1.Cookie登录
    直接去浏览器F12复制粘贴Cookie即可，只需在headers里面加入”Cookie”

    2.多线程下载
    最方便的多线程调用外部含参方法，每个线程传入的参数都不同

    1. def func(id):
    2.     os.makedirs(out_path+str(id*1000), exist_ok=True)  # 输出目录
    3.     for i in range(id*1000, (id+1)*1000):
    4.         downloadfeed(i, './dynamics/'+str(id*1000)+'/')
    5.         print(str(i))
    7. for i in range(0,16):
    8.     t=threading.Thread(target=func,args=(i,))  # 此处格式需注意
    9.     '''
    10.     target=右边写方法名，不加括号，args=右边写传入方法的参数，最后要多加一个逗号
    11.     '''
    12.     t.start()

    以下完整代码：分了16个线程，分的线程越多，下载速度越快

    1. import os
    2. import requests
    3. import threading
    4. import time
    6. out_path = './dynamics/'
    8. cookie = 'pgv_pvid=1766022180; ptcz=d8ab098bd2c8905001b854755a03c3b97807c29b1d6f0dcf1ce7c0b7397eb355; RK=D+JFl04PN0; ptui_loginuin=1311738213; _qpsvr_localtk=0.44438202147946215; pgv_info=ssid=s9187442548; uin=o1311738213; skey=@VW09dxbUs; qz_screen=1366x768; 1311738213_todaycount=0; 1311738213_totalcount=25636; cpu_performance_v8=28; Loading=Yes; __Q_w_s__QZN_TodoMsgCnt=1; QZ_FE_WEBP_SUPPORT=0; p_uin=o1311738213; pt4_token=BpahtF7G7mhfAwMt-16gXq8WfAM-ywr9v3FTo--9VvM_; p_skey=12hehjj8HdNcNZt3hAmFTmBZF3apwcgcS--PW2bOy0k_'
    10. def download(file_path, url):
    11.     headers = {
    12.         "Cookie": cookie,
    13.         "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36             (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36 QIHU 360SE",
    14.     }
    15.     r = requests.get(url, headers=headers)
    16.     if(len(r.content) > 100):
    17.         with open(file_path, 'wb') as f:
    18.             f.write(r.content)
    20. def downloadfeed(offset, path):
    21.     left_url = 'https://user.qzone.qq.com/proxy/domain/ic2.qzone.qq.com/cgi-bin/feeds/feeds2_html_pav_all?uin=1311738213&begin_time=0&end_time=0&getappnotification=1&getnotifi=1&has_get_key=0&offset='
    22.     right_url = '&set=0&count=10&useutf8=1&outputhtmlfeed=1&grz=0.8910795355675938&scope=1&g_tk=1626987046'
    23.     url = url = left_url + str(offset) + right_url
    24.     file_path = path + str(offset) + '.txt'
    25.     download(file_path, url)
    27. def func(id):
    28.     os.makedirs(out_path+str(id*1000), exist_ok=True)  # 输出目录
    29.     for i in range(id*1000, (id+1)*1000):
    30.         downloadfeed(i, './dynamics/'+str(id*1000)+'/')
    31.         print(str(i))
    33. for i in range(0,16):
    34.     t=threading.Thread(target=func,args=(i,))
    35.     t.start()

    此脚本用于爬取所有QQ空间“关于我的”消息，直接爬到天荒地老。前提是需要先登录。

    原理参考链接：https://www.zhihu.com/question/340649774/answer/1277723623
    简单记录步骤：
    image.png
    打开“关于我的”页面下拉加载，找到上图数据，复制网址修改offset=的值即可，值越大距时间越早