = driver.find_elements_by_css_selector('.Eie04v01')
#selenium取值
if not os.path.exists('D:/video/'):
    os.mkdir(('D:/video/'))
for li in lis:
    try:
        url = li.find_element_by_css_selector('a').get_attribute('href')
        #下面路径

        print(url)


        headers ={
            'cookie': 'douyin.com; ttwid=1%7CWi46JI7KdSaF9yqta1kL28XUbEiDv91IIfMOxY-EhZ0%7C1675841330%7C89a9430cc447d8576d53d4fbc9546dfa417bc4e88d586762cbe878514cc1df57; passport_csrf_token=9d7dab91f7a045a68d9fa2deb1f60b0c; passport_csrf_token_default=9d7dab91f7a045a68d9fa2deb1f60b0c; s_v_web_id=verify_ldvcnlvk_10t9slUd_4n0m_42o1_8p9b_8ZRx0cAV4nv5; home_can_add_dy_2_desktop=%220%22; xgplayer_user_id=646767496422; passport_assist_user=CkGmgQ_jszMN1m-PPWYjH_QNdsf_8klBB_8wS0bJsZWcfTnMc97HC73w9WNOnHbLoE1PnrcXtGsuQy6FV7HUCWBMZhpICjxihoJBypQ-JpI9KH--ZN_-TY41fsc-wLsvlbmXM97JsrDcbP2eTP44_kJCdfLHGFu-6P8ZZJ6MfHQMHRAQsrKpDRiJr9ZUIgEDDUbOBg%3D%3D; n_mh=1a3e5XCqMARKIH9Y88jP23zsLolfuhxxp5ZQomXRvOY; sso_uid_tt=c2f6884d45856a3a866e96b167c36a10; sso_uid_tt_ss=c2f6884d45856a3a866e96b167c36a10; toutiao_sso_user=ab04894ee6c7df3eeecec15922d832ea; toutiao_sso_user_ss=ab04894ee6c7df3eeecec15922d832ea; sid_ucp_sso_v1=1.0.0-KDdhNTJmMjRlNmI0Yzg5OWVmNDcxMzllNWFlMWQ1M2M5MTEwNDE1NTYKHwjT1eCOovTiBhCw-bOfBhjvMSAMMKu7iOkFOAZA9AcaAmhsIiBhYjA0ODk0ZWU2YzdkZjNlZWVjZWMxNTkyMmQ4MzJlYQ; ssid_ucp_sso_v1=1.0.0-KDdhNTJmMjRlNmI0Yzg5OWVmNDcxMzllNWFlMWQ1M2M5MTEwNDE1NTYKHwjT1eCOovTiBhCw-bOfBhjvMSAMMKu7iOkFOAZA9AcaAmhsIiBhYjA0ODk0ZWU2YzdkZjNlZWVjZWMxNTkyMmQ4MzJlYQ; odin_tt=fc686e88a993cd8b3c475705e2e286b79bea48c0f1571b1d71907cb4bc263bd8e81c55f29d0d2d82e6f2f828e0f9322ffc9a0c11a8d50f931542468903f614d5; passport_auth_status=f7cba991b8c1ae560c1f55df240d23f4%2C; passport_auth_status_ss=f7cba991b8c1ae560c1f55df240d23f4%2C; uid_tt=4b64917790b6f7fa2f4452c2c2322ae0; uid_tt_ss=4b64917790b6f7fa2f4452c2c2322ae0; sid_tt=052095ac92e67fd17382c560a00588f4; sessionid=052095ac92e67fd17382c560a00588f4; sessionid_ss=052095ac92e67fd17382c560a00588f4; sid_guard=052095ac92e67fd17382c560a00588f4%7C1676475573%7C5183995%7CSun%2C+16-Apr-2023+15%3A39%3A28+GMT; sid_ucp_v1=1.0.0-KGU5MTMzMTcwOTk5OWIyNTQxZTVjZmQ4NTU2YWYwZGQ5ZGZlMDYxOGEKGwjT1eCOovTiBhC1-bOfBhjvMSAMOAZA9AdIBBoCbGYiIDA1MjA5NWFjOTJlNjdmZDE3MzgyYzU2MGEwMDU4OGY0; ssid_ucp_v1=1.0.0-KGU5MTMzMTcwOTk5OWIyNTQxZTVjZmQ4NTU2YWYwZGQ5ZGZlMDYxOGEKGwjT1eCOovTiBhC1-bOfBhjvMSAMOAZA9AdIBBoCbGYiIDA1MjA5NWFjOTJlNjdmZDE3MzgyYzU2MGEwMDU4OGY0; LOGIN_STATUS=1; store-region=cn-hn; store-region-src=uid; douyin.com; strategyABtestKey=%221677080469.918%22; bd_ticket_guard_client_data=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; csrf_session_id=a20f3074e912cd7499eb53ecdc4db1a9; _tea_utm_cache_1243=undefined; MONITOR_WEB_ID=0d0f5307-22e5-4da5-9733-509ce9a07bff; __ac_nonce=063f637ba00a0a8d51802; __ac_signature=_02B4Z6wo00f017RWXlgAAIDDNFSkGepfEH-0dlrAAI7sBLimHJxVv1T5BysGBkNlcpvr3LeKyLCmY4XZwDrZ0jqSxokT6IUn7HfSFn.hlK-QNAZuu532oIbDVIs0LIs4.MYYg6YpRUbfLUFk66; VIDEO_FILTER_MEMO_SELECT=%7B%22expireTime%22%3A1677685307532%2C%22type%22%3A1%7D; tt_scid=77Cu9dRAW7f0mFfa6zzUUQROFT8L1BR0CaDGGuTexi1Q8PTvg7FzDpvupBEHERJq5644; download_guide=%221%2F20230222%22; FOLLOW_LIVE_POINT_INFO=%22MS4wLjABAAAAsvjdwafT6SV5V7SI5uK5KRQj0h2akfJsbUU4Tr9IQ3_wXxWaNlCrcjtqZ2lusCwh%2F1677081600000%2F0%2F0%2F1677081445546%22; FOLLOW_NUMBER_YELLOW_POINT_INFO=%22MS4wLjABAAAAsvjdwafT6SV5V7SI5uK5KRQj0h2akfJsbUU4Tr9IQ3_wXxWaNlCrcjtqZ2lusCwh%2F1677081600000%2F0%2F1677080845546%2F0%22; msToken=1KOGSu7iKfb2VJQJ89TVgUWYYeX3eXGQof9T1ZSz027OKe8TVsgg_okULDbFjWGCq6MUnIo-5aUW6cgPiYGVHZQy1xSFwiE5HoBgl5gh5PrLoGvRpTmtGdJ3hU9-StVk; msToken=FbYQeqlbqNPVPa6dRII68yh3bHHd67y1lWGYIVDyOlYcydKxzxSC80eRqQR2bC_P4W75pjmlT3eZSD2gMMXYmpvA5KweN62l-c_nq7O0iSO6yo0e_KhyglwRWCwESIM=; passport_fe_beating_status=false',
              'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36 Core/1.94.190.400 QQBrowser/11.5.5240.400'
              }

