Python批量爬取抖音图集 【失效】

介绍

　　自己捣鼓几个小时写的，我百度搜了，也没什么爬取抖音图集的爬虫，然后就自己写了，此贴只是分享学习心得跟笔记，切勿使用爬虫做违法违规的事情

搞不懂cookie值，跟请求链接是怎么生成的，写完成功一天，就失效了 无语死了

食用方法

　　使用requests跟selenium模块，操作很麻烦，selenium使用的是3.141.0版本的
　　然后下载好的浏览器驱动要放在python解释器同级目录，然后复制这个目录，在代码33行修改

操作方法

　　模块下载跟浏览器驱动下载，

pip install requests

pip install -i https://pypi.doubanio.com/simple/ requests

pip install -i https://pypi.doubanio.com/simple/ selenium==3.141.0

效果

{card-list-item}

{/card-list-item}

代码

"""
只能爬取图集。。
不懂的可以联系1469979950
"""

import re
import requests
import time
import os
from selenium import webdriver
#引用模块 selenium==3.141.0
try:
    data_url = input('输入你要爬取的主页链接(仅爬取图集)>>>')
    cookie =input('输入cookie值(\033[36m第一次爬取可乱输入，按下面提示输入cookie值\033[0m)>>>')
    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'
    }#这个是主页页面请求头

    head ={
           'cookie':cookie,
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36 Edg/113.0.1774.50'
    }#这个是json页面请求头


    data=requests.get(data_url,headers=headers).text
    title =re.findall('<title data-react-helmet="true">(.*?) - 抖音</title>',data)[0]                      #取抖音主页昵称
    introduce=re.findall('<meta data-react-helmet="true" name="description" content="(.*?)"/>',data)[0]   #取主页简介
    zp=re.findall('作品</span><span class="J6IbfgzH" data-e2e="user-tab-count">(.*?)</span>',data)[0]      #取作品数
    print('\033[34m\n===============================================================')                             #打印出信息
    print('|爬取目标：',title)
    print('|主页介绍：',introduce)
    print('|目标主页：',data_url)
    print('|作品总数：',zp)
    print('\033[32m|tips：爬取的时候，切勿关闭浏览器，验证也需要自己过，让浏览器自动下滑到底部，不然图集链接获取不到。\033[0m')
    print('\033[32m|tips：下面遇到报错\033[31mExpecting value: line 1 column 1 (char 0)\033[0m报错，就是cookie失效，需要自己抓取 \n\033[0m')

    print('\033[31m====================== 程序开始运行。。。===========================\033[0m')
except  ValueError:
    print('\033[31m输入链接错误，请输入正确的抖音主页链接\033[0m')
    exit()


driver= webdriver.Chrome(r'D:\python\chromedriver.exe')
# 引用chromedriver.exe程序，填你自己谷歌浏览器驱动路径

statr =time.time()  #计时

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() #页面下滑


lis = driver.find_elements_by_css_selector('.Eie04v01')     #取标签
#selenium取值
# print(lis)
num =1
for li in lis:
    try:
        url = li.find_element_by_css_selector('a').get_attribute('href')    #取作品页面url
        #下面路径
        print('\n=============正在爬取第', zp, '/', num, '个图集作品=============\n')
        print('图集内容：',url)
        url =re.sub('https://www.douyin.com/note/','',url).split()          #id拼接

        num +=1
        for i in url:

            img_url ='https://www.douyin.com/web/api/v2/aweme/iteminfo/?reflow_source=reflow_page&item_ids='+i

            print('\nTEST_JSON：>>>>',img_url)   #打印输出 json url
            print('\t\t\t\t\033[32m点击上面链接跳转浏览器，按开发人员抓取cookie值，然后重新运行程序输入cookie值即可\033[0m')

            data =requests.get(url=img_url,headers=head).json()  #请求json页面取值
            # print(data)
            img = data['item_list'][0]['images']                #取图片url
            name =data['item_list'][0]['desc']                  #取图片标题
            name =re.sub('[\\/:*?<>|\\n#@)\》/\."\/ /《(\r]','',name) #替换特殊字符


            if not os.path.exists(f'D:/image/{name}'):          #判断文件夹是否存在
                os.mkdir((f'D:/image/{name}'))                  #不存在则新建


            for k,j in enumerate(img):                          #取值
                    image =j['url_list'][3]
                    print(name+'_'+str(k),image)
                    data1 =requests.get(url=image,headers=headers).content
                    with open(f'D:/image/{name}/{name}_{k}.jpg',mode='wb')as f:
                        f.write(data1)
    except Exception as e:       #报错跳过执行下一条

        print('第',num,'个图集爬取失败！错误内容：\033[31m',e,'\033[0m')    #输出报错内容
        end =time.time()    #计时
        print('====================================')
        print('\n\n爬取完毕!!!')
try:

    print('程序运行时间：',end - statr,'秒')    #输出程序运行时间
except Exception as e:
    print('\n\033[31m览器加载超时或验证错误，请重新再试\033[0m')

import re
import requests
import os


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'
      }

# get =input('输入你需要爬取的抖音主页')

url = 'https://www.douyin.com/user/MS4wLjABAAAAwN8fRkQsYGvl3T0aF7PRFffd1yM7hDA7DUhNMPMWpaY'
data =requests.get(url=url,headers=headers)
data.encoding = 'utf-8'
# print(data.text)
title = re.findall('<p class="__0w4MvO">(.*?)</p>',data.text)
img =re.findall('<li class="Eie04v01"><div><a href="//(.*?)" class="B3AsdZT9 chmb2GX8"',data.text)
num=1
print(title)
for i in img:
    img_url= 'https://'+i
    print(img_url)

    data =requests.get(url=img_url,headers=headers)
    data.encoding='utf-8'
    # print(data.text)
    img_url=re.findall('<div class="qylGvmT4"><img class="V5BLJkWV" src="(.*?)"',data.text)
    title =re.findall('<h1 class="A_DQnbx8"><span><span class="Nu66P_ba"><span><span><span><span>(.*?)</span></span></span></span></span></span></h1>',data.text)

    for a,c in enumerate(img_url):
        images =re.sub('amp;','',c)

        for b in title:
            if not os.path.exists(f'D:/image/{b}/'):  # 判断文件夹是否存在
                os.mkdir((f'D:/image/{b}/'))
            print(title[0]+f'{a}',images)
            data1 = requests.get(url=images, headers=headers).content
            with open(f'D:/image/{b}/{b}_{a}.jpg', mode='wb') as f:
                f.write(data1)
                num += 1

笔记

　　写个笔记 记录一下知识点

time.time()函数

time.time()  #可用作计时
#例子
statr =time.time()
.......
end =time.time()

print('程序运行时间：',end - statr,'秒')

更换颜色

　　在Python中，可以使用ANSI控制码来实现在终端输出文本时改变字体颜色。下面是一些常用的ANSI控制码：

• "\033[0m"：重置终端颜色设置。
• "\033[30m"：设置字体颜色为黑色。
• "\033[31m"：设置字体颜色为红色。
• "\033[32m"：设置字体颜色为绿色。
• "\033[33m"：设置字体颜色为黄色。
• "\033[34m"：设置字体颜色为蓝色。
• "\033[35m"：设置字体颜色为紫色。
• "\033[36m"：设置字体颜色为青色。
• "\033[37m"：设置字体颜色为白色。
  例如，如果要将输出的文本设置为红色，可以使用以下代码：

print("\033[31mHello World\033[0m")

这将会输出红色的"Hello World"。