        # url = 'https://www.douyin.com/video/6950985129997126952'
        #测试url

        response = requests.get(url=url,headers=headers)
        response.encoding = 'utf-8'

        title = re.findall('<title data-react-helmet="true">(.*?)</title>',response.text)[0]
        video_title =re.sub('[#@。“”&\- 抖音]','',title)
        #re取视频标题
        data = re.findall('playApi(.*?)playAddrH265',response.text)[0]
        #取加密url
        data_url =requests.utils.unquote(data).replace('","','').replace('":"','https:')
        #解密

        print(video_title,data_url)
        #打印输出标题跟url

        video_url = requests.get(url=data_url,headers=headers).content
        with open('D:/video/'+video_title+'.mp4',mode='wb')as f:
            #文件保存 路径,可自己修改
         f.write(video_url)
    except Exception as e:
        print(e)


9

海报

正在生成.....

评论 (5)

取消
  1. 头像
    32.01hst8vwnr6smmvbgrc309abhp@mail4u.lt
    XX ·MacOS · Safari
    俄罗斯 俄罗斯 沙发

    doloribus ullam dolorem explicabo ipsa commodi quibusdam. quasi nulla qui illum ipsum vel quis.

    Mac OS X 10.15.7   Safari  回复 删除 垃圾
  2. 头像
    light
    上海 ·Windows 10 · Google Chrome
    上海市 电信 上海市 板凳

    代码这里的cookie值要抓取替换吗

    Windows 10   Microsoft Edge  回复 删除 垃圾
    1. 头像
      博主
      XX ·Windows 10 · Google Chrome
      广东省东莞市 移动 广东省
      @ light

      yes

      Windows 10   Microsoft Edge  回复 删除 垃圾
  3. 头像
    light
    ·Windows 10 · Google Chrome
    上海市 电信 上海市 地毯
    该回复疑似异常,已被系统拦截!
    Windows 10   Microsoft Edge  回复 删除 垃圾
    1. 头像
      博主
      XX ·Windows 10 · Google Chrome
      广东省东莞市 移动 广东省
      @ light

      是的,需要你自己抓cookie,代码好久之前写的,我也不确定能不能用,你自己试试

      Windows 10   Microsoft Edge  回复 删除 垃圾